Paper Group NANR 5
EICA Team at SemEval-2017 Task 3: Semantic and Metadata-based Features for Community Question Answering. Time-dependent spatially varying graphical models, with application to brain fMRI data analysis. A Transition-based System for Universal Dependency Parsing. Assessing Authenticity in Media Englishes and the Englishes of Popular Culture. Docforia …
EICA Team at SemEval-2017 Task 3: Semantic and Metadata-based Features for Community Question Answering
| Title | EICA Team at SemEval-2017 Task 3: Semantic and Metadata-based Features for Community Question Answering |
| Authors | Yufei Xie, Maoquan Wang, Jing Ma, Jian Jiang, Zhao Lu |
| Abstract | We describe our system for participating in SemEval-2017 Task 3 on Community Question Answering. Our approach relies on combining a rich set of various types of features: semantic and metadata. The most important group turned out to be the metadata feature and the semantic vectors trained on QatarLiving data. In the main Subtask C, our primary submission was ranked fourth, with a MAP of 13.48 and accuracy of 97.08. In Subtask A, our primary submission get into the top 50{%}. |
| Tasks | Community Question Answering, Feature Engineering, Feature Selection, Question Answering, Question Similarity |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2047/ |
| https://www.aclweb.org/anthology/S17-2047 | |
| PWC | https://paperswithcode.com/paper/eica-team-at-semeval-2017-task-3-semantic-and |
| Repo | |
| Framework | |
Time-dependent spatially varying graphical models, with application to brain fMRI data analysis
| Title | Time-dependent spatially varying graphical models, with application to brain fMRI data analysis |
| Authors | Kristjan Greenewald, Seyoung Park, Shuheng Zhou, Alexander Giessing |
| Abstract | In this work, we present an additive model for space-time data that splits the data into a temporally correlated component and a spatially correlated component. We model the spatially correlated portion using a time-varying Gaussian graphical model. Under assumptions on the smoothness of changes in covariance matrices, we derive strong single sample convergence results, confirming our ability to estimate meaningful graphical structures as they evolve over time. We apply our methodology to the discovery of time-varying spatial structures in human brain fMRI signals. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7165-time-dependent-spatially-varying-graphical-models-with-application-to-brain-fmri-data-analysis |
| http://papers.nips.cc/paper/7165-time-dependent-spatially-varying-graphical-models-with-application-to-brain-fmri-data-analysis.pdf | |
| PWC | https://paperswithcode.com/paper/time-dependent-spatially-varying-graphical |
| Repo | |
| Framework | |
A Transition-based System for Universal Dependency Parsing
| Title | A Transition-based System for Universal Dependency Parsing |
| Authors | Hao Wang, Hai Zhao, Zhisong Zhang |
| Abstract | This paper describes the system for our participation in the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. In this work, we design a system based on UDPipe1 for universal dependency parsing, where multilingual transition-based models are trained for different treebanks. Our system directly takes raw texts as input, performing several intermediate steps like tokenizing and tagging, and finally generates the corresponding dependency trees. For the special surprise languages for this task, we adopt a delexicalized strategy and predict basing on transfer learning from other related languages. In the final evaluation of the shared task, our system achieves a result of 66.53{%} in macro-averaged LAS F1-score. |
| Tasks | Dependency Parsing, Transfer Learning, Transition-Based Dependency Parsing |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-3020/ |
| https://www.aclweb.org/anthology/K17-3020 | |
| PWC | https://paperswithcode.com/paper/a-transition-based-system-for-universal |
| Repo | |
| Framework | |
Assessing Authenticity in Media Englishes and the Englishes of Popular Culture
| Title | Assessing Authenticity in Media Englishes and the Englishes of Popular Culture |
| Authors | Andrew Moody |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1003/ |
| https://www.aclweb.org/anthology/Y17-1003 | |
| PWC | https://paperswithcode.com/paper/assessing-authenticity-in-media-englishes-and |
| Repo | |
| Framework | |
Docforia: A Multilayer Document Model
| Title | Docforia: A Multilayer Document Model |
| Authors | Marcus Klang, Pierre Nugues |
| Abstract | |
| Tasks | Coreference Resolution, Dependency Parsing, Entity Linking, Named Entity Recognition, Part-Of-Speech Tagging, Question Answering, Semantic Role Labeling, Tokenization |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0227/ |
| https://www.aclweb.org/anthology/W17-0227 | |
| PWC | https://paperswithcode.com/paper/docforia-a-multilayer-document-model |
| Repo | |
| Framework | |
