acl acl2010 acl2010-231 knowledge-graph by maker-knowledge-mining

231 acl-2010-The Prevalence of Descriptive Referring Expressions in News and Narrative

Source: pdf

Author: Raquel Hervas ; Mark Finlayson

Abstract: Generating referring expressions is a key step in Natural Language Generation. Researchers have focused almost exclusively on generating distinctive referring expressions, that is, referring expressions that uniquely identify their intended referent. While undoubtedly one of their most important functions, referring expressions can be more than distinctive. In particular, descriptive referring expressions those that provide additional information not required for distinction are critical to flu– – ent, efficient, well-written text. We present a corpus analysis in which approximately one-fifth of 7,207 referring expressions in 24,422 words ofnews and narrative are descriptive. These data show that if we are ever to fully master natural language generation, especially for the genres of news and narrative, researchers will need to devote more attention to understanding how to generate descriptive, and not just distinctive, referring expressions. 1 A Distinctive Focus Generating referring expressions is a key step in Natural Language Generation (NLG). From early treatments in seminal papers by Appelt (1985) and Reiter and Dale (1992) to the recent set of Referring Expression Generation (REG) Challenges (Gatt et al., 2009) through different corpora available for the community (Eugenio et al., 1998; van Deemter et al., 2006; Viethen and Dale, 2008), generating referring expressions has become one of the most studied areas of NLG. Researchers studying this area have, almost without exception, focused exclusively on how to generate distinctive referring expressions, that is, referring expressions that unambiguously idenMark Alan Finlayson Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge, MA, 02139 USA markaf@mit .edu tify their intended referent. Referring expressions, however, may be more than distinctive. It is widely acknowledged that they can be used to achieve multiple goals, above and beyond distinction. Here we focus on descriptive referring expressions, that is, referring expressions that are not only distinctive, but provide additional information not required for identifying their intended referent. Consider the following text, in which some of the referring expressions have been underlined: Once upon a time there was a man, who had three daughters. They lived in a house and their dresses were made of fabric. While a bit strange, the text is perfectly wellformed. All the referring expressions are distinctive, in that we can properly identify the referents of each expression. But the real text, the opening lines to the folktale The Beauty and the Beast, is actually much more lyrical: Once upon a time there was a rich merchant, who had three daughters. They lived in a very fine house and their gowns were made of the richest fabric sewn with jewels. All the boldfaced portions namely, the choice of head nouns, the addition of adjectives, the use of appositive phrases serve to perform a descriptive function, and, importantly, are all unnecessary for distinction! In all of these cases, the author is using the referring expressions as a vehicle for communicating information about the referents. This descriptive information is sometimes – – new, sometimes necessary for understanding the text, and sometimes just for added flavor. But when the expression is descriptive, as opposed to distinctive, this additional information is not required for identifying the referent of the expression, and it is these sorts of referring expressions that we will be concerned with here. 49 Uppsala,P Srwoce de dni,n 1g1s- 1of6 t Jhuely AC 20L1 20 .1 ?0c 2 C0o1n0fe Aresnsoceci Sathio rnt f Poarp Ceorsm,p paugteastio 4n9a–l5 L4i,nguistics Although these sorts of referring expression have been mostly ignored by researchers in this area1 , we show in this corpus study that descriptive expressions are in fact quite prevalent: nearly one-fifth of referring expressions in news and narrative are descriptive. In particular, our data, the trained judgments of native English speakers, show that 18% of all distinctive referring expressions in news and 17% of those in narrative folktales are descriptive. With this as motivation, we argue that descriptive referring expressions must be studied more carefully, especially as the field progresses from referring in a physical, immediate context (like that in the REG Challenges) to generating more literary forms of text. 2 Corpus Annotation This is a corpus study; our procedure was therefore to define our annotation guidelines (Section 2.1), select texts to annotate (2.2), create an annotation tool for our annotators (2.3), and, finally, train annotators, have them annotate referring expressions’ constituents and function, and then adjudicate the double-annotated texts into a gold standard (2.4). 2.1 Definitions We wrote an annotation guide explaining the difference between distinctive and descriptive referring expressions. We used the guide when training annotators, and it was available to them while annotating. With limited space here we can only give an outline of what is contained in the guide; for full details see (Finlayson and Herv a´s, 2010a). Referring Expressions We defined referring expressions as referential noun phrases and their coreferential expressions, e.g., “John kissed Mary. She blushed.”. This included referring expressions to generics (e.g., “Lions are fierce”), dates, times, and numbers, as well as events if they were referred to using a noun phrase. We included in each referring expression all the determiners, quantifiers, adjectives, appositives, and prepositional phrases that syntactically attached to that expression. When referring expressions were nested, all the nested referring expressions were also marked separately. Nuclei vs. Modifiers In the only previous corpus study of descriptive referring expressions, on 1With the exception of a small amount of work, discussed in Section 4. museum labels, Cheng et al. (2001) noted that descriptive information is often integrated into referring expressions using modifiers to the head noun. To study this, and to allow our results to be more closely compared with Cheng’s, we had our annotators split referring expressions into their constituents, portions called either nuclei or modifiers. The nuclei were the portions of the referring expression that performed the ‘core’ referring function; the modifiers were those portions that could be varied, syntactically speaking, independently of the nuclei. Annotators then assigned a distinctive or descriptive function to each constituent, rather than the referring expression as a whole. Normally, the nuclei corresponded to the head of the noun phrase. In (1), the nucleus is the token king, which we have here surrounded with square brackets. The modifiers, surrounded by parentheses, are The and old. (1) (The) (old) [king] was wise. Phrasal modifiers were marked as single modifiers, for example, in (2). (2) (The) [roof] (of the house) collapsed. It is significant that we had our annotators mark and tag the nuclei of referring expressions. Cheng and colleagues only mentioned the possibility that additional information could be introduced in the modifiers. However, O’Donnell et al. (1998) observed that often the choice of head noun can also influence the function of a referring expression. Consider (3), in which the word villain is used to refer to the King. (3) The King assumed the throne today. I ’t trust (that) [villain] one bit. don The speaker could have merely used him to refer to the King–the choice of that particular head noun villain gives us additional information about the disposition of the speaker. Thus villain is descriptive. Function: Distinctive vs. Descriptive As already noted, instead of tagging the whole referring expression, annotators tagged each constituent (nuclei and modifiers) as distinctive or descriptive. The two main tests for determining descriptiveness were (a) if presence of the constituent was unnecessary for identifying the referent, or (b) if 50 the constituent was expressed using unusual or ostentatious word choice. If either was true, the constituent was considered descriptive; otherwise, it was tagged as distinctive. In cases where the constituent was completely irrelevant to identifying the referent, it was tagged as descriptive. For example, in the folktale The Princess and the Pea, from which (1) was extracted, there is only one king in the entire story. Thus, in that story, the king is sufficient for identification, and therefore the modifier old is descriptive. This points out the importance of context in determining distinctiveness or descriptiveness; if there had been a roomful of kings, the tags on those modifiers would have been reversed. There is some question as to whether copular predicates, such as the plumber in (4), are actually referring expressions. (4) John is the plumber Our annotators marked and tagged these constructions as normal referring expressions, but they added an additional flag to identify them as copular predicates. We then excluded these constructions from our final analysis. Note that copular predicates were treated differently from appositives: in appositives the predicate was included in the referring expression, and in most cases (again, depending on context) was marked descriptive (e.g., John, the plumber, slept.). 