hunch_net hunch_net-2005 hunch_net-2005-94 knowledge-graph by maker-knowledge-mining
Source: html
Introduction: Rajat Raina presented a paper on the technique they used for the PASCAL Recognizing Textual Entailment challenge. “Text entailment” is the problem of deciding if one sentence implies another. For example the previous sentence entails: Text entailment is a decision problem. One sentence can imply another. The challenge was of the form: given an original sentence and another sentence predict whether there was an entailment. All current techniques for predicting correctness of an entailment are at the “flail” stage—accuracies of around 58% where humans could achieve near 100% accuracy, so there is much room to improve. Apparently, there may be another PASCAL challenge on this problem in the near future.
sentIndex sentText sentNum sentScore
1 Rajat Raina presented a paper on the technique they used for the PASCAL Recognizing Textual Entailment challenge. [sent-1, score-0.224]
2 “Text entailment” is the problem of deciding if one sentence implies another. [sent-2, score-0.83]
3 For example the previous sentence entails: Text entailment is a decision problem. [sent-3, score-1.28]
4 The challenge was of the form: given an original sentence and another sentence predict whether there was an entailment. [sent-5, score-1.655]
5 All current techniques for predicting correctness of an entailment are at the “flail” stage—accuracies of around 58% where humans could achieve near 100% accuracy, so there is much room to improve. [sent-6, score-1.341]
6 Apparently, there may be another PASCAL challenge on this problem in the near future. [sent-7, score-0.437]
wordName wordTfidf (topN-words)
[('sentence', 0.6), ('entailment', 0.549), ('pascal', 0.22), ('text', 0.185), ('challenge', 0.143), ('raina', 0.137), ('textual', 0.137), ('near', 0.135), ('stage', 0.127), ('rajat', 0.12), ('recognizing', 0.12), ('correctness', 0.114), ('apparently', 0.1), ('deciding', 0.097), ('accuracy', 0.089), ('humans', 0.083), ('original', 0.083), ('another', 0.082), ('presented', 0.081), ('room', 0.079), ('technique', 0.073), ('imply', 0.073), ('predicting', 0.068), ('achieve', 0.064), ('current', 0.064), ('around', 0.061), ('previous', 0.058), ('whether', 0.058), ('techniques', 0.057), ('future', 0.052), ('implies', 0.052), ('predict', 0.051), ('problem', 0.05), ('decision', 0.047), ('form', 0.043), ('could', 0.039), ('given', 0.038), ('used', 0.037), ('paper', 0.033), ('one', 0.031), ('much', 0.028), ('may', 0.027), ('example', 0.026)]
simIndex simValue blogId blogTitle
same-blog 1 1.0 94 hunch net-2005-07-13-Text Entailment at AAAI
Introduction: Rajat Raina presented a paper on the technique they used for the PASCAL Recognizing Textual Entailment challenge. “Text entailment” is the problem of deciding if one sentence implies another. For example the previous sentence entails: Text entailment is a decision problem. One sentence can imply another. The challenge was of the form: given an original sentence and another sentence predict whether there was an entailment. All current techniques for predicting correctness of an entailment are at the “flail” stage—accuracies of around 58% where humans could achieve near 100% accuracy, so there is much room to improve. Apparently, there may be another PASCAL challenge on this problem in the near future.
2 0.079345025 424 hunch net-2011-02-17-What does Watson mean?
Introduction: Watson convincingly beat the best champion Jeopardy! players. The apparent significance of this varies hugely, depending on your background knowledge about the related machine learning, NLP, and search technology. For a random person, this might seem evidence of serious machine intelligence, while for people working on the system itself, it probably seems like a reasonably good assemblage of existing technologies with several twists to make the entire system work. Above all, I think we should congratulate the people who managed to put together and execute this project—many years of effort by a diverse set of highly skilled people were needed to make this happen. In academia, it’s pretty difficult for one professor to assemble that quantity of talent, and in industry it’s rarely the case that such a capable group has both a worthwhile project and the support needed to pursue something like this for several years before success. Alina invited me to the Jeopardy watching party
3 0.078599021 239 hunch net-2007-04-18-$50K Spock Challenge
Introduction: Apparently, the company Spock is setting up a $50k entity resolution challenge . $50k is much less than the Netflix challenge, but it’s effectively the same as Netflix until someone reaches 10% . It’s also nice that the Spock challenge has a short duration. The (visible) test set is of size 25k and the training set has size 75k.
