acl acl2013 acl2013-313 knowledge-graph by maker-knowledge-mining

313 acl-2013-Semantic Parsing with Combinatory Categorial Grammars


Source: pdf

Author: Yoav Artzi ; Nicholas FitzGerald ; Luke Zettlemoyer

Abstract: unkown-abstract

Reference: text


Summary: the most important sentenses genereted by tfidf model

sentIndex sentText sentNum sentScore

1 Semantic Parsing with Combinatory Categorial Grammars Yoav Artzi, Nicholas FitzGerald and Luke Zettlemoyer Computer Science & Engineering University of Washington Seattle, WA 98195 {yoav ,n fit z , l z } @ c s . [sent-1, score-0.043]

2 edu s 1 Abstract Semantic parsers map natural language sentences to formal representations of their underlying meaning. [sent-3, score-0.293]

3 Building accurate semantic parsers without prohibitive engineering costs is a longstanding, open research problem. [sent-4, score-0.431]

4 The tutorial will describe general principles for building semantic parsers. [sent-5, score-0.265]

5 The presentation will be divided into two main parts: modeling and learning. [sent-6, score-0.144]

6 The modeling section will include best practices for grammar design and choice of semantic representation. [sent-7, score-0.298]

7 The discussion will be guided by examples from several domains. [sent-8, score-0.059]

8 To illustrate the choices to be made and show how they can be approached within a real-life representation language, we will use ä˝? [sent-9, score-0.169]

9 In the learning part, we will describe a unified approach for learning Combinatory Categorial Grammar (CCG) semantic parsers, that in- duces both a CCG lexicon and the parameters of a parsing model. [sent-11, score-0.442]

10 The approach learns from data with labeled meaning representations, as well as from more easily gathered weak supervision. [sent-12, score-0.262]

11 It also enables grounded learning where the semantic parser is used in an interactive environment, for example to read and execute instructions. [sent-13, score-0.644]

12 Similarly, the algorithms for inducing CCGs focus on tasks that are formalism independent, learning the meaning of words and estimating parsing parameters. [sent-17, score-0.341]

13 The tutorial will be backed by implementation and experiments in the University of Washington Semantic Parsing Framework (UW SPF). [sent-19, score-0.225]

14 Modeling (a) Questions for database queries (b) Plurality and determiner resolution in grounded applications (c) Event semantics and imperatives in instructional language 3. [sent-23, score-0.579]

15 Learning (a) A unified learning algorithm (b) Learning with supervised data i. [sent-24, score-0.195]

16 Unification-based learning (c) Weakly supervised learning without labeled meaning representations 3 Instructors Yoav Artzi is a Ph. [sent-26, score-0.379]

17 candidate in the Computer Science & Engineering department at the University of Washington. [sent-28, score-0.052]

18 His research studies the acquisition of grounded natural language understanding within interactive systems. [sent-29, score-0.427]

19 His work focuses on modeling semantic representations and designing weakly supervised learning algorithms. [sent-30, score-0.563]

20 His research interests are grounded natural language understanding and generation. [sent-35, score-0.439]

21 He is a recipient of an Intel Science and Technology Center Fellowship and an NSERC Postgraduate Scholarship. [sent-36, score-0.1]

22 Luke Zettlemoyer is an Assistant Professor in the Computer Science & Engineering department at the University of Washington. [sent-37, score-0.052]

23 His research interests are in the intersections of natural language processing, machine learning and decision making under uncertainty. [sent-38, score-0.269]

24 Honors include best paper awards at UAI 2005 and ACL 2009, selection to the DARPA CSSG, and an NSF CAREER Award. [sent-39, score-0.086]

25 Proce Sdoinfiags, B oufl tghear5i a1,st A Aungunusta 4l M-9e 2e0t1in3g. [sent-40, score-0.109]


similar papers computed by tfidf model

tfidf for this paper:

wordName wordTfidf (topN-words)

