Paper Group NANR 31
On the Logical Complexity of Autosegmental Representations. Scalable Model Selection for Belief Networks. On Integrating Discourse in Machine Translation. Hitachi at SemEval-2017 Task 12: System for temporal information extraction from clinical notes. GUIR at SemEval-2017 Task 12: A Framework for Cross-Domain Clinical Temporal Information Extractio …
On the Logical Complexity of Autosegmental Representations
| Title | On the Logical Complexity of Autosegmental Representations |
| Authors | Adam Jardine |
| Abstract | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/W17-3403/ |
| https://www.aclweb.org/anthology/W17-3403 | |
| PWC | https://paperswithcode.com/paper/on-the-logical-complexity-of-autosegmental |
| Repo | |
| Framework | |
Scalable Model Selection for Belief Networks
| Title | Scalable Model Selection for Belief Networks |
| Authors | Zhao Song, Yusuke Muraoka, Ryohei Fujimaki, Lawrence Carin |
| Abstract | We propose a scalable algorithm for model selection in sigmoid belief networks (SBNs), based on the factorized asymptotic Bayesian (FAB) framework. We derive the corresponding generalized factorized information criterion (gFIC) for the SBN, which is proven to be statistically consistent with the marginal log-likelihood. To capture the dependencies within hidden variables in SBNs, a recognition network is employed to model the variational distribution. The resulting algorithm, which we call FABIA, can simultaneously execute both model selection and inference by maximizing the lower bound of gFIC. On both synthetic and real data, our experiments suggest that FABIA, when compared to state-of-the-art algorithms for learning SBNs, $(i)$ produces a more concise model, thus enabling faster testing; $(ii)$ improves predictive performance; $(iii)$ accelerates convergence; and $(iv)$ prevents overfitting. |
| Tasks | Model Selection |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7047-scalable-model-selection-for-belief-networks |
| http://papers.nips.cc/paper/7047-scalable-model-selection-for-belief-networks.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-model-selection-for-belief-networks |
| Repo | |
| Framework | |
On Integrating Discourse in Machine Translation
| Title | On Integrating Discourse in Machine Translation |
| Authors | Karin Sim Smith |
| Abstract | As the quality of Machine Translation (MT) improves, research on improving discourse in automatic translations becomes more viable. This has resulted in an increase in the amount of work on discourse in MT. However many of the existing models and metrics have yet to integrate these insights. Part of this is due to the evaluation methodology, based as it is largely on matching to a single reference. At a time when MT is increasingly being used in a pipeline for other tasks, the semantic element of the translation process needs to be properly integrated into the task. Moreover, in order to take MT to another level, it will need to judge output not based on a single reference translation, but based on notions of fluency and of adequacy {–} ideally with reference to the source text. |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4814/ |
| https://www.aclweb.org/anthology/W17-4814 | |
| PWC | https://paperswithcode.com/paper/on-integrating-discourse-in-machine |
| Repo | |
| Framework | |
Hitachi at SemEval-2017 Task 12: System for temporal information extraction from clinical notes
| Title | Hitachi at SemEval-2017 Task 12: System for temporal information extraction from clinical notes |
| Authors | Sarath P R, Manik R, an, Yoshiki Niwa |
| Abstract | This paper describes the system developed for the task of temporal information extraction from clinical narratives in the context of the 2017 Clinical TempEval challenge. Clinical TempEval 2017 addressed the problem of temporal reasoning in the clinical domain by providing annotated clinical notes, pathology and radiology reports in line with Clinical TempEval challenges 2015/16, across two different evaluation phases focusing on cross domain adaptation. Our team focused on subtasks involving extractions of temporal spans and relations for which the developed systems showed average F-score of 0.45 and 0.47 across the two phases of evaluations. |
| Tasks | Domain Adaptation, Question Answering, Temporal Information Extraction, Text Classification, Unsupervised Domain Adaptation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2176/ |
| https://www.aclweb.org/anthology/S17-2176 | |
| PWC | https://paperswithcode.com/paper/hitachi-at-semeval-2017-task-12-system-for |
| Repo | |
| Framework | |
GUIR at SemEval-2017 Task 12: A Framework for Cross-Domain Clinical Temporal Information Extraction
| Title | GUIR at SemEval-2017 Task 12: A Framework for Cross-Domain Clinical Temporal Information Extraction |
| Authors | Sean MacAvaney, Arman Cohan, Nazli Goharian |
| Abstract | Clinical TempEval 2017 (SemEval 2017 Task 12) addresses the task of cross-domain temporal extraction from clinical text. We present a system for this task that uses supervised learning for the extraction of temporal expression and event spans with corresponding attributes and narrative container relations. Approaches include conditional random fields and decision tree ensembles, using lexical, syntactic, semantic, distributional, and rule-based features. Our system received best or second best scores in TIMEX3 span, EVENT span, and CONTAINS relation extraction. |