4 0.074481979 97 hunch net-2005-07-23-Interesting papers at ACL
Introduction: A recent discussion indicated that one goal of this blog might be to allow people to post comments about recent papers that they liked. I think this could potentially be very useful, especially for those with diverse interests but only finite time to read through conference proceedings. ACL 2005 recently completed, and here are four papers from that conference that I thought were either good or perhaps of interest to a machine learning audience. David Chiang, A Hierarchical Phrase-Based Model for Statistical Machine Translation . (Best paper award.) This paper takes the standard phrase-based MT model that is popular in our field (basically, translate a sentence by individually translating phrases and reordering them according to a complicated statistical model) and extends it to take into account hierarchy in phrases, so that you can learn things like “X ‘s Y” -> “Y de X” in chinese, where X and Y are arbitrary phrases. This takes a step toward linguistic syntax for MT, whic
5 0.052801773 378 hunch net-2009-11-15-The Other Online Learning
Introduction: If you search for “online learning” with any major search engine , it’s interesting to note that zero of the results are for online machine learning. This may not be a mistake if you are committed to a global ordering. In other words, the number of people specifically interested in the least interesting top-10 online human learning result might exceed the number of people interested in online machine learning, even given the presence of the other 9 results. The essential observation here is that the process of human learning is a big business (around 5% of GDP) effecting virtually everyone. The internet is changing this dramatically, by altering the economics of teaching. Consider two possibilities: The classroom-style teaching environment continues as is, with many teachers for the same subject. All the teachers for one subject get together, along with perhaps a factor of 2 more people who are experts in online delivery. They spend a factor of 4 more time designing
6 0.045401275 161 hunch net-2006-03-05-“Structural” Learning
7 0.044741541 18 hunch net-2005-02-12-ROC vs. Accuracy vs. AROC
8 0.043362662 171 hunch net-2006-04-09-Progress in Machine Translation
9 0.041666381 277 hunch net-2007-12-12-Workshop Summary—Principles of Learning Problem Design
10 0.039136879 183 hunch net-2006-06-14-Explorations of Exploration
11 0.03910245 101 hunch net-2005-08-08-Apprenticeship Reinforcement Learning for Control
12 0.035643969 192 hunch net-2006-07-08-Some recent papers
13 0.035464279 418 hunch net-2010-12-02-Traffic Prediction Problem
14 0.035337035 178 hunch net-2006-05-08-Big machine learning
15 0.035330769 291 hunch net-2008-03-07-Spock Challenge Winners
16 0.034881938 304 hunch net-2008-06-27-Reviewing Horror Stories
17 0.034110811 146 hunch net-2006-01-06-MLTV
18 0.034010224 143 hunch net-2005-12-27-Automated Labeling
19 0.033699654 86 hunch net-2005-06-28-The cross validation problem: cash reward
20 0.033247389 51 hunch net-2005-04-01-The Producer-Consumer Model of Research
topicId topicWeight
[(0, 0.067), (1, 0.022), (2, 0.003), (3, 0.003), (4, 0.005), (5, 0.0), (6, -0.002), (7, 0.02), (8, -0.006), (9, -0.023), (10, -0.018), (11, 0.05), (12, -0.02), (13, -0.007), (14, -0.008), (15, 0.001), (16, 0.024), (17, 0.022), (18, 0.011), (19, -0.004), (20, -0.034), (21, -0.051), (22, -0.014), (23, -0.004), (24, 0.01), (25, 0.042), (26, 0.036), (27, 0.006), (28, 0.021), (29, 0.001), (30, 0.058), (31, 0.066), (32, 0.032), (33, -0.003), (34, -0.007), (35, -0.031), (36, 0.02), (37, 0.098), (38, -0.05), (39, -0.024), (40, 0.105), (41, -0.046), (42, -0.055), (43, -0.026), (44, 0.021), (45, -0.005), (46, 0.051), (47, 0.037), (48, 0.025), (49, -0.027)]
simIndex simValue blogId blogTitle
same-blog 1 0.95682687 94 hunch net-2005-07-13-Text Entailment at AAAI
Introduction: Rajat Raina presented a paper on the technique they used for the PASCAL Recognizing Textual Entailment challenge. “Text entailment” is the problem of deciding if one sentence implies another. For example the previous sentence entails: Text entailment is a decision problem. One sentence can imply another. The challenge was of the form: given an original sentence and another sentence predict whether there was an entailment. All current techniques for predicting correctness of an entailment are at the “flail” stage—accuracies of around 58% where humans could achieve near 100% accuracy, so there is much room to improve. Apparently, there may be another PASCAL challenge on this problem in the near future.
