May 4, 2019

1218 words 6 mins read

Paper Group NANR 175

Similarity-Based Alignment of Monolingual Corpora for Text Simplification Purposes. Syntactic Parsing of Web Queries. Reviewers for Volume 42. Solving Event Quantification and Free Variable Problems in Semantics for Minimalist Grammars. An Experimental Study of Subject Properties in Korean Multiple Subject Constructions (MSCs). A Dataset for Joint …

Similarity-Based Alignment of Monolingual Corpora for Text Simplification Purposes


Title	Similarity-Based Alignment of Monolingual Corpora for Text Simplification Purposes
Authors	Sarah Albertsson, Evelina Rennes, Arne J{"o}nsson
Abstract	Comparable or parallel corpora are beneficial for many NLP tasks. The automatic collection of corpora enables large-scale resources, even for less-resourced languages, which in turn can be useful for deducing rules and patterns for text rewriting algorithms, a subtask of automatic text simplification. We present two methods for the alignment of Swedish easy-to-read text segments to text segments from a reference corpus. The first method (M1) was originally developed for the task of text reuse detection, measuring sentence similarity by a modified version of a TF-IDF vector space model. A second method (M2), also accounting for part-of-speech tags, was developed, and the methods were compared. For evaluation, a crowdsourcing platform was built for human judgement data collection, and preliminary results showed that cosine similarity relates better to human ranks than the Dice coefficient. We also saw a tendency that including syntactic context to the TF-IDF vector space model is beneficial for this kind of paraphrase alignment task.
Tasks	Text Simplification
Published	2016-12-01
URL	https://www.aclweb.org/anthology/W16-4118/
PDF	https://www.aclweb.org/anthology/W16-4118
PWC	https://paperswithcode.com/paper/similarity-based-alignment-of-monolingual
Repo
Framework

Syntactic Parsing of Web Queries


Title	Syntactic Parsing of Web Queries
Authors	Xiangyan Sun, Haixun Wang, Yanghua Xiao, Zhongyuan Wang
Abstract
Tasks
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1184/
PDF	https://www.aclweb.org/anthology/D16-1184
PWC	https://paperswithcode.com/paper/syntactic-parsing-of-web-queries
Repo
Framework

Reviewers for Volume 42


Title	Reviewers for Volume 42
Authors
Abstract
Tasks
Published	2016-12-01
URL	https://www.aclweb.org/anthology/J16-4013/
PDF	https://www.aclweb.org/anthology/J16-4013
PWC	https://paperswithcode.com/paper/reviewers-for-volume-42
Repo
Framework

Solving Event Quantification and Free Variable Problems in Semantics for Minimalist Grammars


Title	Solving Event Quantification and Free Variable Problems in Semantics for Minimalist Grammars
Authors	Yu Tomita
Abstract
Tasks
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-2020/
PDF	https://www.aclweb.org/anthology/Y16-2020
PWC	https://paperswithcode.com/paper/solving-event-quantification-and-free
Repo
Framework

An Experimental Study of Subject Properties in Korean Multiple Subject Constructions (MSCs)


Title	An Experimental Study of Subject Properties in Korean Multiple Subject Constructions (MSCs)
Authors	Ji-Hye Kim, Eunah Kim, James Yoon
Abstract
Tasks
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-2016/
PDF	https://www.aclweb.org/anthology/Y16-2016
PWC	https://paperswithcode.com/paper/an-experimental-study-of-subject-properties
Repo
Framework

A Dataset for Joint Noun-Noun Compound Bracketing and Interpretation


Title	A Dataset for Joint Noun-Noun Compound Bracketing and Interpretation
Authors	Murhaf Fares
Abstract
Tasks	Machine Translation
Published	2016-08-01
URL	https://www.aclweb.org/anthology/P16-3011/
PDF	https://www.aclweb.org/anthology/P16-3011
PWC	https://paperswithcode.com/paper/a-dataset-for-joint-noun-noun-compound
Repo
Framework