2.2 Text Selection Our corpus comprised 62 texts, all originally written in English, from two different genres, news and folktales. We began with 30 folktales of different sizes, totaling 12,050 words. These texts were used in a previous work on the influence of dialogues on anaphora resolution algorithms (Aggarwal et al., 2009); they were assembled with an eye toward including different styles, different authors, and different time periods. Following this, we matched, approximately, the number of words in the folktales by selecting 32 texts from Wall Street Journal section of the Penn Treebank (Marcus et al., 1993). These texts were selected at ran- dom from the first 200 texts in the corpus. 2.3 The Story Workbench We used the Story Workbench application (Finlayson, 2008) to actually perform the annotation. The Story Workbench is a semantic annotation program that, among other things, includes the ability to annotate referring expressions and coreferential relationships. We added the ability to annotate nuclei, modifiers, and their functions by writing a workbench “plugin” in Java that could be installed in the application. The Story Workbench is not yet available to the public at large, being in a limited distribution beta testing phase. The developers plan to release it as free software within the next year. At that time, we also plan to release our plugin as free, downloadable software. 2.4 Annotation & Adjudication The main task of the study was the annotation of the constituents of each referring expression, as well as the function (distinctive or descriptive) of each constituent. The system generated a first pass of constituent analysis, but did not mark functions. We hired two native English annotators, neither of whom had any linguistics background, who corrected these automatically-generated constituent analyses, and tagged each constituent as descriptive or distinctive. Every text was annotated by both annotators. Adjudication of the differences was conducted by discussion between the two annotators; the second author moderated these discussions and settled irreconcilable disagreements. We followed a “train-as-you-go” paradigm, where there was no distinct training period, but rather adjudication proceeded in step with annotation, and annotators received feedback during those sessions. We calculated two measures of inter-annotator agreement: a kappa statistic and an f-measure, shown in Table 1. All of our f-measures indicated that annotators agreed almost perfectly on the location of referring expressions and their breakdown into constituents. These agreement calculations were performed on the annotators’ original corrected texts. All the kappa statistics were calculated for two tags (nuclei vs. modifier for the constituents, and distinctive vs. descriptive for the functions) over both each token assigned to a nucleus or modifier and each referring expression pair. Our kappas indicate moderate to good agreement, especially for the folktales. These results are expected because of the inherent subjectivity of language. During the adjudication sessions it became clear that different people do not consider the same information 51 as obvious or descriptive for the same concepts, and even the contexts deduced by each annotators from the texts were sometimes substantially different. 3 Results Table 2 lists the primary results of the study. We considered a referring expression descriptive if any of its constituents were descriptive. Thus, 18% of the referring expressions in the corpus added additional information beyond what was required to unambiguously identify their referent. The results were similar in both genres. Tales Articles Total Texts303262 Words Sentences 12,050 904 12,372 571 24,422 1,475 Ref. Exp.3,6813,5267,207 Dist. Ref. Exp. 3,057 2,830 5,887 Desc. Ref. Exp. 609 672 1,281 % Dist. Ref.83%81%82% % Desc. Ref. 17% 19% Table 2: Primary results. 18% Table 3 contains the percentages of descriptive and distinctive tags broken down by constituent. Like Cheng’s results, our analysis shows that descriptive referring expressions make up a significant fraction of all referring expressions. Although Cheng did not examine nuclei, our results show that the use of descriptive nuclei is small but not negligible. 4 Relation to the Field Researchers working on generating referring expressions typically acknowledge that referring expressions can perform functions other than distinction. Despite this widespread acknowledgment, researchers have, for the most part, explicitly ignored these functions. Exceptions to this trend Tales Articles Total Nuclei3,6663,5027,168 Max. Nuc/Ref Dist. Nuc. 1 95% 1 97% 1 96% Desc. Nuc. 5% 3% 4% Modifiers2,2773,6275,904 Avg. Mod/Ref Max. Mod/Ref Dist. Mod. Desc. Mod. 0.6 4 78% 22% 1.0 6 81% 19% 0.8 6 80% 20% Table 3: Breakdown of Constituent Tags are three. First is the general study of aggregation in the process of referring expression generation. Second and third are corpus studies by Cheng et al. (2001) and Jordan (2000a) that bear on the prevalence of descriptive referring expressions. The NLG subtask of aggregation can be used to imbue referring expressions with a descriptive function (Reiter and Dale, 2000, §5.3). There is a specific nk (iRned otefr aggregation 0c0al0le,d § embedding t ihsa at moves information from one clause to another inside the structure of a separate noun phrase. This type of aggregation can be used to transform two sentences such as “The princess lived in a castle. She was pretty ” into “The pretty princess lived in a castle ”. The adjective pretty, previously a cop- ular predicate, becomes a descriptive modifier of the reference to the princess, making the second text more natural and fluent. This kind of aggregation is widely used by humans for making the discourse more compact and efficient. In order to create NLG systems with this ability, we must take into account the caveat, noted by Cheng (1998), that any non-distinctive information in a referring expression must not lead to confusion about the distinctive function of the referring expression. This is by no means a trivial problem this sort of aggregation interferes with referring and coherence planning at both a local and global level (Cheng and Mellish, 2000; Cheng et al., 2001). It is clear, from the current state of the art of NLG, that we have not yet obtained a deep enough understanding of aggregation to enable us to handle these interactions. More research on the topic is needed. Two previous corpus studies have looked at the use of descriptive referring expressions. The first showed explicitly that people craft descriptive referring expressions to accomplish different – 52 goals. Jordan and colleagues (Jordan, 2000b; Jordan, 2000a) examined the use of referring expressions using the COCONUT corpus (Eugenio et al., 1998). They tested how domain and discourse goals can influence the content of non-pronominal referring expressions in a dialogue context, checking whether or not a subject’s goals led them to include non-referring information in a referring expression. Their results are intriguing because they point toward heretofore unexamined constraints, utilities and expectations (possibly genre- or styledependent) that