July 26, 2019

996 words 5 mins read

Paper Group NANR 168

``Haters gonna hate’': challenges for sentiment analysis of Facebook comments in Brazilian Portuguese. Applying the Rhetorical Structure Theory in Alzheimer patients’ speech. Experiments on Morphological Reinflection: CoNLL-2017 Shared Task. If you can’t beat them, join them: the University of Alberta system description. Formalization of Speech Ver …

``Haters gonna hate’': challenges for sentiment analysis of Facebook comments in Brazilian Portuguese


Title	``Haters gonna hate’': challenges for sentiment analysis of Facebook comments in Brazilian Portuguese \|
Authors	Juliano D. Antonio, Ana Carolina L. Santin
Abstract
Tasks	Sentiment Analysis
Published	2017-09-01
URL	https://www.aclweb.org/anthology/W17-3609/
PDF	https://www.aclweb.org/anthology/W17-3609
PWC	https://paperswithcode.com/paper/ahaters-gonna-hatea-challenges-for-sentiment
Repo
Framework

Applying the Rhetorical Structure Theory in Alzheimer patients’ speech


Title	Applying the Rhetorical Structure Theory in Alzheimer patients’ speech
Authors	Anayeli Paulino, Gerardo Sierra
Abstract
Tasks
Published	2017-09-01
URL	https://www.aclweb.org/anthology/W17-3605/
PDF	https://www.aclweb.org/anthology/W17-3605
PWC	https://paperswithcode.com/paper/applying-the-rhetorical-structure-theory-in
Repo
Framework

Experiments on Morphological Reinflection: CoNLL-2017 Shared Task


Title	Experiments on Morphological Reinflection: CoNLL-2017 Shared Task
Authors	Akhilesh Sudhakar, Anil Kumar Singh
Abstract
Tasks	Machine Translation, Morphological Inflection
Published	2017-08-01
URL	https://www.aclweb.org/anthology/K17-2007/
PDF	https://www.aclweb.org/anthology/K17-2007
PWC	https://paperswithcode.com/paper/experiments-on-morphological-reinflection-1
Repo
Framework

If you can’t beat them, join them: the University of Alberta system description


Title	If you can’t beat them, join them: the University of Alberta system description
Authors	Garrett Nicolai, Bradley Hauer, Mohammad Motallebi, Saeed Najafi, Grzegorz Kondrak
Abstract
Tasks
Published	2017-08-01
URL	https://www.aclweb.org/anthology/K17-2008/
PDF	https://www.aclweb.org/anthology/K17-2008
PWC	https://paperswithcode.com/paper/if-you-cant-beat-them-join-them-the
Repo
Framework

Formalization of Speech Verbs with NooJ for Machine Translation: the French Verb accuser


Title	Formalization of Speech Verbs with NooJ for Machine Translation: the French Verb accuser
Authors	Jouda Ghorbel
Abstract
Tasks	Machine Translation, Text Generation
Published	2017-09-01
URL	https://www.aclweb.org/anthology/W17-3807/
PDF	https://www.aclweb.org/anthology/W17-3807
PWC	https://paperswithcode.com/paper/formalization-of-speech-verbs-with-nooj-for
Repo
Framework

Opinion Target Extraction for Student Course Feedback


Title	Opinion Target Extraction for Student Course Feedback
Authors	Janaka Chathuranga, Shanika Ediriweera, Pranidhith Munasinghe, Ravindu Hasantha, Surangika Ranathunga
Abstract
Tasks
Published	2017-11-01
URL	https://www.aclweb.org/anthology/O17-1028/
PDF	https://www.aclweb.org/anthology/O17-1028
PWC	https://paperswithcode.com/paper/opinion-target-extraction-for-student-course
Repo
Framework

Using bilingual word-embeddings for multilingual collocation extraction


Title	Using bilingual word-embeddings for multilingual collocation extraction
Authors	Marcos Garcia, Marcos Garc{'\i}a-Salido, Margarita Alonso-Ramos
Abstract	This paper presents a new strategy for multilingual collocation extraction which takes advantage of parallel corpora to learn bilingual word-embeddings. Monolingual collocation candidates are retrieved using Universal Dependencies, while the distributional models are then applied to search for equivalents of the elements of each collocation in the target languages. The proposed method extracts not only collocation equivalents with direct translation between languages, but also other cases where the collocations in the two languages are not literal translations of each other. Several experiments -evaluating collocations with three syntactic patterns- in English, Spanish, and Portuguese show that our approach can effectively extract large pairs of bilingual equivalents with an average precision of about 90{%}. Moreover, preliminary results on comparable corpora suggest that the distributional models can be applied for identifying new bilingual collocations in different domains.
Tasks	Machine Translation, Word Embeddings
Published	2017-04-01
URL	https://www.aclweb.org/anthology/W17-1703/
PDF	https://www.aclweb.org/anthology/W17-1703
PWC	https://paperswithcode.com/paper/using-bilingual-word-embeddings-for
Repo
Framework

基於次頻道遞迴類神經網路之麥克風陣列電視回聲消除系統 (Subband Recurrent Neural Networks-based Microphone Array Television Echo Cancellation) [In Chinese]