2 0.62861001 239 hunch net-2007-04-18-$50K Spock Challenge
Introduction: Apparently, the company Spock is setting up a $50k entity resolution challenge . $50k is much less than the Netflix challenge, but it’s effectively the same as Netflix until someone reaches 10% . It’s also nice that the Spock challenge has a short duration. The (visible) test set is of size 25k and the training set has size 75k.
3 0.59764248 291 hunch net-2008-03-07-Spock Challenge Winners
Introduction: The spock challenge for named entity recognition was won by Berno Stein , Sven Eissen, Tino Rub, Hagen Tonnies, Christof Braeutigam, and Martin Potthast .
4 0.50035006 190 hunch net-2006-07-06-Branch Prediction Competition
Introduction: Alan Fern points out the second branch prediction challenge (due September 29) which is a follow up to the first branch prediction competition . Branch prediction is one of the fundamental learning problems of the computer age: without it our computers might run an order of magnitude slower. This is a tough problem since there are sharp constraints on time and space complexity in an online environment. For machine learning, the “idealistic track” may fit well. Essentially, they remove these constraints to gain a weak upper bound on what might be done.
5 0.46775708 418 hunch net-2010-12-02-Traffic Prediction Problem
Introduction: Slashdot points out the Traffic Prediction Challenge which looks pretty fun. The temporal aspect seems to be very common in many real-world problems and somewhat understudied.
6 0.42131343 161 hunch net-2006-03-05-“Structural” Learning
7 0.41091436 171 hunch net-2006-04-09-Progress in Machine Translation
8 0.40034497 120 hunch net-2005-10-10-Predictive Search is Coming
9 0.38049418 373 hunch net-2009-10-03-Static vs. Dynamic multiclass prediction
10 0.35891506 193 hunch net-2006-07-09-The Stock Prediction Machine Learning Problem
11 0.34188628 26 hunch net-2005-02-21-Problem: Cross Validation
12 0.33964711 133 hunch net-2005-11-28-A question of quantification
13 0.33254337 56 hunch net-2005-04-14-Families of Learning Theory Statements
14 0.33153951 424 hunch net-2011-02-17-What does Watson mean?
15 0.3285569 160 hunch net-2006-03-02-Why do people count for learning?
16 0.32077309 277 hunch net-2007-12-12-Workshop Summary—Principles of Learning Problem Design
17 0.31956822 276 hunch net-2007-12-10-Learning Track of International Planning Competition
18 0.31920648 63 hunch net-2005-04-27-DARPA project: LAGR
19 0.31492716 144 hunch net-2005-12-28-Yet more nips thoughts
20 0.3122769 112 hunch net-2005-09-14-The Predictionist Viewpoint
topicId topicWeight
[(14, 0.509), (27, 0.192), (38, 0.065), (55, 0.052)]
simIndex simValue blogId blogTitle
same-blog 1 0.87483329 94 hunch net-2005-07-13-Text Entailment at AAAI
Introduction: Rajat Raina presented a paper on the technique they used for the PASCAL Recognizing Textual Entailment challenge. “Text entailment” is the problem of deciding if one sentence implies another. For example the previous sentence entails: Text entailment is a decision problem. One sentence can imply another. The challenge was of the form: given an original sentence and another sentence predict whether there was an entailment. All current techniques for predicting correctness of an entailment are at the “flail” stage—accuracies of around 58% where humans could achieve near 100% accuracy, so there is much room to improve. Apparently, there may be another PASCAL challenge on this problem in the near future.