TTI-COIN at SemEval-2017 Task 10: Investigating Embeddings for End-to-End Relation Extraction from Scientific Papers
| Title | TTI-COIN at SemEval-2017 Task 10: Investigating Embeddings for End-to-End Relation Extraction from Scientific Papers |
| Authors | Tomoki Tsujimura, Makoto Miwa, Yutaka Sasaki |
| Abstract | This paper describes our TTI-COIN system that participated in SemEval-2017 Task 10. We investigated appropriate embeddings to adapt a neural end-to-end entity and relation extraction system LSTM-ER to this task. We participated in the full task setting of the entity segmentation, entity classification and relation classification (scenario 1) and the setting of relation classification only (scenario 3). The system was directly applied to the scenario 1 without modifying the codes thanks to its generality and flexibility. Our evaluation results show that the choice of appropriate pre-trained embeddings affected the performance significantly. With the best embeddings, our system was ranked third in the scenario 1 with the micro F1 score of 0.38. We also confirm that our system can produce the micro F1 score of 0.48 for the scenario 3 on the test data, and this score is close to the score of the 3rd ranked system in the task. |
| Tasks | Relation Classification, Relation Extraction, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2172/ |
| https://www.aclweb.org/anthology/S17-2172 | |
| PWC | https://paperswithcode.com/paper/tti-coin-at-semeval-2017-task-10 |
| Repo | |
| Framework | |
Universal Dependencies for Arabic Tweets
| Title | Universal Dependencies for Arabic Tweets |
| Authors | Fahad Albogamy, Allan Ramsay |
| Abstract | To facilitate cross-lingual studies, there is an increasing interest in identifying linguistic universals. Recently, a new universal scheme was designed as a part of universal dependency project. In this paper, we map the Arabic tweets dependency treebank (ATDT) to the Universal Dependency (UD) scheme to compare it to other language resources and for the purpose of cross-lingual studies. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1007/ |
| https://doi.org/10.26615/978-954-452-049-6_007 | |
| PWC | https://paperswithcode.com/paper/universal-dependencies-for-arabic-tweets |
| Repo | |
| Framework | |
Skip-Prop: Representing Sentences with One Vector Per Proposition
| Title | Skip-Prop: Representing Sentences with One Vector Per Proposition |
| Authors | Rachel Rudinger, Kevin Duh, Benjamin Van Durme |
| Abstract | |
| Tasks | Machine Translation, Question Answering, Semantic Role Labeling, Sentence Embedding |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6936/ |
| https://www.aclweb.org/anthology/W17-6936 | |
| PWC | https://paperswithcode.com/paper/skip-prop-representing-sentences-with-one |
| Repo | |
| Framework | |
XMU Neural Machine Translation Systems for WMT 17
| Title | XMU Neural Machine Translation Systems for WMT 17 |
| Authors | Zhixing Tan, Boli Wang, Jinming Hu, Yidong Chen, Xiaodong Shi |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4740/ |
| https://www.aclweb.org/anthology/W17-4740 | |
| PWC | https://paperswithcode.com/paper/xmu-neural-machine-translation-systems-for |
| Repo | |
| Framework | |
A Characterization Study of Arabic Twitter Data with a Benchmarking for State-of-the-Art Opinion Mining Models
| Title | A Characterization Study of Arabic Twitter Data with a Benchmarking for State-of-the-Art Opinion Mining Models |
| Authors | Ramy Baly, Gilbert Badaro, Georges El-Khoury, Rawan Moukalled, Rita Aoun, Hazem Hajj, Wassim El-Hajj, Nizar Habash, Khaled Shaban |
| Abstract | Opinion mining in Arabic is a challenging task given the rich morphology of the language. The task becomes more challenging when it is applied to Twitter data, which contains additional sources of noise, such as the use of unstandardized dialectal variations, the nonconformation to grammatical rules, the use of Arabizi and code-switching, and the use of non-text objects such as images and URLs to express opinion. In this paper, we perform an analytical study to observe how such linguistic phenomena vary across different Arab regions. This study of Arabic Twitter characterization aims at providing better understanding of Arabic Tweets, and fostering advanced research on the topic. Furthermore, we explore the performance of the two schools of machine learning on Arabic Twitter, namely the feature engineering approach and the deep learning approach. We consider models that have achieved state-of-the-art performance for opinion mining in English. Results highlight the advantages of using deep learning-based models, and confirm the importance of using morphological abstractions to address Arabic{'}s complex morphology. |
| Tasks | Feature Engineering, Opinion Mining, Sentiment Analysis |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1314/ |
| https://www.aclweb.org/anthology/W17-1314 | |