may underlie the use ofdescriptive information to perform different functions, and are not yet captured by aggregation modules in particular or NLG systems in general. In the other corpus study, which partially inspired this work, Cheng and colleagues analyzed a set of museum descriptions, the GNOME corpus (Poesio, 2004), for the pragmatic functions of referring expressions. They had three functions in their study, in contrast to our two. Their first function (marked by their uniq tag) was equiv- alent to our distinctive function. The other two were specializations of our descriptive tag, where they differentiated between additional information that helped to understand the text (int), or additional information not necessary for understanding (att r). Despite their annotators seeming to have trouble distinguishing between the latter two tags, they did achieve good overall inter-annotator agreement. They identified 1,863 modifiers to referring expressions in their corpus, of which 47.3% fulfilled a descriptive (att r or int) function. This is supportive of our main assertion, namely, that descriptive referring expressions, not only crucial for efficient and fluent text, are actually a significant phenomenon. It is interesting, though, that Cheng’s fraction of descriptive referring expression was so much higher than ours (47.3% versus our 18%). We attribute this substantial difference to genre, in that Cheng studied museum labels, in which the writer is spaceconstrained, having to pack a lot of information into a small label. The issue bears further study, and perhaps will lead to insights into differences in writing style that may be attributed to author or genre. 5 Contributions We make two contributions in this paper. First, we assembled, double-annotated, and adjudicated into a gold-standard a corpus of 24,422 words. We marked all referring expressions, coreferential relations, and referring expression constituents, and tagged each constituent as having a descriptive or distinctive function. We wrote an annotation guide and created software that allows the annotation of this information in free text. The corpus and the guide are available on-line in a permanent digital archive (Finlayson and Herv a´s, 2010a; Finlayson and Herv a´s, 2010b). The software will also be released in the same archive when the Story Workbench annotation application is released to the public. This corpus will be useful for the automatic generation and analysis of both descriptive and distinctive referring expressions. Any kind of system intended to generate text as humans do must take into account that identifica- tion is not the only function of referring expressions. Many analysis applications would benefit from the automatic recognition of descriptive referring expressions. Second, we demonstrated that descriptive referring expressions comprise a substantial fraction (18%) of the referring expressions in news and narrative. Along with museum descriptions, studied by Cheng, it seems that news and narrative are genres where authors naturally use a large number ofdescriptive referring expressions. Given that so little work has been done on descriptive referring expressions, this indicates that the field would be well served by focusing more attention on this phenomenon. Acknowledgments This work was supported in part by the Air Force Office of Scientific Research under grant number A9550-05-1-0321, as well as by the Office of Naval Research under award number N00014091059. Any opinions, findings, and con- clusions or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of the Office of Naval Research. This research is also partially funded the Spanish Ministry of Education and Science (TIN200914659-C03-01) and Universidad Complutense de Madrid (GR58/08). We also thank Whitman Richards, Ozlem Uzuner, Peter Szolovits, Patrick Winston, Pablo Gerv a´s, and Mark Seifter for their helpful comments and discussion, and thank our annotators Saam Batmanghelidj and Geneva Trotter. 53 References Alaukik Aggarwal, Pablo Gerv a´s, and Raquel Herv a´s. 2009. Measuring the influence of errors induced by the presence of dialogues in reference clustering of narrative text. In Proceedings of ICON-2009: 7th International Conference on Natural Language Processing, India. Macmillan Publishers. Douglas E. Appelt. 1985. Planning English referring expressions. Artificial Intelligence, 26: 1–33. Hua Cheng and Chris Mellish. 2000. Capturing the interaction between aggregation and text planning in two generation systems. In INLG ’00: First international conference on Natural Language Generation 2000, pages 186–193, Morristown, NJ, USA. Association for Computational Linguistics. Hua Cheng, Massimo Poesio, Renate Henschel, and Chris Mellish. 2001 . Corpus-based np modifier generation. In NAACL ’01: Second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies 2001, pages 1–8, Morristown, NJ, USA. Association for Computational Linguistics. Hua Cheng. 1998. Embedding new information into referring expressions. In ACL-36: Proceedings of the 36thAnnual Meeting ofthe Associationfor Computational Linguistics and 17th International Conference on Computational Linguistics, pages 1478– 1480, Morristown, NJ, USA. Association for Computational Linguistics. Barbara Di Eugenio, Johanna D. Moore, Pamela W. Jordan, and Richmond H. Thomason. 1998. An empirical investigation of proposals in collaborative dialogues. In Proceedings of the 17th international conference on Computational linguistics, pages 325–329, Morristown, NJ, USA. Association for Computational Linguistics. Mark A. Finlayson and Raquel Herv a´s. 2010a. Annotation guide for the UCM/MIT indications, referring expressions, and coreference corpus (UMIREC corpus). Technical Report MIT-CSAIL-TR-2010-025, MIT Computer Science and Artificial Intelligence Laboratory. http://hdl.handle.net/1721. 1/54765. Mark A. Finlayson and Raquel Herv a´s. 2010b. UCM/MIT indications, referring expressions, and coreference corpus (UMIREC corpus). Work product, MIT Computer Science and Artificial Intelligence Laboratory. http://hdl.handle.net/1721 .1/54766. Mark A. Finlayson. 2008. Collecting semantics in the wild: The Story Workbench. In Proceedings of the AAAI Fall Symposium on Naturally-Inspired Artificial Intelligence, pages 46–53, Menlo Park, CA, USA. AAAI Press. Albert Gatt, Anja Belz, and Eric Kow. 2009. The TUNA-REG challenge 2009: overview and evaluation results. In ENLG ’09: Proceedings of the 12th European Workshop on Natural Language Generation, pages 174–182, Morristown, NJ, USA. Association for Computational Linguistics. Pamela W. Jordan. 2000a. Can nominal expressions achieve multiple goals?: an empirical study. In ACL ’00: Proceedings of the 38th Annual Meeting on Association for Computational Linguistics, pages 142– 149, Morristown, NJ, USA. Association for Computational Linguistics. Pamela W. Jordan. 2000b. Influences on attribute selection in redescriptions: A corpus study. In Proceedings of CogSci2000, pages 250–255. Mitchell P. Marcus, Mary Ann Marcinkiewicz, and Beatrice Santorini. 1993. Building a large annotated corpus of english: the penn treebank. Computational Linguistics, 19(2):3 13–330. Michael O’Donnell, Hua Cheng, and Janet Hitzeman. 1998. Integrating referring and informing in NP planning. In Proceedings of COLING-ACL’98 Workshop on the Computational Treatment of Nominals, pages 46–56. Massimo Poesio. 2004. Discourse annotation and semantic annotation in the GNOME corpus. In DiscAnnotation ’04: Proceedings of the 2004 ACL Workshop on Discourse Annotation, pages 72–79, Morristown, NJ, USA. Association for Computational Linguistics. Ehud Reiter and Robert Dale. 1992. A fast algorithm for the generation of referring expressions. In Proceedings of the 14th conference on Computational linguistics, Nantes, France. Ehud Reiter and Robert Dale. 2000. Building Natural Language Generation Systems. Cambridge University Press. Kees van Deemter, Ielka van der Sluis, and Albert Gatt. 2006. Building a semantically transparent corpus for the generation of referring expressions. In Proceedings of the 4th International Conference on Natural Language Generation (Special Session on Data Sharing and Evaluation), INLG-06. Jette Viethen and Robert Dale. 2008. The use of spatial relations in referring expressions. In Proceedings of the 5th International Conference on Natural Language Generation. 54

