May 4, 2019

1282 words 7 mins read

Paper Group NANR 159

Paper Group NANR 159

Why ``Blow Out’'? A Structural Analysis of the Movie Dialog Dataset. VoxSim: A Visual Platform for Modeling Motion Language. TextImager: a Distributed UIMA-based System for NLP. Frustratingly Easy Cross-Lingual Transfer for Transition-Based Dependency Parsing. Factoring Adjunction in Hierarchical Phrase-Based SMT. Proceedings of the 30th Pacific As …

Why ``Blow Out’'? A Structural Analysis of the Movie Dialog Dataset

Title Why ``Blow Out’'? A Structural Analysis of the Movie Dialog Dataset |
Authors Richard Searle, Megan Bingham-Walker
Abstract
Tasks Information Retrieval, Question Answering, Representation Learning
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-1625/
PDF https://www.aclweb.org/anthology/W16-1625
PWC https://paperswithcode.com/paper/why-blow-out-a-structural-analysis-of-the
Repo
Framework

VoxSim: A Visual Platform for Modeling Motion Language

Title VoxSim: A Visual Platform for Modeling Motion Language
Authors Nikhil Krishnaswamy, James Pustejovsky
Abstract Much existing work in text-to-scene generation focuses on generating static scenes. By introducing a focus on motion verbs, we integrate dynamic semantics into a rich formal model of events to generate animations in real time that correlate with human conceptions of the event described. This paper presents a working system that generates these animated scenes over a test set, discussing challenges encountered and describing the solutions implemented.
Tasks Scene Generation
Published 2016-12-01
URL https://www.aclweb.org/anthology/C16-2012/
PDF https://www.aclweb.org/anthology/C16-2012
PWC https://paperswithcode.com/paper/voxsim-a-visual-platform-for-modeling-motion
Repo
Framework

TextImager: a Distributed UIMA-based System for NLP

Title TextImager: a Distributed UIMA-based System for NLP
Authors Wahed Hemati, Tolga Uslu, Alex Mehler, er
Abstract More and more disciplines require NLP tools for performing automatic text analyses on various levels of linguistic resolution. However, the usage of established NLP frameworks is often hampered for several reasons: in most cases, they require basic to sophisticated programming skills, interfere with interoperability due to using non-standard I/O-formats and often lack tools for visualizing computational results. This makes it difficult especially for humanities scholars to use such frameworks. In order to cope with these challenges, we present TextImager, a UIMA-based framework that offers a range of NLP and visualization tools by means of a user-friendly GUI. Using TextImager requires no programming skills.
Tasks Sentiment Analysis, Text Classification
Published 2016-12-01
URL https://www.aclweb.org/anthology/C16-2013/
PDF https://www.aclweb.org/anthology/C16-2013
PWC https://paperswithcode.com/paper/textimager-a-distributed-uima-based-system
Repo
Framework

Frustratingly Easy Cross-Lingual Transfer for Transition-Based Dependency Parsing

Title Frustratingly Easy Cross-Lingual Transfer for Transition-Based Dependency Parsing
Authors Oph{'e}lie Lacroix, Lauriane Aufrant, Guillaume Wisniewski, Fran{\c{c}}ois Yvon
Abstract
Tasks Cross-Lingual Transfer, Dependency Parsing, Transition-Based Dependency Parsing
Published 2016-06-01
URL https://www.aclweb.org/anthology/N16-1121/
PDF https://www.aclweb.org/anthology/N16-1121
PWC https://paperswithcode.com/paper/frustratingly-easy-cross-lingual-transfer-for
Repo
Framework

Factoring Adjunction in Hierarchical Phrase-Based SMT

Title Factoring Adjunction in Hierarchical Phrase-Based SMT
Authors Sophie Arnoult, Khalil Sima{'}an
Abstract
Tasks Machine Translation
Published 2016-10-01
URL https://www.aclweb.org/anthology/W16-6402/
PDF https://www.aclweb.org/anthology/W16-6402
PWC https://paperswithcode.com/paper/factoring-adjunction-in-hierarchical-phrase
Repo
Framework

Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Oral Papers

Title Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Oral Papers
Authors
Abstract
Tasks
Published 2016-10-01
URL https://www.aclweb.org/anthology/papers/Y/Y16/Y16-2000/
PDF https://www.aclweb.org/anthology/Y16-2000
PWC https://paperswithcode.com/paper/proceedings-of-the-30th-pacific-asia-1
Repo
Framework

Statistical Modeling of Creole Genesis

Title Statistical Modeling of Creole Genesis
Authors Yugo Murawaki
Abstract
Tasks
Published 2016-06-01
URL https://www.aclweb.org/anthology/N16-1158/
PDF https://www.aclweb.org/anthology/N16-1158
PWC https://paperswithcode.com/paper/statistical-modeling-of-creole-genesis
Repo
Framework

Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Posters

Title Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Posters
Authors
Abstract
Tasks
Published 2016-10-01
URL https://www.aclweb.org/anthology/papers/Y/Y16/Y16-3000/
PDF https://www.aclweb.org/anthology/Y16-3000
PWC https://paperswithcode.com/paper/proceedings-of-the-30th-pacific-asia-2
Repo
Framework