[('ccgs', 0.37), ('grounded', 0.25), ('yoav', 0.184), ('fitzgerald', 0.18), ('artzi', 0.18), ('combinatory', 0.147), ('nicholas', 0.144), ('interests', 0.137), ('luke', 0.132), ('ccg', 0.129), ('zettlemoyer', 0.129), ('categorial', 0.127), ('tutorial', 0.125), ('parsers', 0.12), ('weakly', 0.112), ('postgraduate', 0.109), ('aotnio', 0.109), ('asoscsioacti', 0.109), ('aungunusta', 0.109), ('cmopmuptaut', 0.109), ('cssg', 0.109), ('iaotinoanla', 0.109), ('lli', 0.109), ('lnignugiusti', 0.109), ('oufl', 0.109), ('sdoinfiags', 0.109), ('representations', 0.108), ('longstanding', 0.1), ('duces', 0.1), ('instructors', 0.1), ('recipient', 0.1), ('shingt', 0.1), ('backed', 0.1), ('washington', 0.097), ('imperatives', 0.095), ('nserc', 0.095), ('professor', 0.095), ('engineering', 0.09), ('fnor', 0.09), ('unified', 0.088), ('modeling', 0.087), ('semantic', 0.087), ('uai', 0.086), ('execute', 0.086), ('instructional', 0.086), ('plurality', 0.086), ('assistant', 0.086), ('intersections', 0.086), ('awards', 0.086), ('interactive', 0.086), ('approached', 0.08), ('meaning', 0.08), ('career', 0.078), ('prohibitive', 0.078), ('uw', 0.076), ('parsing', 0.075), ('fellowship', 0.074), ('yahoo', 0.072), ('practices', 0.07), ('intel', 0.069), ('determiner', 0.067), ('formal', 0.065), ('designing', 0.062), ('seattle', 0.061), ('supervised', 0.061), ('guided', 0.059), ('outline', 0.058), ('gathered', 0.058), ('formalism', 0.058), ('presentation', 0.057), ('costs', 0.056), ('cro', 0.055), ('grammar', 0.054), ('environment', 0.053), ('wa', 0.053), ('principles', 0.053), ('understanding', 0.052), ('ideas', 0.052), ('nsf', 0.052), ('department', 0.052), ('student', 0.05), ('darpa', 0.049), ('choices', 0.048), ('learning', 0.046), ('weak', 0.045), ('enables', 0.045), ('read', 0.044), ('templates', 0.043), ('fit', 0.043), ('estimating', 0.042), ('learns', 0.041), ('illustrate', 0.041), ('resolution', 0.041), ('queries', 0.04), ('inducing', 0.04), ('science', 0.039), ('grammars', 0.039), ('acquisition', 0.039), ('labeled', 0.038), ('induction', 0.037)]

similar papers list:

simIndex simValue paperId paperTitle

same-paper 1 1.0 313 acl-2013-Semantic Parsing with Combinatory Categorial Grammars

Author: Yoav Artzi ; Nicholas FitzGerald ; Luke Zettlemoyer

Abstract: unkown-abstract

2 0.16344441 384 acl-2013-Visual Features for Linguists: Basic image analysis techniques for multimodally-curious NLPers

Author: Elia Bruni ; Marco Baroni

Abstract: unkown-abstract

3 0.13300665 347 acl-2013-The Role of Syntax in Vector Space Models of Compositional Semantics

Author: Karl Moritz Hermann ; Phil Blunsom

Abstract: Modelling the compositional process by which the meaning of an utterance arises from the meaning of its parts is a fundamental task of Natural Language Processing. In this paper we draw upon recent advances in the learning of vector space representations of sentential semantics and the transparent interface between syntax and semantics provided by Combinatory Categorial Grammar to introduce Combinatory Categorial Autoencoders. This model leverages the CCG combinatory operators to guide a non-linear transformation of meaning within a sentence. We use this model to learn high dimensional embeddings for sentences and evaluate them in a range of tasks, demonstrating that the incorporation of syntax allows a concise model to learn representations that are both effective and general.

4 0.11869 199 acl-2013-Integrating Multiple Dependency Corpora for Inducing Wide-coverage Japanese CCG Resources

Author: Sumire Uematsu ; Takuya Matsuzaki ; Hiroki Hanaoka ; Yusuke Miyao ; Hideki Mima

Abstract: This paper describes a method of inducing wide-coverage CCG resources for Japanese. While deep parsers with corpusinduced grammars have been emerging for some languages, those for Japanese have not been widely studied, mainly because most Japanese syntactic resources are dependency-based. Our method first integrates multiple dependency-based corpora into phrase structure trees and then converts the trees into CCG derivations. The method is empirically evaluated in terms of the coverage of the obtained lexi- con and the accuracy of parsing.

