Paper Group NANR 90
Collaborative PAC Learning. Towards Decoding as Continuous Optimisation in Neural Machine Translation. Supervised Learning of Automatic Pyramid for Optimization-Based Multi-Document Summarization. PositionRank: An Unsupervised Approach to Keyphrase Extraction from Scholarly Documents. Question Difficulty – How to Estimate Without Norming, How to U …
Collaborative PAC Learning
| Title | Collaborative PAC Learning |
| Authors | Avrim Blum, Nika Haghtalab, Ariel D. Procaccia, Mingda Qiao |
| Abstract | We introduce a collaborative PAC learning model, in which k players attempt to learn the same underlying concept. We ask how much more information is required to learn an accurate classifier for all players simultaneously. We refer to the ratio between the sample complexity of collaborative PAC learning and its non-collaborative (single-player) counterpart as the overhead. We design learning algorithms with O(ln(k)) and O(ln^2(k)) overhead in the personalized and centralized variants our model. This gives an exponential improvement upon the naive algorithm that does not share information among players. We complement our upper bounds with an Omega(ln(k)) overhead lower bound, showing that our results are tight up to a logarithmic factor. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6833-collaborative-pac-learning |
| http://papers.nips.cc/paper/6833-collaborative-pac-learning.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-pac-learning |
| Repo | |
| Framework | |
Towards Decoding as Continuous Optimisation in Neural Machine Translation
| Title | Towards Decoding as Continuous Optimisation in Neural Machine Translation |
| Authors | Cong Duy Vu Hoang, Gholamreza Haffari, Trevor Cohn |
| Abstract | We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We reformulate decoding, a discrete optimization problem, into a continuous problem, such that optimization can make use of efficient gradient-based techniques. Our powerful decoding framework allows for more accurate decoding for standard neural machine translation models, as well as enabling decoding in intractable models such as intersection of several different NMT models. Our empirical results show that our decoding framework is effective, and can leads to substantial improvements in translations, especially in situations where greedy search and beam search are not feasible. Finally, we show how the technique is highly competitive with, and complementary to, reranking. |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1014/ |
| https://www.aclweb.org/anthology/D17-1014 | |
| PWC | https://paperswithcode.com/paper/towards-decoding-as-continuous-optimisation |
| Repo | |
| Framework | |
Supervised Learning of Automatic Pyramid for Optimization-Based Multi-Document Summarization
| Title | Supervised Learning of Automatic Pyramid for Optimization-Based Multi-Document Summarization |
| Authors | Maxime Peyrard, Judith Eckle-Kohler |
| Abstract | We present a new supervised framework that learns to estimate automatic Pyramid scores and uses them for optimization-based extractive multi-document summarization. For learning automatic Pyramid scores, we developed a method for automatic training data generation which is based on a genetic algorithm using automatic Pyramid as the fitness function. Our experimental evaluation shows that our new framework significantly outperforms strong baselines regarding automatic Pyramid, and that there is much room for improvement in comparison with the upper-bound for automatic Pyramid. |
| Tasks | Document Summarization, Multi-Document Summarization, Open Information Extraction, Text Summarization |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1100/ |
| https://www.aclweb.org/anthology/P17-1100 | |
| PWC | https://paperswithcode.com/paper/supervised-learning-of-automatic-pyramid-for |
| Repo | |
| Framework | |
PositionRank: An Unsupervised Approach to Keyphrase Extraction from Scholarly Documents
| Title | PositionRank: An Unsupervised Approach to Keyphrase Extraction from Scholarly Documents |
| Authors | Corina Florescu, Cornelia Caragea |
| Abstract | The large and growing amounts of online scholarly data present both challenges and opportunities to enhance knowledge discovery. One such challenge is to automatically extract a small set of keyphrases from a document that can accurately describe the document{'}s content and can facilitate fast information processing. In this paper, we propose PositionRank, an unsupervised model for keyphrase extraction from scholarly documents that incorporates information from all positions of a word{'}s occurrences into a biased PageRank. Our model obtains remarkable improvements in performance over PageRank models that do not take into account word positions as well as over strong baselines for this task. Specifically, on several datasets of research papers, PositionRank achieves improvements as high as 29.09{%}. |
| Tasks | Information Retrieval |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1102/ |
| https://www.aclweb.org/anthology/P17-1102 | |
| PWC | https://paperswithcode.com/paper/positionrank-an-unsupervised-approach-to |
| Repo | |
| Framework | |
Question Difficulty – How to Estimate Without Norming, How to Use for Automated Grading
| Title | Question Difficulty – How to Estimate Without Norming, How to Use for Automated Grading |
| Authors | Ulrike Pad{'o} |
| Abstract | Question difficulty estimates guide test creation, but are too costly for small-scale testing. We empirically verify that Bloom{'}s Taxonomy, a standard tool for difficulty estimation during question creation, reliably predicts question difficulty observed after testing in a short-answer corpus. We also find that difficulty is mirrored in the amount of variation in student answers, which can be computed before grading. We show that question difficulty and its approximations are useful for \textit{automated grading}, allowing us to identify the optimal feature set for grading each question even in an unseen-question setting. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5001/ |