HistoryComparator: Interactive Across-Time Comparison in Document Archives

Title HistoryComparator: Interactive Across-Time Comparison in Document Archives
Authors Adam Jatowt, Marc Bron
Abstract Recent years have witnessed significant increase in the number of large scale digital collections of archival documents such as news articles, books, etc. Typically, users access these collections through searching or browsing. In this paper we investigate another way of accessing temporal collections - across-time comparison, i.e., comparing query-relevant information at different periods in the past. We propose an interactive framework called HistoryComparator for contrastively analyzing concepts in archival document collections at different time periods.
Tasks Decision Making, Named Entity Recognition
Published 2016-12-01
URL https://www.aclweb.org/anthology/C16-2018/
PDF https://www.aclweb.org/anthology/C16-2018
PWC https://paperswithcode.com/paper/historycomparator-interactive-across-time
Repo
Framework

Deriving Morphological Analyzers from Example Inflections

Title Deriving Morphological Analyzers from Example Inflections
Authors Markus Forsberg, Mans Hulden
Abstract This paper presents a semi-automatic method to derive morphological analyzers from a limited number of example inflections suitable for languages with alphabetic writing systems. The system we present learns the inflectional behavior of morphological paradigms from examples and converts the learned paradigms into a finite-state transducer that is able to map inflected forms of previously unseen words into lemmas and corresponding morphosyntactic descriptions. We evaluate the system when provided with inflection tables for several languages collected from the Wiktionary.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1410/
PDF https://www.aclweb.org/anthology/L16-1410
PWC https://paperswithcode.com/paper/deriving-morphological-analyzers-from-example
Repo
Framework

A Customizable Editor for Text Simplification

Title A Customizable Editor for Text Simplification
Authors John Lee, Wenlong Zhao, Wenxiu Xie
Abstract We present a browser-based editor for simplifying English text. Given an input sentence, the editor performs both syntactic and lexical simplification. It splits a complex sentence into shorter ones, and suggests word substitutions in drop-down lists. The user can choose the best substitution from the list, undo any inappropriate splitting, and further edit the sentence as necessary. A significant novelty is that the system accepts a customized vocabulary list for a target reader population. It identifies all words in the text that do not belong to the list, and attempts to substitute them with words from the list, thus producing a text tailored for the targeted readers.
Tasks Lexical Simplification, Text Simplification
Published 2016-12-01
URL https://www.aclweb.org/anthology/C16-2020/
PDF https://www.aclweb.org/anthology/C16-2020
PWC https://paperswithcode.com/paper/a-customizable-editor-for-text-simplification
Repo
Framework

Threshold Learning for Optimal Decision Making

Title Threshold Learning for Optimal Decision Making
Authors Nathan F. Lepora
Abstract Decision making under uncertainty is commonly modelled as a process of competitive stochastic evidence accumulation to threshold (the drift-diffusion model). However, it is unknown how animals learn these decision thresholds. We examine threshold learning by constructing a reward function that averages over many trials to Wald’s cost function that defines decision optimality. These rewards are highly stochastic and hence challenging to optimize, which we address in two ways: first, a simple two-factor reward-modulated learning rule derived from Williams’ REINFORCE method for neural networks; and second, Bayesian optimization of the reward function with a Gaussian process. Bayesian optimization converges in fewer trials than REINFORCE but is slower computationally with greater variance. The REINFORCE method is also a better model of acquisition behaviour in animals and a similar learning rule has been proposed for modelling basal ganglia function.
Tasks Decision Making, Decision Making Under Uncertainty
Published 2016-12-01
URL http://papers.nips.cc/paper/6494-threshold-learning-for-optimal-decision-making
PDF http://papers.nips.cc/paper/6494-threshold-learning-for-optimal-decision-making.pdf
PWC https://paperswithcode.com/paper/threshold-learning-for-optimal-decision
Repo
Framework

Automatic label generation for news comment clusters

Title Automatic label generation for news comment clusters
Authors Ahmet Aker, Monica Paramita, Emina Kurtic, Adam Funk, Emma Barker, Mark Hepple, Rob Gaizauskas
Abstract
Tasks Information Retrieval, Text Generation
Published 2016-09-01
URL https://www.aclweb.org/anthology/W16-6610/
PDF https://www.aclweb.org/anthology/W16-6610
PWC https://paperswithcode.com/paper/automatic-label-generation-for-news-comment
Repo
Framework
Title Understanding Discourse on Work and Job-Related Well-Being in Public Social Media
Authors Tong Liu, Christopher Homan, Cecilia Ovesdotter Alm, Megan Lytle, Ann Marie White, Henry Kautz
Abstract
Tasks Active Learning
Published 2016-08-01
URL https://www.aclweb.org/anthology/P16-1099/
PDF https://www.aclweb.org/anthology/P16-1099
PWC https://paperswithcode.com/paper/understanding-discourse-on-work-and-job
Repo
Framework

Opinion Retrieval Systems using Tweet-external Factors

Title Opinion Retrieval Systems using Tweet-external Factors
Authors Yoon-Sung Kim, Young-In Song, Hae-Chang Rim
Abstract Opinion mining is a natural language processing technique which extracts subjective information from natural language text. To estimate an opinion about a query in large data collection, an opinion retrieval system that retrieves subjective and relevant information about the query can be useful. We present an opinion retrieval system that retrieves subjective and query-relevant tweets from Twitter, which is a useful source of obtaining real-time opinions. Our system outperforms previous opinion retrieval systems, and it further provides subjective information about Twitter authors and hashtags to describe their subjective tendencies.
Tasks Opinion Mining, Sentiment Analysis
Published 2016-12-01
URL https://www.aclweb.org/anthology/C16-2027/
PDF https://www.aclweb.org/anthology/C16-2027
PWC https://paperswithcode.com/paper/opinion-retrieval-systems-using-tweet
Repo
Framework
comments powered by Disqus