5 0.093920171 382 acl-2013-Variational Inference for Structured NLP Models

Author: David Burkett ; Dan Klein

Abstract: unkown-abstract

6 0.091817327 357 acl-2013-Transfer Learning for Constituency-Based Grammars

7 0.089372925 372 acl-2013-Using CCG categories to improve Hindi dependency parsing

8 0.077508479 212 acl-2013-Language-Independent Discriminative Parsing of Temporal Expressions

9 0.076625146 36 acl-2013-Adapting Discriminative Reranking to Grounded Language Learning

10 0.06927146 228 acl-2013-Leveraging Domain-Independent Information in Semantic Parsing

11 0.064209066 272 acl-2013-Paraphrase-Driven Learning for Open Question Answering

12 0.057480823 312 acl-2013-Semantic Parsing as Machine Translation

13 0.053217109 349 acl-2013-The mathematics of language learning

14 0.052600808 155 acl-2013-Fast and Accurate Shift-Reduce Constituent Parsing

15 0.052012697 215 acl-2013-Large-scale Semantic Parsing via Schema Matching and Lexicon Extension

16 0.051667046 112 acl-2013-Dependency Parser Adaptation with Subtrees from Auto-Parsed Target Domain Data

17 0.051288854 176 acl-2013-Grounded Unsupervised Semantic Parsing

18 0.049751397 230 acl-2013-Lightly Supervised Learning of Procedural Dialog Systems

19 0.048145719 85 acl-2013-Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis

20 0.046508245 175 acl-2013-Grounded Language Learning from Video Described with Sentences


similar papers computed by lsi model

lsi for this paper:

topicId topicWeight

[(0, 0.103), (1, -0.009), (2, -0.071), (3, -0.046), (4, -0.11), (5, -0.006), (6, 0.062), (7, -0.047), (8, 0.025), (9, 0.023), (10, -0.05), (11, -0.046), (12, 0.108), (13, -0.005), (14, 0.04), (15, -0.002), (16, 0.016), (17, 0.026), (18, -0.106), (19, 0.019), (20, 0.034), (21, -0.112), (22, -0.079), (23, 0.029), (24, 0.05), (25, -0.015), (26, -0.039), (27, 0.114), (28, -0.017), (29, -0.012), (30, 0.048), (31, -0.002), (32, 0.032), (33, 0.002), (34, 0.008), (35, -0.018), (36, 0.018), (37, 0.005), (38, 0.047), (39, 0.088), (40, -0.009), (41, 0.043), (42, 0.025), (43, -0.02), (44, 0.034), (45, 0.09), (46, -0.02), (47, 0.005), (48, 0.049), (49, 0.016)]

similar papers list:

simIndex simValue paperId paperTitle

same-paper 1 0.9142518 313 acl-2013-Semantic Parsing with Combinatory Categorial Grammars

Author: Yoav Artzi ; Nicholas FitzGerald ; Luke Zettlemoyer

Abstract: unkown-abstract

2 0.67653143 199 acl-2013-Integrating Multiple Dependency Corpora for Inducing Wide-coverage Japanese CCG Resources

Author: Sumire Uematsu ; Takuya Matsuzaki ; Hiroki Hanaoka ; Yusuke Miyao ; Hideki Mima

Abstract: This paper describes a method of inducing wide-coverage CCG resources for Japanese. While deep parsers with corpusinduced grammars have been emerging for some languages, those for Japanese have not been widely studied, mainly because most Japanese syntactic resources are dependency-based. Our method first integrates multiple dependency-based corpora into phrase structure trees and then converts the trees into CCG derivations. The method is empirically evaluated in terms of the coverage of the obtained lexi- con and the accuracy of parsing.