| Tasks | Domain Adaptation, Information Retrieval, Relation Extraction, Temporal Information Extraction |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2180/ |
| https://www.aclweb.org/anthology/S17-2180 | |
| PWC | https://paperswithcode.com/paper/guir-at-semeval-2017-task-12-a-framework-for |
| Repo | |
| Framework | |
Temporal information extraction from clinical text
| Title | Temporal information extraction from clinical text |
| Authors | Julien Tourille, Olivier Ferret, Xavier Tannier, Aur{'e}lie N{'e}v{'e}ol |
| Abstract | In this paper, we present a method for temporal relation extraction from clinical narratives in French and in English. We experiment on two comparable corpora, the MERLOT corpus and the THYME corpus, and show that a common approach can be used for both languages. |
| Tasks | Relation Extraction, Temporal Information Extraction |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2117/ |
| https://www.aclweb.org/anthology/E17-2117 | |
| PWC | https://paperswithcode.com/paper/temporal-information-extraction-from-clinical |
| Repo | |
| Framework | |
ParaDi: Dictionary of Paraphrases of Czech Complex Predicates with Light Verbs
| Title | ParaDi: Dictionary of Paraphrases of Czech Complex Predicates with Light Verbs |
| Authors | Petra Baran{\v{c}}{'\i}kov{'a}, V{'a}clava Kettnerov{'a} |
| Abstract | We present a new freely available dictionary of paraphrases of Czech complex predicates with light verbs, ParaDi. Candidates for single predicative paraphrases of selected complex predicates have been extracted automatically from large monolingual data using word2vec. They have been manually verified and further refined. We demonstrate one of many possible applications of ParaDi in an experiment with improving machine translation quality. |
| Tasks | Information Retrieval, Machine Translation, Question Answering |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1701/ |
| https://www.aclweb.org/anthology/W17-1701 | |
| PWC | https://paperswithcode.com/paper/paradi-dictionary-of-paraphrases-of-czech |
| Repo | |
| Framework | |
Proceedings of the 13th International Conference on Finite State Methods and Natural Language Processing (FSMNLP 2017)
| Title | Proceedings of the 13th International Conference on Finite State Methods and Natural Language Processing (FSMNLP 2017) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4000/ |
| https://www.aclweb.org/anthology/W17-4000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-13th-international-1 |
| Repo | |
| Framework | |
Talla at SemEval-2017 Task 3: Identifying Similar Questions Through Paraphrase Detection
| Title | Talla at SemEval-2017 Task 3: Identifying Similar Questions Through Paraphrase Detection |
| Authors | Byron Galbraith, Bhanu Pratap, Daniel Shank |
| Abstract | This paper describes our approach to the SemEval-2017 shared task of determining question-question similarity in a community question-answering setting (Task 3B). We extracted both syntactic and semantic similarity features between candidate questions, performed pairwise-preference learning to optimize for ranking order, and then trained a random forest classifier to predict whether the candidate questions are paraphrases of each other. This approach achieved a MAP of 45.7{%} out of max achievable 67.0{%} on the test set. |
| Tasks | Community Question Answering, Information Retrieval, Question Answering, Question Similarity, Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2062/ |
| https://www.aclweb.org/anthology/S17-2062 | |
| PWC | https://paperswithcode.com/paper/talla-at-semeval-2017-task-3-identifying |
| Repo | |
| Framework | |
VOILA: An Optimised Dialogue System for Interactively Learning Visually-Grounded Word Meanings (Demonstration System)
| Title | VOILA: An Optimised Dialogue System for Interactively Learning Visually-Grounded Word Meanings (Demonstration System) |
| Authors | Yanchao Yu, Arash Eshghi, Oliver Lemon |
| Abstract | We present VOILA: an optimised, multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human user. VOILA is: (1) able to learn new visual categories interactively from users from scratch; (2) trained on real human-human dialogues in the same domain, and so is able to conduct natural spontaneous dialogue; (3) optimised to find the most effective trade-off between the accuracy of the visual categories it learns and the cost it incurs to users. VOILA is deployed on Furhat, a human-like, multi-modal robot head with back-projection of the face, and a graphical virtual character. |
| Tasks | Active Learning |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5524/ |
| https://www.aclweb.org/anthology/W17-5524 | |
| PWC | https://paperswithcode.com/paper/voila-an-optimised-dialogue-system-for |
| Repo | |
| Framework | |
Using Electronic Dictionaries and NooJ to Generate Sentences Containing English Phrasal Verbs
| Title | Using Electronic Dictionaries and NooJ to Generate Sentences Containing English Phrasal Verbs |
| Authors | Peter A. Machonis |
| Abstract | |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3805/ |
| https://www.aclweb.org/anthology/W17-3805 | |
| PWC | https://paperswithcode.com/paper/using-electronic-dictionaries-and-nooj-to |
| Repo | |
| Framework | |
HeidelPlace: An Extensible Framework for Geoparsing
| Title | HeidelPlace: An Extensible Framework for Geoparsing |
| Authors | Ludwig Richter, Johanna Gei{\ss}, Andreas Spitz, Michael Gertz |