| https://www.aclweb.org/anthology/W17-5001 | |
| PWC | https://paperswithcode.com/paper/question-difficulty-a-how-to-estimate-without |
| Repo | |
| Framework | |
From Small to Big Data: paper manuscripts to RDF triples of Australian Indigenous Vocabularies
| Title | From Small to Big Data: paper manuscripts to RDF triples of Australian Indigenous Vocabularies |
| Authors | Nick Thieberger, Conal Tuohy |
| Abstract | |
| Tasks | |
| Published | 2017-03-01 |
| URL | https://www.aclweb.org/anthology/W17-0103/ |
| https://www.aclweb.org/anthology/W17-0103 | |
| PWC | https://paperswithcode.com/paper/from-small-to-big-data-paper-manuscripts-to |
| Repo | |
| Framework | |
STREAMLInED Challenges: Aligning Research Interests with Shared Tasks
| Title | STREAMLInED Challenges: Aligning Research Interests with Shared Tasks |
| Authors | Gina-Anne Levow, Emily M. Bender, Patrick Littell, Kristen Howell, Shobhana Chelliah, Joshua Crowgey, Dan Garrette, Jeff Good, Sharon Hargus, David Inman, Michael Maxwell, Michael Tjalve, Fei Xia |
| Abstract | |
| Tasks | |
| Published | 2017-03-01 |
| URL | https://www.aclweb.org/anthology/W17-0106/ |
| https://www.aclweb.org/anthology/W17-0106 | |
| PWC | https://paperswithcode.com/paper/streamlined-challenges-aligning-research |
| Repo | |
| Framework | |
MERALI at SemEval-2017 Task 2 Subtask 1: a Cognitively Inspired approach
| Title | MERALI at SemEval-2017 Task 2 Subtask 1: a Cognitively Inspired approach |
| Authors | Enrico Mensa, Daniele P. Radicioni, Antonio Lieto |
| Abstract | In this paper we report on the participation of the MERALI system to the SemEval Task 2 Subtask 1. The MERALI system approaches conceptual similarity through a simple, cognitively inspired, heuristics; it builds on a linguistic resource, the TTCS-e, that relies on BabelNet, NASARI and ConceptNet. The linguistic resource in fact contains a novel mixture of common-sense and encyclopedic knowledge. The obtained results point out that there is ample room for improvement, so that they are used to elaborate on present limitations and on future steps. |
| Tasks | Common Sense Reasoning |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2038/ |
| https://www.aclweb.org/anthology/S17-2038 | |
| PWC | https://paperswithcode.com/paper/merali-at-semeval-2017-task-2-subtask-1-a |
| Repo | |
| Framework | |
Click reduction in fluent speech: a semi-automated analysis of Mangetti Dune !Xung
| Title | Click reduction in fluent speech: a semi-automated analysis of Mangetti Dune !Xung |
| Authors | Am Miller, a, Micha Elsner |
| Abstract | |
| Tasks | |
| Published | 2017-03-01 |
| URL | https://www.aclweb.org/anthology/W17-0115/ |
| https://www.aclweb.org/anthology/W17-0115 | |
| PWC | https://paperswithcode.com/paper/click-reduction-in-fluent-speech-a-semi |
| Repo | |
| Framework | |
Proceedings of the 21st Nordic Conference on Computational Linguistics
| Title | Proceedings of the 21st Nordic Conference on Computational Linguistics |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0200/ |
| https://www.aclweb.org/anthology/W17-0200 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-21st-nordic-conference-on |
| Repo | |
| Framework | |
Optimizing a PoS Tagset for Norwegian Dependency Parsing
| Title | Optimizing a PoS Tagset for Norwegian Dependency Parsing |
| Authors | Petter Hohle, Lilja {\O}vrelid, Erik Velldal |
| Abstract | |
| Tasks | Dependency Parsing, Feature Engineering, Morphological Analysis, Named Entity Recognition, Part-Of-Speech Tagging, Sentiment Analysis |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0217/ |
| https://www.aclweb.org/anthology/W17-0217 | |
| PWC | https://paperswithcode.com/paper/optimizing-a-pos-tagset-for-norwegian |
| Repo | |
| Framework | |
Converting the T"uBa-D/Z Treebank of German to Universal Dependencies
| Title | Converting the T"uBa-D/Z Treebank of German to Universal Dependencies |
| Authors | {\c{C}}a{\u{g}}r{\i} {\c{C}}{"o}ltekin, Ben Campbell, Erhard Hinrichs, Heike Telljohann |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0404/ |
| https://www.aclweb.org/anthology/W17-0404 | |
| PWC | https://paperswithcode.com/paper/converting-the-ta14ba-dz-treebank-of-german |
| Repo | |
| Framework | |
Udapi: Universal API for Universal Dependencies
| Title | Udapi: Universal API for Universal Dependencies |
| Authors | Martin Popel, Zden{\v{e}}k {\v{Z}}abokrtsk{'y}, Martin Vojtek |
| Abstract | |
| Tasks | Dependency Parsing, Tokenization |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0412/ |
| https://www.aclweb.org/anthology/W17-0412 | |
| PWC | https://paperswithcode.com/paper/udapi-universal-api-for-universal |
| Repo | |
| Framework | |
From Universal Dependencies to Abstract Syntax
| Title | From Universal Dependencies to Abstract Syntax |
| Authors | Aarne Ranta, Prasanth Kolachina |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0414/ |
| https://www.aclweb.org/anthology/W17-0414 | |
| PWC | https://paperswithcode.com/paper/from-universal-dependencies-to-abstract |
| Repo | |
| Framework | |
Ambiguity in Semantically Related Word Substitutions: an investigation in historical Bible translations
| Title | Ambiguity in Semantically Related Word Substitutions: an investigation in historical Bible translations |
| Authors | Maria Moritz, Marco B{"u}chler |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0505/ |
| https://www.aclweb.org/anthology/W17-0505 | |
| PWC | https://paperswithcode.com/paper/ambiguity-in-semantically-related-word |
| Repo | |
| Framework | |