Title	基於次頻道遞迴類神經網路之麥克風陣列電視回聲消除系統 (Subband Recurrent Neural Networks-based Microphone Array Television Echo Cancellation) [In Chinese]
Authors	Wei-Jung Hung, Shih-An Su, Yuan-Fu Liao
Abstract
Tasks
Published	2017-11-01
URL	https://www.aclweb.org/anthology/O17-1004/
PDF	https://www.aclweb.org/anthology/O17-1004
PWC	https://paperswithcode.com/paper/ao14e-eee-eccc2e-a1eoae-eaeeae2ec3c-subband
Repo
Framework

Extracting hypernym relations from Wikipedia disambiguation pages : comparing symbolic and machine learning approaches


Title	Extracting hypernym relations from Wikipedia disambiguation pages : comparing symbolic and machine learning approaches
Authors	Mouna Kamel, Cassia Trojahn, Adel Ghamnia, Nathalie Aussenac-Gilles, C{'e}cile Fabre
Abstract
Tasks	Information Retrieval
Published	2017-01-01
URL	https://www.aclweb.org/anthology/W17-6812/
PDF	https://www.aclweb.org/anthology/W17-6812
PWC	https://paperswithcode.com/paper/extracting-hypernym-relations-from-wikipedia
Repo
Framework

Modeling Quantification with Polysemous Nouns


Title	Modeling Quantification with Polysemous Nouns
Authors	Laura Kallmeyer, Rainer Osswald
Abstract
Tasks
Published	2017-01-01
URL	https://www.aclweb.org/anthology/W17-6914/
PDF	https://www.aclweb.org/anthology/W17-6914
PWC	https://paperswithcode.com/paper/modeling-quantification-with-polysemous-nouns
Repo
Framework

Exploring Substitutability through Discourse Adverbials and Multiple Judgments


Title	Exploring Substitutability through Discourse Adverbials and Multiple Judgments
Authors	Hannah Rohde, Anna Dickinson, Nathan Schneider, Annie Louis, Bonnie Webber
Abstract
Tasks
Published	2017-01-01
URL	https://www.aclweb.org/anthology/W17-6814/
PDF	https://www.aclweb.org/anthology/W17-6814
PWC	https://paperswithcode.com/paper/exploring-substitutability-through-discourse
Repo
Framework

Framework for the Analysis of Simplified Texts Taking Discourse into Account: the Basque Causal Relations as Case Study


Title	Framework for the Analysis of Simplified Texts Taking Discourse into Account: the Basque Causal Relations as Case Study
Authors	Itziar Gonzalez-Dios, Arantza Diaz de Ilarraza, Mikel Iruskieta
Abstract
Tasks	Text Simplification
Published	2017-09-01
URL	https://www.aclweb.org/anthology/W17-3607/
PDF	https://www.aclweb.org/anthology/W17-3607
PWC	https://paperswithcode.com/paper/framework-for-the-analysis-of-simplified
Repo
Framework

Improving neural tagging with lexical information


Title	Improving neural tagging with lexical information
Authors	Beno{^\i}t Sagot, H{'e}ctor Mart{'\i}nez Alonso
Abstract	Neural part-of-speech tagging has achieved competitive results with the incorporation of character-based and pre-trained word embeddings. In this paper, we show that a state-of-the-art bi-LSTM tagger can benefit from using information from morphosyntactic lexicons as additional input. The tagger, trained on several dozen languages, shows a consistent, average improvement when using lexical information, even when also using character-based embeddings, thus showing the complementarity of the different sources of lexical information. The improvements are particularly important for the smaller datasets.
Tasks	Part-Of-Speech Tagging, Word Embeddings
Published	2017-09-01
URL	https://www.aclweb.org/anthology/W17-6304/
PDF	https://www.aclweb.org/anthology/W17-6304
PWC	https://paperswithcode.com/paper/improving-neural-tagging-with-lexical
Repo
Framework

Combining Global Models for Parsing Universal Dependencies


Title	Combining Global Models for Parsing Universal Dependencies
Authors	Tianze Shi, Felix G. Wu, Xilun Chen, Yao Cheng
Abstract	We describe our entry, C2L2, to the CoNLL 2017 shared task on parsing Universal Dependencies from raw text. Our system features an ensemble of three global parsing paradigms, one graph-based and two transition-based. Each model leverages character-level bi-directional LSTMs as lexical feature extractors to encode morphological information. Though relying on baseline tokenizers and focusing only on parsing, our system ranked second in the official end-to-end evaluation with a macro-average of 75.00 LAS F1 score over 81 test treebanks. In addition, we had the top average performance on the four surprise languages and on the small treebank subset.
Tasks	Boundary Detection, Dependency Parsing, Part-Of-Speech Tagging, Tokenization
Published	2017-08-01
URL	https://www.aclweb.org/anthology/K17-3003/
PDF	https://www.aclweb.org/anthology/K17-3003
PWC	https://paperswithcode.com/paper/combining-global-models-for-parsing-universal
Repo
Framework

Handling Multiword Expressions in Causality Estimation


Title	Handling Multiword Expressions in Causality Estimation
Authors	Shota Sasaki, Sho Takase, Naoya Inoue, Naoaki Okazaki, Kentaro Inui
Abstract
Tasks	Common Sense Reasoning
Published	2017-01-01
URL	https://www.aclweb.org/anthology/W17-6937/
PDF	https://www.aclweb.org/anthology/W17-6937
PWC	https://paperswithcode.com/paper/handling-multiword-expressions-in-causality
Repo
Framework