Reference: text

Summary: the most important sentenses genereted by tfidf model

sentIndex sentText sentNum sentScore

1 e s Abstract Generating referring expressions is a key step in Natural Language Generation. [sent-3, score-0.909]

2 Researchers have focused almost exclusively on generating distinctive referring expressions, that is, referring expressions that uniquely identify their intended referent. [sent-4, score-1.839]

3 While undoubtedly one of their most important functions, referring expressions can be more than distinctive. [sent-5, score-0.909]

4 In particular, descriptive referring expressions those that provide additional information not required for distinction are critical to flu– – ent, efficient, well-written text. [sent-6, score-1.276]

5 We present a corpus analysis in which approximately one-fifth of 7,207 referring expressions in 24,422 words ofnews and narrative are descriptive. [sent-7, score-0.986]

6 These data show that if we are ever to fully master natural language generation, especially for the genres of news and narrative, researchers will need to devote more attention to understanding how to generate descriptive, and not just distinctive, referring expressions. [sent-8, score-0.734]

7 1 A Distinctive Focus Generating referring expressions is a key step in Natural Language Generation (NLG). [sent-9, score-0.909]

8 , 2006; Viethen and Dale, 2008), generating referring expressions has become one of the most studied areas of NLG. [sent-13, score-0.956]

9 Here we focus on descriptive referring expressions, that is, referring expressions that are not only distinctive, but provide additional information not required for identifying their intended referent. [sent-18, score-1.94]

10 Consider the following text, in which some of the referring expressions have been underlined: Once upon a time there was a man, who had three daughters. [sent-19, score-0.909]

11 They lived in a house and their dresses were made of fabric. [sent-20, score-0.087]

12 All the referring expressions are distinctive, in that we can properly identify the referents of each expression. [sent-22, score-0.909]

13 They lived in a very fine house and their gowns were made of the richest fabric sewn with jewels. [sent-24, score-0.087]

14 All the boldfaced portions namely, the choice of head nouns, the addition of adjectives, the use of appositive phrases serve to perform a descriptive function, and, importantly, are all unnecessary for distinction! [sent-25, score-0.433]

15 In all of these cases, the author is using the referring expressions as a vehicle for communicating information about the referents. [sent-26, score-0.909]

16 This descriptive information is sometimes – – new, sometimes necessary for understanding the text, and sometimes just for added flavor. [sent-27, score-0.433]

17 But when the expression is descriptive, as opposed to distinctive, this additional information is not required for identifying the referent of the expression, and it is these sorts of referring expressions that we will be concerned with here. [sent-28, score-1.06]

18 In particular, our data, the trained judgments of native English speakers, show that 18% of all distinctive referring expressions in news and 17% of those in narrative folktales are descriptive. [sent-32, score-1.318]

19 With this as motivation, we argue that descriptive referring expressions must be studied more carefully, especially as the field progresses from referring in a physical, immediate context (like that in the REG Challenges) to generating more literary forms of text. [sent-33, score-1.96]

20 3), and, finally, train annotators, have them annotate referring expressions’ constituents and function, and then adjudicate the double-annotated texts into a gold standard (2. [sent-37, score-0.741]

21 1 Definitions We wrote an annotation guide explaining the difference between distinctive and descriptive referring expressions. [sent-40, score-1.357]

22 Referring Expressions We defined referring expressions as referential noun phrases and their coreferential expressions, e. [sent-43, score-0.949]

23 We included in each referring expression all the determiners, quantifiers, adjectives, appositives, and prepositional phrases that syntactically attached to that expression. [sent-51, score-0.721]

24 When referring expressions were nested, all the nested referring expressions were also marked separately. [sent-52, score-1.847]

25 Modifiers In the only previous corpus study of descriptive referring expressions, on 1With the exception of a small amount of work, discussed in Section 4. [sent-54, score-1.004]

26 (2001) noted that descriptive information is often integrated into referring expressions using modifiers to the head noun. [sent-56, score-1.354]

27 To study this, and to allow our results to be more closely compared with Cheng’s, we had our annotators split referring expressions into their constituents, portions called either nuclei or modifiers. [sent-57, score-1.21]

28 The nuclei were the portions of the referring expression that performed the ‘core’ referring function; the modifiers were those portions that could be varied, syntactically speaking, independently of the nuclei. [sent-58, score-1.684]

29 Annotators then assigned a distinctive or descriptive function to each constituent, rather than the referring expression as a whole. [sent-59, score-1.33]

30 Normally, the nuclei corresponded to the head of the noun phrase. [sent-60, score-0.164]

31 Phrasal modifiers were marked as single modifiers, for example, in (2). [sent-64, score-0.107]

32 It is significant that we had our annotators mark and tag the nuclei of referring expressions. [sent-66, score-0.896]

33 (1998) observed that often the choice of head noun can also influence the function of a referring expression. [sent-69, score-0.637]

34 Consider (3), in which the word villain is used to refer to the King. [sent-70, score-0.075]

35 don The speaker could have merely used him to refer to the King–the choice of that particular head noun villain gives us additional information about the disposition of the speaker. [sent-73, score-0.075]

