May 4, 2019

1064 words 5 mins read

Paper Group NANR 188

Squibs: Restricted Non-Projectivity: Coverage vs. Efficiency. Squibs: Towards a Catalogue of Linguistic Graph Banks. Using lexical and Dependency Features to Disambiguate Discourse Connectives in Hindi. IXA Biomedical Translation System at WMT16 Biomedical Translation Task. Learning to Capitalize with Character-Level Recurrent Neural Networks: An E …

Squibs: Restricted Non-Projectivity: Coverage vs. Efficiency


Title	Squibs: Restricted Non-Projectivity: Coverage vs. Efficiency
Authors	Carlos G{'o}mez-Rodr{'\i}guez
Abstract
Tasks
Published	2016-12-01
URL	https://www.aclweb.org/anthology/J16-4008/
PDF	https://www.aclweb.org/anthology/J16-4008
PWC	https://paperswithcode.com/paper/squibs-restricted-non-projectivity-coverage
Repo
Framework

Squibs: Towards a Catalogue of Linguistic Graph Banks


Title	Squibs: Towards a Catalogue of Linguistic Graph Banks
Authors	Marco Kuhlmann, Stephan Oepen
Abstract
Tasks
Published	2016-12-01
URL	https://www.aclweb.org/anthology/J16-4009/
PDF	https://www.aclweb.org/anthology/J16-4009
PWC	https://paperswithcode.com/paper/squibs-towards-a-catalogue-of-linguistic
Repo
Framework

Using lexical and Dependency Features to Disambiguate Discourse Connectives in Hindi


Title	Using lexical and Dependency Features to Disambiguate Discourse Connectives in Hindi
Authors	Rohit Jain, Himanshu Sharma, Dipti Sharma
Abstract	Discourse parsing is a challenging task in NLP and plays a crucial role in discourse analysis. To enable discourse analysis for Hindi, Hindi Discourse Relations Bank was created on a subset of Hindi TreeBank. The benefits of a discourse analyzer in automated discourse analysis, question summarization and question answering domains has motivated us to begin work on a discourse analyzer for Hindi. In this paper, we focus on discourse connective identification for Hindi. We explore various available syntactic features for this task. We also explore the use of dependency tree parses present in the Hindi TreeBank and study the impact of the same on the performance of the system. We report that the novel dependency features introduced have a higher impact on precision, in comparison to the syntactic features previously used for this task. In addition, we report a high accuracy of 96{%} for this task.
Tasks	Question Answering
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1276/
PDF	https://www.aclweb.org/anthology/L16-1276
PWC	https://paperswithcode.com/paper/using-lexical-and-dependency-features-to
Repo
Framework

IXA Biomedical Translation System at WMT16 Biomedical Translation Task


Title	IXA Biomedical Translation System at WMT16 Biomedical Translation Task
Authors	Olatz Perez-de-Vi{~n}aspre, Gorka Labaka
Abstract
Tasks	Language Modelling, Machine Translation, Transliteration
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2338/
PDF	https://www.aclweb.org/anthology/W16-2338
PWC	https://paperswithcode.com/paper/ixa-biomedical-translation-system-at-wmt16
Repo
Framework

Learning to Capitalize with Character-Level Recurrent Neural Networks: An Empirical Study


Title	Learning to Capitalize with Character-Level Recurrent Neural Networks: An Empirical Study
Authors	Raymond Hendy Susanto, Hai Leong Chieu, Wei Lu
Abstract
Tasks	Language Modelling, Machine Translation, Named Entity Recognition
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1225/
PDF	https://www.aclweb.org/anthology/D16-1225
PWC	https://paperswithcode.com/paper/learning-to-capitalize-with-character-level
Repo
Framework

Nearly Isometric Embedding by Relaxation


Title	Nearly Isometric Embedding by Relaxation
Authors	James Mcqueen, Marina Meila, Dominique Joncas
Abstract	Many manifold learning algorithms aim to create embeddings with low or no distortion (i.e. isometric). If the data has intrinsic dimension d, it is often impossible to obtain an isometric embedding in d dimensions, but possible in s > d dimensions. Yet, most geometry preserving algorithms cannot do the latter. This paper proposes an embedding algorithm that overcomes this problem. The algorithm directly computes, for any data embedding Y, a distortion loss(Y), and iteratively updates Y in order to decrease it. The distortion measure we propose is based on the push-forward Riemannian metric associated with the coordinates Y. The experiments confirm the superiority of our algorithm in obtaining low distortion embeddings.
Tasks
Published	2016-12-01
URL	http://papers.nips.cc/paper/6535-nearly-isometric-embedding-by-relaxation
PDF	http://papers.nips.cc/paper/6535-nearly-isometric-embedding-by-relaxation.pdf
PWC	https://paperswithcode.com/paper/nearly-isometric-embedding-by-relaxation
Repo
Framework

Using the verifiability of details as a test of deception: A conceptual framework for the automation of the verifiability approach


Title	Using the verifiability of details as a test of deception: A conceptual framework for the automation of the verifiability approach
Authors	Bennett Kleinberg, Galit Nahari, Bruno Verschuere
Abstract
Tasks	Deception Detection, Named Entity Recognition
Published	2016-06-01
URL	https://www.aclweb.org/anthology/W16-0803/
PDF	https://www.aclweb.org/anthology/W16-0803
PWC	https://paperswithcode.com/paper/using-the-verifiability-of-details-as-a-test
Repo
Framework