3 0.65861231 347 acl-2013-The Role of Syntax in Vector Space Models of Compositional Semantics

Author: Karl Moritz Hermann ; Phil Blunsom

Abstract: Modelling the compositional process by which the meaning of an utterance arises from the meaning of its parts is a fundamental task of Natural Language Processing. In this paper we draw upon recent advances in the learning of vector space representations of sentential semantics and the transparent interface between syntax and semantics provided by Combinatory Categorial Grammar to introduce Combinatory Categorial Autoencoders. This model leverages the CCG combinatory operators to guide a non-linear transformation of meaning within a sentence. We use this model to learn high dimensional embeddings for sentences and evaluate them in a range of tasks, demonstrating that the incorporation of syntax allows a concise model to learn representations that are both effective and general.

4 0.63044345 357 acl-2013-Transfer Learning for Constituency-Based Grammars

Author: Yuan Zhang ; Regina Barzilay ; Amir Globerson

Abstract: In this paper, we consider the problem of cross-formalism transfer in parsing. We are interested in parsing constituencybased grammars such as HPSG and CCG using a small amount of data specific for the target formalism, and a large quantity of coarse CFG annotations from the Penn Treebank. While all of the target formalisms share a similar basic syntactic structure with Penn Treebank CFG, they also encode additional constraints and semantic features. To handle this apparent discrepancy, we design a probabilistic model that jointly generates CFG and target formalism parses. The model includes features of both parses, allowing trans- fer between the formalisms, while preserving parsing efficiency. We evaluate our approach on three constituency-based grammars CCG, HPSG, and LFG, augmented with the Penn Treebank-1. Our experiments show that across all three formalisms, the target parsers significantly benefit from the coarse annotations.1 —

5 0.59226125 372 acl-2013-Using CCG categories to improve Hindi dependency parsing

Author: Bharat Ram Ambati ; Tejaswini Deoskar ; Mark Steedman

Abstract: We show that informative lexical categories from a strongly lexicalised formalism such as Combinatory Categorial Grammar (CCG) can improve dependency parsing of Hindi, a free word order language. We first describe a novel way to obtain a CCG lexicon and treebank from an existing dependency treebank, using a CCG parser. We use the output of a supertagger trained on the CCGbank as a feature for a state-of-the-art Hindi dependency parser (Malt). Our results show that using CCG categories improves the accuracy of Malt on long distance dependencies, for which it is known to have weak rates of recovery.

6 0.55578196 176 acl-2013-Grounded Unsupervised Semantic Parsing

7 0.50253427 36 acl-2013-Adapting Discriminative Reranking to Grounded Language Learning

8 0.50034934 215 acl-2013-Large-scale Semantic Parsing via Schema Matching and Lexicon Extension

9 0.49219066 311 acl-2013-Semantic Neighborhoods as Hypergraphs

10 0.47374409 228 acl-2013-Leveraging Domain-Independent Information in Semantic Parsing

11 0.43009928 275 acl-2013-Parsing with Compositional Vector Grammars

12 0.42689958 212 acl-2013-Language-Independent Discriminative Parsing of Temporal Expressions

13 0.41039804 161 acl-2013-Fluid Construction Grammar for Historical and Evolutionary Linguistics

14 0.40859687 175 acl-2013-Grounded Language Learning from Video Described with Sentences

15 0.39968604 382 acl-2013-Variational Inference for Structured NLP Models

16 0.39418507 312 acl-2013-Semantic Parsing as Machine Translation

17 0.3711971 249 acl-2013-Models of Semantic Representation with Visual Attributes

18 0.36767635 380 acl-2013-VSEM: An open library for visual semantics representation

19 0.36699486 324 acl-2013-Smatch: an Evaluation Metric for Semantic Feature Structures

20 0.36619669 384 acl-2013-Visual Features for Linguists: Basic image analysis techniques for multimodally-curious NLPers


similar papers computed by lda model

lda for this paper:

topicId topicWeight

[(0, 0.045), (6, 0.017), (11, 0.043), (24, 0.033), (26, 0.038), (31, 0.455), (35, 0.065), (42, 0.028), (48, 0.043), (70, 0.069), (88, 0.037), (95, 0.034)]

similar papers list:

simIndex simValue paperId paperTitle

same-paper 1 0.75085193 313 acl-2013-Semantic Parsing with Combinatory Categorial Grammars