36 Descriptive As already noted, instead of tagging the whole referring expression, annotators tagged each constituent (nuclei and modifiers) as distinctive or descriptive. [sent-76, score-1.076]

37 The two main tests for determining descriptiveness were (a) if presence of the constituent was unnecessary for identifying the referent, or (b) if 50 the constituent was expressed using unusual or ostentatious word choice. [sent-77, score-0.196]

38 If either was true, the constituent was considered descriptive; otherwise, it was tagged as distinctive. [sent-78, score-0.102]

39 In cases where the constituent was completely irrelevant to identifying the referent, it was tagged as descriptive. [sent-79, score-0.102]

40 For example, in the folktale The Princess and the Pea, from which (1) was extracted, there is only one king in the entire story. [sent-80, score-0.089]

41 Thus, in that story, the king is sufficient for identification, and therefore the modifier old is descriptive. [sent-81, score-0.092]

42 This points out the importance of context in determining distinctiveness or descriptiveness; if there had been a roomful of kings, the tags on those modifiers would have been reversed. [sent-82, score-0.1]

43 There is some question as to whether copular predicates, such as the plumber in (4), are actually referring expressions. [sent-83, score-0.738]

44 (4) John is the plumber Our annotators marked and tagged these constructions as normal referring expressions, but they added an additional flag to identify them as copular predicates. [sent-84, score-0.897]

45 Note that copular predicates were treated differently from appositives: in appositives the predicate was included in the referring expression, and in most cases (again, depending on context) was marked descriptive (e. [sent-86, score-1.12]

46 Following this, we matched, approximately, the number of words in the folktales by selecting 32 texts from Wall Street Journal section of the Penn Treebank (Marcus et al. [sent-95, score-0.089]

47 The Story Workbench is a semantic annotation program that, among other things, includes the ability to annotate referring expressions and coreferential relationships. [sent-100, score-1.019]

48 We added the ability to annotate nuclei, modifiers, and their functions by writing a workbench “plugin” in Java that could be installed in the application. [sent-101, score-0.16]

49 4 Annotation & Adjudication The main task of the study was the annotation of the constituents of each referring expression, as well as the function (distinctive or descriptive) of each constituent. [sent-106, score-0.722]

50 We hired two native English annotators, neither of whom had any linguistics background, who corrected these automatically-generated constituent analyses, and tagged each constituent as descriptive or distinctive. [sent-108, score-0.536]

51 We followed a “train-as-you-go” paradigm, where there was no distinct training period, but rather adjudication proceeded in step with annotation, and annotators received feedback during those sessions. [sent-111, score-0.17]

52 All of our f-measures indicated that annotators agreed almost perfectly on the location of referring expressions and their breakdown into constituents. [sent-113, score-1.053]

53 descriptive for the functions) over both each token assigned to a nucleus or modifier and each referring expression pair. [sent-117, score-1.159]

54 During the adjudication sessions it became clear that different people do not consider the same information 51 as obvious or descriptive for the same concepts, and even the contexts deduced by each annotators from the texts were sometimes substantially different. [sent-120, score-0.592]

55 We considered a referring expression descriptive if any of its constituents were descriptive. [sent-122, score-1.131]

56 Thus, 18% of the referring expressions in the corpus added additional information beyond what was required to unambiguously identify their referent. [sent-123, score-0.932]

57 18% Table 3 contains the percentages of descriptive and distinctive tags broken down by constituent. [sent-138, score-0.631]

58 Like Cheng’s results, our analysis shows that descriptive referring expressions make up a significant fraction of all referring expressions. [sent-139, score-1.939]

59 Although Cheng did not examine nuclei, our results show that the use of descriptive nuclei is small but not negligible. [sent-140, score-0.531]

60 4 Relation to the Field Researchers working on generating referring expressions typically acknowledge that referring expressions can perform functions other than distinction. [sent-141, score-1.875]

61 First is the general study of aggregation in the process of referring expression generation. [sent-158, score-0.82]

62 (2001) and Jordan (2000a) that bear on the prevalence of descriptive referring expressions. [sent-160, score-1.032]

63 The NLG subtask of aggregation can be used to imbue referring expressions with a descriptive function (Reiter and Dale, 2000, §5. [sent-161, score-1.375]

64 There is a specific nk (iRned otefr aggregation 0c0al0le,d § embedding t ihsa at moves information from one clause to another inside the structure of a separate noun phrase. [sent-163, score-0.099]

65 This type of aggregation can be used to transform two sentences such as “The princess lived in a castle. [sent-164, score-0.218]

66 She was pretty ” into “The pretty princess lived in a castle ”. [sent-165, score-0.187]

67 The adjective pretty, previously a cop- ular predicate, becomes a descriptive modifier of the reference to the princess, making the second text more natural and fluent. [sent-166, score-0.408]

68 This kind of aggregation is widely used by humans for making the discourse more compact and efficient. [sent-167, score-0.099]

69 In order to create NLG systems with this ability, we must take into account the caveat, noted by Cheng (1998), that any non-distinctive information in a referring expression must not lead to confusion about the distinctive function of the referring expression. [sent-168, score-1.6]

70 This is by no means a trivial problem this sort of aggregation interferes with referring and coherence planning at both a local and global level (Cheng and Mellish, 2000; Cheng et al. [sent-169, score-0.762]

71 It is clear, from the current state of the art of NLG, that we have not yet obtained a deep enough understanding of aggregation to enable us to handle these interactions. [sent-171, score-0.099]

72 Two previous corpus studies have looked at the use of descriptive referring expressions. [sent-173, score-1.004]

73 The first showed explicitly that people craft descriptive referring expressions to accomplish different – 52 goals. [sent-174, score-1.276]

74 Jordan and colleagues (Jordan, 2000b; Jordan, 2000a) examined the use of referring expressions using the COCONUT corpus (Eugenio et al. [sent-175, score-0.943]

75 They tested how domain and discourse goals can influence the content of non-pronominal referring expressions in a dialogue context, checking whether or not a subject’s goals led them to include non-referring information in a referring expression. [sent-177, score-1.604]

76 In the other corpus study, which partially inspired this work, Cheng and colleagues analyzed a set of museum descriptions, the GNOME corpus (Poesio, 2004), for the pragmatic functions of referring expressions. [sent-179, score-0.764]