Bridging Relations in Polish: Adaptation of Existing Typologies


Title	Bridging Relations in Polish: Adaptation of Existing Typologies
Authors	Maciej Ogrodniczuk, Magdalena Zawis{\l}awska
Abstract
Tasks	Coreference Resolution
Published	2016-06-01
URL	https://www.aclweb.org/anthology/W16-0703/
PDF	https://www.aclweb.org/anthology/W16-0703
PWC	https://paperswithcode.com/paper/bridging-relations-in-polish-adaptation-of
Repo
Framework

Error analysis for anaphora resolution in Russian: new challenging issues for anaphora resolution task in a morphologically rich language


Title	Error analysis for anaphora resolution in Russian: new challenging issues for anaphora resolution task in a morphologically rich language
Authors	Svetlana Toldova, Ilya Azerkovich, Alina Ladygina, Anna Roitberg, Maria Vasilyeva
Abstract
Tasks	Coreference Resolution
Published	2016-06-01
URL	https://www.aclweb.org/anthology/W16-0711/
PDF	https://www.aclweb.org/anthology/W16-0711
PWC	https://paperswithcode.com/paper/error-analysis-for-anaphora-resolution-in
Repo
Framework

Automatically Suggesting Example Sentences of Near-Synonyms for Language Learners


Title	Automatically Suggesting Example Sentences of Near-Synonyms for Language Learners
Authors	Chieh-Yang Huang, Nicole Peinelt, Lun-Wei Ku
Abstract	In this paper, we propose GiveMeExample that ranks example sentences according to their capacity of demonstrating the differences among English and Chinese near-synonyms for language learners. The difficulty of the example sentences is automatically detected. Furthermore, the usage models of the near-synonyms are built by the GMM and Bi-LSTM models to suggest the best elaborative sentences. Experiments show the good performance both in the fill-in-the-blank test and on the manually labeled gold data, that is, the built models can select the appropriate words for the given context and vice versa.
Tasks
Published	2016-12-01
URL	https://www.aclweb.org/anthology/C16-2063/
PDF	https://www.aclweb.org/anthology/C16-2063
PWC	https://paperswithcode.com/paper/automatically-suggesting-example-sentences-of
Repo
Framework

Semi-supervised and unsupervised categorization of posts in Web discussion forums using part-of-speech information and minimal features


Title	Semi-supervised and unsupervised categorization of posts in Web discussion forums using part-of-speech information and minimal features
Authors	Krish Perumal, Graeme Hirst
Abstract
Tasks	Information Retrieval
Published	2016-06-01
URL	https://www.aclweb.org/anthology/W16-0417/
PDF	https://www.aclweb.org/anthology/W16-0417
PWC	https://paperswithcode.com/paper/semi-supervised-and-unsupervised
Repo
Framework

Language Identification in Code-Switched Text Using Conditional Random Fields and Babelnet


Title	Language Identification in Code-Switched Text Using Conditional Random Fields and Babelnet
Authors	Utpal Kumar Sikdar, Bj{"o}rn Gamb{"a}ck
Abstract
Tasks	Language Identification
Published	2016-11-01
URL	https://www.aclweb.org/anthology/W16-5817/
PDF	https://www.aclweb.org/anthology/W16-5817
PWC	https://paperswithcode.com/paper/language-identification-in-code-switched-text
Repo
Framework

Richer Event Description: Integrating event coreference with temporal, causal and bridging annotation


Title	Richer Event Description: Integrating event coreference with temporal, causal and bridging annotation
Authors	Tim O{'}Gorman, Kristin Wright-Bettner, Martha Palmer
Abstract
Tasks
Published	2016-11-01
URL	https://www.aclweb.org/anthology/W16-5706/
PDF	https://www.aclweb.org/anthology/W16-5706
PWC	https://paperswithcode.com/paper/richer-event-description-integrating-event
Repo
Framework

CMU at SemEval-2016 Task 8: Graph-based AMR Parsing with Infinite Ramp Loss


Title	CMU at SemEval-2016 Task 8: Graph-based AMR Parsing with Infinite Ramp Loss
Authors	Jeffrey Flanigan, Chris Dyer, Noah A. Smith, Jaime Carbonell
Abstract
Tasks	Amr Parsing, Structured Prediction
Published	2016-06-01
URL	https://www.aclweb.org/anthology/S16-1186/
PDF	https://www.aclweb.org/anthology/S16-1186
PWC	https://paperswithcode.com/paper/cmu-at-semeval-2016-task-8-graph-based-amr
Repo
Framework

Word-Level Language Identification and Predicting Codeswitching Points in Swahili-English Language Data


Title	Word-Level Language Identification and Predicting Codeswitching Points in Swahili-English Language Data
Authors	Mario Piergallini, Rouzbeh Shirvani, Gauri S. Gautam, Mohamed Chouikha
Abstract
Tasks	Language Identification, Sentiment Analysis, Speech Recognition
Published	2016-11-01
URL	https://www.aclweb.org/anthology/W16-5803/
PDF	https://www.aclweb.org/anthology/W16-5803
PWC	https://paperswithcode.com/paper/word-level-language-identification-and
Repo
Framework