Author: Yoav Artzi ; Nicholas FitzGerald ; Luke Zettlemoyer

Abstract: unkown-abstract

2 0.68913895 48 acl-2013-An Open Source Toolkit for Quantitative Historical Linguistics

Author: Johann-Mattis List ; Steven Moran

Abstract: Given the increasing interest and development of computational and quantitative methods in historical linguistics, it is important that scholars have a basis for documenting, testing, evaluating, and sharing complex workflows. We present a novel open-source toolkit for quantitative tasks in historical linguistics that offers these features. This toolkit also serves as an interface between existing software packages and frequently used data formats, and it provides implementations of new and existing algorithms within a homogeneous framework. We illustrate the toolkit’s functionality with an exemplary workflow that starts with raw language data and ends with automatically calculated phonetic alignments, cognates and borrowings. We then illustrate evaluation metrics on gold standard datasets that are provided with the toolkit.

3 0.55899668 234 acl-2013-Linking and Extending an Open Multilingual Wordnet

Author: Francis Bond ; Ryan Foster

Abstract: We create an open multilingual wordnet with large wordnets for over 26 languages and smaller ones for 57 languages. It is made by combining wordnets with open licences, data from Wiktionary and the Unicode Common Locale Data Repository. Overall there are over 2 million senses for over 100 thousand concepts, linking over 1.4 million words in hundreds of languages.

4 0.55278587 367 acl-2013-Universal Conceptual Cognitive Annotation (UCCA)

Author: Omri Abend ; Ari Rappoport

Abstract: Syntactic structures, by their nature, reflect first and foremost the formal constructions used for expressing meanings. This renders them sensitive to formal variation both within and across languages, and limits their value to semantic applications. We present UCCA, a novel multi-layered framework for semantic representation that aims to accommodate the semantic distinctions expressed through linguistic utterances. We demonstrate UCCA’s portability across domains and languages, and its relative insensitivity to meaning-preserving syntactic variation. We also show that UCCA can be effectively and quickly learned by annotators with no linguistic background, and describe the compilation of a UCCAannotated corpus.

5 0.42059246 211 acl-2013-LABR: A Large Scale Arabic Book Reviews Dataset

Author: Mohamed Aly ; Amir Atiya

Abstract: We introduce LABR, the largest sentiment analysis dataset to-date for the Arabic language. It consists of over 63,000 book reviews, each rated on a scale of 1 to 5 stars. We investigate the properties of the the dataset, and present its statistics. We explore using the dataset for two tasks: sentiment polarity classification and rating classification. We provide standard splits of the dataset into training and testing, for both polarity and rating classification, in both balanced and unbalanced settings. We run baseline experiments on the dataset to establish a benchmark.

6 0.36344045 374 acl-2013-Using Context Vectors in Improving a Machine Translation System with Bridge Language

7 0.32859468 382 acl-2013-Variational Inference for Structured NLP Models

8 0.30464461 198 acl-2013-IndoNet: A Multilingual Lexical Knowledge Network for Indian Languages

9 0.28817749 249 acl-2013-Models of Semantic Representation with Visual Attributes

10 0.28075898 380 acl-2013-VSEM: An open library for visual semantics representation

11 0.28051487 169 acl-2013-Generating Synthetic Comparable Questions for News Articles

12 0.28038278 85 acl-2013-Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis

13 0.2802403 272 acl-2013-Paraphrase-Driven Learning for Open Question Answering

14 0.27950084 275 acl-2013-Parsing with Compositional Vector Grammars

15 0.27936783 318 acl-2013-Sentiment Relevance

16 0.27909118 224 acl-2013-Learning to Extract International Relations from Political Context

17 0.27821207 329 acl-2013-Statistical Machine Translation Improves Question Retrieval in Community Question Answering via Matrix Factorization

18 0.27810964 369 acl-2013-Unsupervised Consonant-Vowel Prediction over Hundreds of Languages

19 0.27646866 291 acl-2013-Question Answering Using Enhanced Lexical Semantic Models

20 0.27612281 167 acl-2013-Generalizing Image Captions for Image-Text Parallel Corpus