77 Their first function (marked by their uniq tag) was equiv- alent to our distinctive function. [sent-181, score-0.242]

78 The other two were specializations of our descriptive tag, where they differentiated between additional information that helped to understand the text (int), or additional information not necessary for understanding (att r). [sent-182, score-0.367]

79 Despite their annotators seeming to have trouble distinguishing between the latter two tags, they did achieve good overall inter-annotator agreement. [sent-183, score-0.095]

80 They identified 1,863 modifiers to referring expressions in their corpus, of which 47. [sent-184, score-0.987]

81 This is supportive of our main assertion, namely, that descriptive referring expressions, not only crucial for efficient and fluent text, are actually a significant phenomenon. [sent-186, score-1.004]

82 It is interesting, though, that Cheng’s fraction of descriptive referring expression was so much higher than ours (47. [sent-187, score-1.114]

83 We attribute this substantial difference to genre, in that Cheng studied museum labels, in which the writer is spaceconstrained, having to pack a lot of information into a small label. [sent-189, score-0.083]

84 We marked all referring expressions, coreferential relations, and referring expression constituents, and tagged each constituent as having a descriptive or distinctive function. [sent-193, score-2.138]

85 We wrote an annotation guide and created software that allows the annotation of this information in free text. [sent-194, score-0.175]

86 The software will also be released in the same archive when the Story Workbench annotation application is released to the public. [sent-196, score-0.089]

87 This corpus will be useful for the automatic generation and analysis of both descriptive and distinctive referring expressions. [sent-197, score-1.283]

88 Any kind of system intended to generate text as humans do must take into account that identifica- tion is not the only function of referring expressions. [sent-198, score-0.664]

89 Many analysis applications would benefit from the automatic recognition of descriptive referring expressions. [sent-199, score-1.004]

90 Second, we demonstrated that descriptive referring expressions comprise a substantial fraction (18%) of the referring expressions in news and narrative. [sent-200, score-2.245]

91 Along with museum descriptions, studied by Cheng, it seems that news and narrative are genres where authors naturally use a large number ofdescriptive referring expressions. [sent-201, score-0.899]

92 Given that so little work has been done on descriptive referring expressions, this indicates that the field would be well served by focusing more attention on this phenomenon. [sent-202, score-1.004]

93 We also thank Whitman Richards, Ozlem Uzuner, Peter Szolovits, Patrick Winston, Pablo Gerv a´s, and Mark Seifter for their helpful comments and discussion, and thank our annotators Saam Batmanghelidj and Geneva Trotter. [sent-206, score-0.095]

94 Measuring the influence of errors induced by the presence of dialogues in reference clustering of narrative text. [sent-209, score-0.077]

95 Capturing the interaction between aggregation and text planning in two generation systems. [sent-219, score-0.162]

96 Annotation guide for the UCM/MIT indications, referring expressions, and coreference corpus (UMIREC corpus). [sent-243, score-0.676]

97 UCM/MIT indications, referring expressions, and coreference corpus (UMIREC corpus). [sent-252, score-0.637]

98 Discourse annotation and semantic annotation in the GNOME corpus. [sent-292, score-0.084]

99 A fast algorithm for the generation of referring expressions. [sent-297, score-0.674]

100 Building a semantically transparent corpus for the generation of referring expressions. [sent-305, score-0.674]

similar papers computed by tfidf model

tfidf for this paper:

wordName wordTfidf (topN-words)

[('referring', 0.637), ('descriptive', 0.367), ('expressions', 0.272), ('distinctive', 0.242), ('cheng', 0.176), ('nuclei', 0.164), ('finlayson', 0.131), ('herv', 0.131), ('aggregation', 0.099), ('workbench', 0.099), ('annotators', 0.095), ('expression', 0.084), ('modifiers', 0.078), ('narrative', 0.077), ('adjudication', 0.075), ('villain', 0.075), ('constituent', 0.067), ('raquel', 0.066), ('princess', 0.066), ('story', 0.062), ('museum', 0.06), ('nlg', 0.057), ('folktales', 0.056), ('plumber', 0.056), ('lived', 0.053), ('king', 0.051), ('hua', 0.051), ('pamela', 0.045), ('copular', 0.045), ('reiter', 0.044), ('jordan', 0.043), ('constituents', 0.043), ('appositives', 0.042), ('annotation', 0.042), ('portions', 0.042), ('modifier', 0.041), ('morristown', 0.04), ('coreferential', 0.04), ('eugenio', 0.04), ('guide', 0.039), ('madrid', 0.038), ('aggarwal', 0.038), ('complutense', 0.038), ('descriptiveness', 0.038), ('folktale', 0.038), ('gnome', 0.038), ('ofdescriptive', 0.038), ('umirec', 0.038), ('viethen', 0.038), ('generation', 0.037), ('nj', 0.035), ('tagged', 0.035), ('referent', 0.034), ('colleagues', 0.034), ('house', 0.034), ('pretty', 0.034), ('news', 0.034), ('functions', 0.033), ('texts', 0.033), ('donnell', 0.033), ('sorts', 0.033), ('gerv', 0.033), ('gatt', 0.033), ('researchers', 0.033), ('genres', 0.03), ('dale', 0.03), ('universidad', 0.03), ('ehud', 0.03), ('wrote', 0.03), ('nucleus', 0.03), ('plugin', 0.03), ('indications', 0.03), ('tales', 0.03), ('marked', 0.029), ('goals', 0.029), ('office', 0.028), ('prevalence', 0.028), ('surrounded', 0.028), ('reg', 0.028), ('att', 0.028), ('annotate', 0.028), ('intended', 0.027), ('breakdown', 0.027), ('pablo', 0.027), ('albert', 0.027), ('fraction', 0.026), ('planning', 0.026), ('assembled', 0.025), ('archive', 0.025), ('deemter', 0.024), ('generating', 0.024), ('unnecessary', 0.024), ('naval', 0.024), ('studied', 0.023), ('unambiguously', 0.023), ('software', 0.022), ('tags', 0.022), ('sometimes', 0.022), ('perfectly', 0.022), ('int', 0.022)]

similar papers list:

simIndex simValue paperId paperTitle

same-paper 1 0.99999958 231 acl-2010-The Prevalence of Descriptive Referring Expressions in News and Narrative

Author: Raquel Hervas ; Mark Finlayson

2 0.28990942 149 acl-2010-Incorporating Extra-Linguistic Information into Reference Resolution in Collaborative Task Dialogue

Author: Ryu Iida ; Syumpei Kobayashi ; Takenobu Tokunaga

Abstract: This paper proposes an approach to reference resolution in situated dialogues by exploiting extra-linguistic information. Recently, investigations of referential behaviours involved in situations in the real world have received increasing attention by researchers (Di Eugenio et al., 2000; Byron, 2005; van Deemter, 2007; Spanger et al., 2009). In order to create an accurate reference resolution model, we need to handle extra-linguistic information as well as textual information examined by existing approaches (Soon et al., 2001 ; Ng and Cardie, 2002, etc.). In this paper, we incorporate extra-linguistic information into an existing corpus-based reference resolution model, and investigate its effects on refer- ence resolution problems within a corpus of Japanese dialogues. The results demonstrate that our proposed model achieves an accuracy of 79.0% for this task.