| PWC | https://paperswithcode.com/paper/a-characterization-study-of-arabic-twitter |
| Repo | |
| Framework | |
Cross-Lingual Syntax: Relating Grammatical Framework with Universal Dependencies
| Title | Cross-Lingual Syntax: Relating Grammatical Framework with Universal Dependencies |
| Authors | Aarne Ranta, Prasanth Kolachina, Thomas Hallgren |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0247/ |
| https://www.aclweb.org/anthology/W17-0247 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-syntax-relating-grammatical |
| Repo | |
| Framework | |
Gradual Learning of Matrix-Space Models of Language for Sentiment Analysis
| Title | Gradual Learning of Matrix-Space Models of Language for Sentiment Analysis |
| Authors | Shima Asaadi, Sebastian Rudolph |
| Abstract | Learning word representations to capture the semantics and compositionality of language has received much research interest in natural language processing. Beyond the popular vector space models, matrix representations for words have been proposed, since then, matrix multiplication can serve as natural composition operation. In this work, we investigate the problem of learning matrix representations of words. We present a learning approach for compositional matrix-space models for the task of sentiment analysis. We show that our approach, which learns the matrices gradually in two steps, outperforms other approaches and a gradient-descent baseline in terms of quality and computational cost. |
| Tasks | Representation Learning, Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2621/ |
| https://www.aclweb.org/anthology/W17-2621 | |
| PWC | https://paperswithcode.com/paper/gradual-learning-of-matrix-space-models-of |
| Repo | |
| Framework | |
L2F/INESC-ID at SemEval-2017 Tasks 1 and 2: Lexical and semantic features in word and textual similarity
| Title | L2F/INESC-ID at SemEval-2017 Tasks 1 and 2: Lexical and semantic features in word and textual similarity |
| Authors | Pedro Fialho, Hugo Patinho Rodrigues, Lu{'\i}sa Coheur, Paulo Quaresma |
| Abstract | This paper describes our approach to the SemEval-2017 {}Semantic Textual Similarity{''} and {}Multilingual Word Similarity{''} tasks. In the former, we test our approach in both English and Spanish, and use a linguistically-rich set of features. These move from lexical to semantic features. In particular, we try to take advantage of the recent Abstract Meaning Representation and SMATCH measure. Although without state of the art results, we introduce semantic structures in textual similarity and analyze their impact. Regarding word similarity, we target the English language and combine WordNet information with Word Embeddings. Without matching the best systems, our approach proved to be simple and effective. |
| Tasks | Semantic Textual Similarity, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2032/ |
| https://www.aclweb.org/anthology/S17-2032 | |
| PWC | https://paperswithcode.com/paper/l2finesc-id-at-semeval-2017-tasks-1-and-2 |
| Repo | |
| Framework | |
Generalizing GANs: A Turing Perspective
| Title | Generalizing GANs: A Turing Perspective |
| Authors | Roderich Gross, Yue Gu, Wei Li, Melvin Gauci |
| Abstract | Recently, a new class of machine learning algorithms has emerged, where models and discriminators are generated in a competitive setting. The most prominent example is Generative Adversarial Networks (GANs). In this paper we examine how these algorithms relate to the Turing test, and derive what - from a Turing perspective - can be considered their defining features. Based on these features, we outline directions for generalizing GANs - resulting in the family of algorithms referred to as Turing Learning. One such direction is to allow the discriminators to interact with the processes from which the data samples are obtained, making them “interrogators”, as in the Turing test. We validate this idea using two case studies. In the first case study, a computer infers the behavior of an agent while controlling its environment. In the second case study, a robot infers its own sensor configuration while controlling its movements. The results confirm that by allowing discriminators to interrogate, the accuracy of models is improved. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7211-generalizing-gans-a-turing-perspective |
| http://papers.nips.cc/paper/7211-generalizing-gans-a-turing-perspective.pdf | |
| PWC | https://paperswithcode.com/paper/generalizing-gans-a-turing-perspective |
| Repo | |
| Framework | |
Chinese Descriptive and Resultative V-de Constructions. A Dependency-based Analysis
| Title | Chinese Descriptive and Resultative V-de Constructions. A Dependency-based Analysis |
| Authors | Ruochen Niu |
| Abstract | |
| Tasks | Chunking |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6519/ |
| https://www.aclweb.org/anthology/W17-6519 | |
| PWC | https://paperswithcode.com/paper/chinese-descriptive-and-resultative-v-de |
| Repo | |
| Framework | |