2 0.73094213 471 hunch net-2012-08-24-Patterns for research in machine learning
Introduction: There are a handful of basic code patterns that I wish I was more aware of when I started research in machine learning. Each on its own may seem pointless, but collectively they go a long way towards making the typical research workflow more efficient. Here they are: Separate code from data. Separate input data, working data and output data. Save everything to disk frequently. Separate options from parameters. Do not use global variables. Record the options used to generate each run of the algorithm. Make it easy to sweep options. Make it easy to execute only portions of the code. Use checkpointing. Write demos and tests. Click here for discussion and examples for each item. Also see Charles Sutton’s and HackerNews’ thoughts on the same topic. My guess is that these patterns will not only be useful for machine learning, but also any other computational work that involves either a) processing large amounts of data, or b) algorithms that take a signif
3 0.63986909 407 hunch net-2010-08-23-Boosted Decision Trees for Deep Learning
Introduction: About 4 years ago, I speculated that decision trees qualify as a deep learning algorithm because they can make decisions which are substantially nonlinear in the input representation. Ping Li has proved this correct, empirically at UAI by showing that boosted decision trees can beat deep belief networks on versions of Mnist which are artificially hardened so as to make them solvable only by deep learning algorithms. This is an important point, because the ability to solve these sorts of problems is probably the best objective definition of a deep learning algorithm we have. I’m not that surprised. In my experience, if you can accept the computational drawbacks of a boosted decision tree, they can achieve pretty good performance. Geoff Hinton once told me that the great thing about deep belief networks is that they work. I understand that Ping had very substantial difficulty in getting this published, so I hope some reviewers step up to the standard of valuing wha
4 0.63518518 380 hunch net-2009-11-29-AI Safety
Introduction: Dan Reeves introduced me to Michael Vassar who ran the Singularity Summit and educated me a bit on the subject of AI safety which the Singularity Institute has small grants for . I still believe that interstellar space travel is necessary for long term civilization survival, and the AI is necessary for interstellar space travel . On these grounds alone, we could judge that developing AI is much more safe than not. Nevertheless, there is a basic reasonable fear, as expressed by some commenters, that AI could go bad. A basic scenario starts with someone inventing an AI and telling it to make as much money as possible. The AI promptly starts trading in various markets to make money. To improve, it crafts a virus that takes over most of the world’s computers using it as a surveillance network so that it can always make the right decision. The AI also branches out into any form of distance work, taking over the entire outsourcing process for all jobs that are entirely di
5 0.6264146 430 hunch net-2011-04-11-The Heritage Health Prize
Introduction: The Heritage Health Prize is potentially the largest prediction prize yet at $3M, which is sure to get many people interested. Several elements of the competition may be worth discussing. The most straightforward way for HPN to deploy this predictor is in determining who to cover with insurance. This might easily cover the costs of running the contest itself, but the value to the health system of a whole is minimal, as people not covered still exist. While HPN itself is a provider network, they have active relationships with a number of insurance companies, and the right to resell any entrant. It’s worth keeping in mind that the research and development may nevertheless end up being useful in the longer term, especially as entrants also keep the right to their code. The judging metric is something I haven’t seen previously. If a patient has probability 0.5 of being in the hospital 0 days and probability 0.5 of being in the hospital ~53.6 days, the optimal prediction in e
6 0.38138232 131 hunch net-2005-11-16-The Everything Ensemble Edge
7 0.36963478 72 hunch net-2005-05-16-Regret minimizing vs error limiting reductions
8 0.36698514 196 hunch net-2006-07-13-Regression vs. Classification as a Primitive
9 0.36332721 304 hunch net-2008-06-27-Reviewing Horror Stories
10 0.36126208 251 hunch net-2007-06-24-Interesting Papers at ICML 2007
11 0.36042228 352 hunch net-2009-05-06-Machine Learning to AI
12 0.36018309 288 hunch net-2008-02-10-Complexity Illness
13 0.358062 308 hunch net-2008-07-06-To Dual or Not
14 0.35784614 133 hunch net-2005-11-28-A question of quantification
15 0.35525325 14 hunch net-2005-02-07-The State of the Reduction
16 0.35523462 341 hunch net-2009-02-04-Optimal Proxy Loss for Classification
17 0.35500869 230 hunch net-2007-02-02-Thoughts regarding “Is machine learning different from statistics?”
18 0.35470766 172 hunch net-2006-04-14-JMLR is a success
19 0.35450312 274 hunch net-2007-11-28-Computational Consequences of Classification
20 0.35405162 247 hunch net-2007-06-14-Interesting Papers at COLT 2007