3 0.2326767 167 acl-2010-Learning to Adapt to Unknown Users: Referring Expression Generation in Spoken Dialogue Systems

Author: Srinivasan Janarthanam ; Oliver Lemon

Abstract: We present a data-driven approach to learn user-adaptive referring expression generation (REG) policies for spoken dialogue systems. Referring expressions can be difficult to understand in technical domains where users may not know the technical ‘jargon’ names of the domain entities. In such cases, dialogue systems must be able to model the user’s (lexical) domain knowledge and use appropriate referring expressions. We present a reinforcement learning (RL) framework in which the sys- tem learns REG policies which can adapt to unknown users online. Furthermore, unlike supervised learning methods which require a large corpus of expert adaptive behaviour to train on, we show that effective adaptive policies can be learned from a small dialogue corpus of non-adaptive human-machine interaction, by using a RL framework and a statistical user simulation. We show that in comparison to adaptive hand-coded baseline policies, the learned policy performs significantly better, with an 18.6% average increase in adaptation accuracy. The best learned policy also takes less dialogue time (average 1.07 min less) than the best hand-coded policy. This is because the learned policies can adapt online to changing evidence about the user’s domain expertise.

4 0.15047653 199 acl-2010-Preferences versus Adaptation during Referring Expression Generation

Author: Martijn Goudbeek ; Emiel Krahmer

Abstract: Current Referring Expression Generation algorithms rely on domain dependent preferences for both content selection and linguistic realization. We present two experiments showing that human speakers may opt for dispreferred properties and dispreferred modifier orderings when these were salient in a preceding interaction (without speakers being consciously aware of this). We discuss the impact of these findings for current generation algorithms.

5 0.091336571 35 acl-2010-Automated Planning for Situated Natural Language Generation

Author: Konstantina Garoufi ; Alexander Koller

Abstract: We present a natural language generation approach which models, exploits, and manipulates the non-linguistic context in situated communication, using techniques from AI planning. We show how to generate instructions which deliberately guide the hearer to a location that is convenient for the generation of simple referring expressions, and how to generate referring expressions with context-dependent adjectives. We implement and evaluate our approach in the framework of the Challenge on Generating Instructions in Virtual Environments, finding that it performs well even under the constraints of realtime generation.

6 0.088041849 196 acl-2010-Plot Induction and Evolutionary Search for Story Generation

7 0.082179718 58 acl-2010-Classification of Feedback Expressions in Multimodal Data

8 0.07828334 208 acl-2010-Sentence and Expression Level Annotation of Opinions in User-Generated Discourse

9 0.063712776 139 acl-2010-Identifying Generic Noun Phrases

10 0.063292012 4 acl-2010-A Cognitive Cost Model of Annotations Based on Eye-Tracking Data

11 0.052239139 5 acl-2010-A Framework for Figurative Language Detection Based on Sense Differentiation

12 0.049328543 33 acl-2010-Assessing the Role of Discourse References in Entailment Inference

13 0.048446789 38 acl-2010-Automatic Evaluation of Linguistic Quality in Multi-Document Summarization

14 0.048260916 187 acl-2010-Optimising Information Presentation for Spoken Dialogue Systems

15 0.045356452 226 acl-2010-The Human Language Project: Building a Universal Corpus of the World's Languages

16 0.044941731 55 acl-2010-Bootstrapping Semantic Analyzers from Non-Contradictory Texts

17 0.042117454 31 acl-2010-Annotation

18 0.040994655 213 acl-2010-Simultaneous Tokenization and Part-Of-Speech Tagging for Arabic without a Morphological Analyzer

19 0.040988903 49 acl-2010-Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates

20 0.039641447 101 acl-2010-Entity-Based Local Coherence Modelling Using Topological Fields

similar papers computed by lsi model

lsi for this paper:

topicId topicWeight

[(0, -0.112), (1, 0.083), (2, -0.041), (3, -0.135), (4, -0.058), (5, -0.021), (6, -0.089), (7, 0.069), (8, -0.0), (9, 0.031), (10, 0.065), (11, -0.027), (12, 0.002), (13, 0.059), (14, 0.026), (15, -0.077), (16, 0.124), (17, 0.082), (18, 0.075), (19, 0.148), (20, 0.115), (21, -0.03), (22, 0.096), (23, 0.069), (24, -0.023), (25, 0.03), (26, 0.024), (27, 0.067), (28, -0.114), (29, 0.055), (30, -0.291), (31, -0.083), (32, -0.204), (33, -0.094), (34, 0.021), (35, 0.094), (36, 0.268), (37, -0.038), (38, 0.004), (39, -0.2), (40, 0.017), (41, 0.04), (42, -0.039), (43, -0.143), (44, -0.051), (45, 0.149), (46, -0.158), (47, 0.058), (48, -0.053), (49, -0.003)]

similar papers list:

simIndex simValue paperId paperTitle

same-paper 1 0.98739898 231 acl-2010-The Prevalence of Descriptive Referring Expressions in News and Narrative

Author: Raquel Hervas ; Mark Finlayson

2 0.77361882 149 acl-2010-Incorporating Extra-Linguistic Information into Reference Resolution in Collaborative Task Dialogue

Author: Ryu Iida ; Syumpei Kobayashi ; Takenobu Tokunaga

3 0.72148246 199 acl-2010-Preferences versus Adaptation during Referring Expression Generation

Author: Martijn Goudbeek ; Emiel Krahmer

4 0.46730292 167 acl-2010-Learning to Adapt to Unknown Users: Referring Expression Generation in Spoken Dialogue Systems

Author: Srinivasan Janarthanam ; Oliver Lemon

5 0.44646904 58 acl-2010-Classification of Feedback Expressions in Multimodal Data

Author: Costanza Navarretta ; Patrizia Paggio

Abstract: This paper addresses the issue of how linguistic feedback expressions, prosody and head gestures, i.e. head movements and face expressions, relate to one another in a collection of eight video-recorded Danish map-task dialogues. The study shows that in these data, prosodic features and head gestures significantly improve automatic classification of dialogue act labels for linguistic expressions of feedback.