| Abstract | Geographic information extraction from textual data sources, called geoparsing, is a key task in text processing and central to subsequent spatial analysis approaches. Several geoparsers are available that support this task, each with its own (often limited or specialized) gazetteer and its own approaches to toponym detection and resolution. In this demonstration paper, we present HeidelPlace, an extensible framework in support of geoparsing. Key features of HeidelPlace include a generic gazetteer model that supports the integration of place information from different knowledge bases, and a pipeline approach that enables an effective combination of diverse modules tailored to specific geoparsing tasks. This makes HeidelPlace a valuable tool for testing and evaluating different gazetteer sources and geoparsing methods. In the demonstration, we show how to set up a geoparsing workflow with HeidelPlace and how it can be used to compare and consolidate the output of different geoparsing approaches. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-2015/ |
| https://www.aclweb.org/anthology/D17-2015 | |
| PWC | https://paperswithcode.com/paper/heidelplace-an-extensible-framework-for |
| Repo | |
| Framework | |
Generating Pattern-Based Entailment Graphs for Relation Extraction
| Title | Generating Pattern-Based Entailment Graphs for Relation Extraction |
| Authors | Kathrin Eichler, Feiyu Xu, Hans Uszkoreit, Sebastian Krause |
| Abstract | Relation extraction is the task of recognizing and extracting relations between entities or concepts in texts. A common approach is to exploit existing knowledge to learn linguistic patterns expressing the target relation and use these patterns for extracting new relation mentions. Deriving relation patterns automatically usually results in large numbers of candidates, which need to be filtered to derive a subset of patterns that reliably extract correct relation mentions. We address the pattern selection task by exploiting the knowledge represented by entailment graphs, which capture semantic relationships holding among the learned pattern candidates. This is motivated by the fact that a pattern may not express the target relation explicitly, but still be useful for extracting instances for which the relation holds, because its meaning entails the meaning of the target relation. We evaluate the usage of both automatically generated and gold-standard entailment graphs in a relation extraction scenario and present favorable experimental results, exhibiting the benefits of structuring and selecting patterns based on entailment graphs. |
| Tasks | Knowledge Base Population, Natural Language Inference, Relation Extraction |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1026/ |
| https://www.aclweb.org/anthology/S17-1026 | |
| PWC | https://paperswithcode.com/paper/generating-pattern-based-entailment-graphs |
| Repo | |
| Framework | |
Evaluation of word embeddings against cognitive processes: primed reaction times in lexical decision and naming tasks
| Title | Evaluation of word embeddings against cognitive processes: primed reaction times in lexical decision and naming tasks |
| Authors | Jeremy Auguste, Arnaud Rey, Benoit Favre |
| Abstract | This work presents a framework for word similarity evaluation grounded on cognitive sciences experimental data. Word pair similarities are compared to reaction times of subjects in large scale lexical decision and naming tasks under semantic priming. Results show that GloVe embeddings lead to significantly higher correlation with experimental measurements than other controlled and off-the-shelf embeddings, and that the choice of a training corpus is less important than that of the algorithm. Comparison of rankings with other datasets shows that the cognitive phenomenon covers more aspects than simply word relatedness or similarity. |
| Tasks | Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5304/ |
| https://www.aclweb.org/anthology/W17-5304 | |
| PWC | https://paperswithcode.com/paper/evaluation-of-word-embeddings-against |
| Repo | |
| Framework | |
Learning to Solve Geometry Problems from Natural Language Demonstrations in Textbooks
| Title | Learning to Solve Geometry Problems from Natural Language Demonstrations in Textbooks |
| Authors | Mrinmaya Sachan, Eric Xing |
| Abstract | Humans as well as animals are good at imitation. Inspired by this, the learning by demonstration view of machine learning learns to perform a task from detailed example demonstrations. In this paper, we introduce the task of question answering using natural language demonstrations where the question answering system is provided with detailed demonstrative solutions to questions in natural language. As a case study, we explore the task of learning to solve geometry problems using demonstrative solutions available in textbooks. We collect a new dataset of demonstrative geometry solutions from textbooks and explore approaches that learn to interpret these demonstrations as well as to use these interpretations to solve geometry problems. Our approaches show improvements over the best previously published system for solving geometry problems. |
| Tasks | Question Answering |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1029/ |
| https://www.aclweb.org/anthology/S17-1029 | |
| PWC | https://paperswithcode.com/paper/learning-to-solve-geometry-problems-from |
| Repo | |
| Framework | |