6 0.41582495 35 acl-2010-Automated Planning for Situated Natural Language Generation

7 0.41475204 196 acl-2010-Plot Induction and Evolutionary Search for Story Generation

8 0.32121503 139 acl-2010-Identifying Generic Noun Phrases

9 0.29524598 5 acl-2010-A Framework for Figurative Language Detection Based on Sense Differentiation

10 0.26285005 208 acl-2010-Sentence and Expression Level Annotation of Opinions in User-Generated Discourse

11 0.2594699 2 acl-2010-"Was It Good? It Was Provocative." Learning the Meaning of Scalar Adjectives

12 0.23662379 187 acl-2010-Optimising Information Presentation for Spoken Dialogue Systems

13 0.22212601 226 acl-2010-The Human Language Project: Building a Universal Corpus of the World's Languages

14 0.22086012 101 acl-2010-Entity-Based Local Coherence Modelling Using Topological Fields

15 0.20959215 213 acl-2010-Simultaneous Tokenization and Part-Of-Speech Tagging for Arabic without a Morphological Analyzer

16 0.20195605 225 acl-2010-Temporal Information Processing of a New Language: Fast Porting with Minimal Resources

17 0.19366565 230 acl-2010-The Manually Annotated Sub-Corpus: A Community Resource for and by the People

18 0.18862098 128 acl-2010-Grammar Prototyping and Testing with the LinGO Grammar Matrix Customization System

19 0.18606856 140 acl-2010-Identifying Non-Explicit Citing Sentences for Citation-Based Summarization.

20 0.18521863 76 acl-2010-Creating Robust Supervised Classifiers via Web-Scale N-Gram Data

similar papers computed by lda model

lda for this paper:

topicId topicWeight

[(14, 0.017), (25, 0.057), (36, 0.293), (39, 0.024), (42, 0.106), (44, 0.011), (59, 0.056), (72, 0.011), (73, 0.042), (76, 0.018), (78, 0.028), (80, 0.016), (83, 0.084), (84, 0.02), (97, 0.027), (98, 0.088)]

similar papers list:

simIndex simValue paperId paperTitle

same-paper 1 0.78357524 231 acl-2010-The Prevalence of Descriptive Referring Expressions in News and Narrative

Author: Raquel Hervas ; Mark Finlayson

2 0.71921045 16 acl-2010-A Statistical Model for Lost Language Decipherment

Author: Benjamin Snyder ; Regina Barzilay ; Kevin Knight

Abstract: In this paper we propose a method for the automatic decipherment of lost languages. Given a non-parallel corpus in a known related language, our model produces both alphabetic mappings and translations of words into their corresponding cognates. We employ a non-parametric Bayesian framework to simultaneously capture both low-level character mappings and highlevel morphemic correspondences. This formulation enables us to encode some of the linguistic intuitions that have guided human decipherers. When applied to the ancient Semitic language Ugaritic, the model correctly maps 29 of 30 letters to their Hebrew counterparts, and deduces the correct Hebrew cognate for 60% of the Ugaritic words which have cognates in Hebrew.

3 0.70590788 168 acl-2010-Learning to Follow Navigational Directions

Author: Adam Vogel ; Dan Jurafsky

Abstract: We present a system that learns to follow navigational natural language directions. Where traditional models learn from linguistic annotation or word distributions, our approach is grounded in the world, learning by apprenticeship from routes through a map paired with English descriptions. Lacking an explicit alignment between the text and the reference path makes it difficult to determine what portions of the language describe which aspects of the route. We learn this correspondence with a reinforcement learning algorithm, using the deviation of the route we follow from the intended path as a reward signal. We demonstrate that our system successfully grounds the meaning of spatial terms like above and south into geometric properties of paths.

4 0.51701164 123 acl-2010-Generating Focused Topic-Specific Sentiment Lexicons

Author: Valentin Jijkoun ; Maarten de Rijke ; Wouter Weerkamp

Abstract: We present a method for automatically generating focused and accurate topicspecific subjectivity lexicons from a general purpose polarity lexicon that allow users to pin-point subjective on-topic information in a set of relevant documents. We motivate the need for such lexicons in the field of media analysis, describe a bootstrapping method for generating a topic-specific lexicon from a general purpose polarity lexicon, and evaluate the quality of the generated lexicons both manually and using a TREC Blog track test set for opinionated blog post retrieval. Although the generated lexicons can be an order of magnitude more selective than the general purpose lexicon, they maintain, or even improve, the performance of an opin- ion retrieval system.

5 0.51693636 149 acl-2010-Incorporating Extra-Linguistic Information into Reference Resolution in Collaborative Task Dialogue

Author: Ryu Iida ; Syumpei Kobayashi ; Takenobu Tokunaga

6 0.51094407 150 acl-2010-Inducing Domain-Specific Semantic Class Taggers from (Almost) Nothing

7 0.50586283 251 acl-2010-Using Anaphora Resolution to Improve Opinion Target Identification in Movie Reviews

8 0.50531286 214 acl-2010-Sparsity in Dependency Grammar Induction

9 0.50450748 178 acl-2010-Non-Cooperation in Dialogue

10 0.49696469 208 acl-2010-Sentence and Expression Level Annotation of Opinions in User-Generated Discourse

11 0.49491552 167 acl-2010-Learning to Adapt to Unknown Users: Referring Expression Generation in Spoken Dialogue Systems

12 0.4879182 134 acl-2010-Hierarchical Sequential Learning for Extracting Opinions and Their Attributes

13 0.48566365 22 acl-2010-A Unified Graph Model for Sentence-Based Opinion Retrieval

14 0.46069425 42 acl-2010-Automatically Generating Annotator Rationales to Improve Sentiment Classification

15 0.45858222 211 acl-2010-Simple, Accurate Parsing with an All-Fragments Grammar

16 0.45826519 112 acl-2010-Extracting Social Networks from Literary Fiction

17 0.4579753 33 acl-2010-Assessing the Role of Discourse References in Entailment Inference

18 0.45753133 101 acl-2010-Entity-Based Local Coherence Modelling Using Topological Fields

19 0.45679036 226 acl-2010-The Human Language Project: Building a Universal Corpus of the World's Languages

20 0.45634985 1 acl-2010-"Ask Not What Textual Entailment Can Do for You..."