On the semantics of Korean modalized question


Title	On the semantics of Korean modalized question
Authors	Arum Kang
Abstract
Tasks
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-3020/
PDF	https://www.aclweb.org/anthology/Y16-3020
PWC	https://paperswithcode.com/paper/on-the-semantics-of-korean-modalized-question
Repo
Framework

The Interaction between SFP-Ne and SpOAs in Mandarin Chinese–A corpus based approach


Title	The Interaction between SFP-Ne and SpOAs in Mandarin Chinese–A corpus based approach
Authors	Yifan He
Abstract
Tasks
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-3019/
PDF	https://www.aclweb.org/anthology/Y16-3019
PWC	https://paperswithcode.com/paper/the-interaction-between-sfp-ne-and-spoas-in
Repo
Framework

Predicting and Using Implicit Discourse Elements in Chinese-English Translation


Title	Predicting and Using Implicit Discourse Elements in Chinese-English Translation
Authors	David Steele, Lucia Specia
Abstract
Tasks	Machine Translation
Published	2016-01-01
URL	https://www.aclweb.org/anthology/W16-3417/
PDF	https://www.aclweb.org/anthology/W16-3417
PWC	https://paperswithcode.com/paper/predicting-and-using-implicit-discourse
Repo
Framework

Supervised Keyphrase Extraction as Positive Unlabeled Learning


Title	Supervised Keyphrase Extraction as Positive Unlabeled Learning
Authors	Lucas Sterckx, Cornelia Caragea, Thomas Demeester, Chris Develder
Abstract
Tasks
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1198/
PDF	https://www.aclweb.org/anthology/D16-1198
PWC	https://paperswithcode.com/paper/supervised-keyphrase-extraction-as-positive
Repo
Framework

Differentia compositionem facit. A Slower-Paced and Reliable Parser for Latin


Title	Differentia compositionem facit. A Slower-Paced and Reliable Parser for Latin
Authors	Edoardo Maria Ponti, Marco Passarotti
Abstract	The Index Thomisticus Treebank is the largest available treebank for Latin; it contains Medieval Latin texts by Thomas Aquinas. After experimenting on its data with a number of dependency parsers based on different supervised machine learning techniques, we found that DeSR with a multilayer perceptron algorithm, a right-to-left transition, and a tailor-made feature model is the parser providing the highest accuracy rates. We improved the results further by using a technique that combines the output parses of DeSR with those provided by other parsers, outperforming the previous state of the art in parsing the Index Thomisticus Treebank. The key idea behind such improvement is to ensure a sufficient diversity and accuracy of the outputs to be combined; for this reason, we performed an in-depth evaluation of the results provided by the different parsers that we combined. Finally, we assessed that, although the general architecture of the parser is portable to Classical Latin, yet the model trained on Medieval Latin is inadequate for such purpose.
Tasks
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1108/
PDF	https://www.aclweb.org/anthology/L16-1108
PWC	https://paperswithcode.com/paper/differentia-compositionem-facit-a-slower
Repo
Framework

A Contextual Language Model to Improve Machine Translation of Pronouns by Re-ranking Translation Hypotheses


Title	A Contextual Language Model to Improve Machine Translation of Pronouns by Re-ranking Translation Hypotheses
Authors	Ngoc Quang Luong, Andrei Popescu-Belis
Abstract
Tasks	Language Modelling, Machine Translation
Published	2016-01-01
URL	https://www.aclweb.org/anthology/W16-3416/
PDF	https://www.aclweb.org/anthology/W16-3416
PWC	https://paperswithcode.com/paper/a-contextual-language-model-to-improve
Repo
Framework

IIT (BHU) Submission on the CoNLL-2016 Shared Task: Shallow Discourse Parsing using Semantic Lexicons


Title	IIT (BHU) Submission on the CoNLL-2016 Shared Task: Shallow Discourse Parsing using Semantic Lexicons
Authors	Manpreet Kaur, Nishu Kumari, Anil Kumar Singh, Rajeev Sangal
Abstract
Tasks
Published	2016-08-01
URL	https://www.aclweb.org/anthology/K16-2015/
PDF	https://www.aclweb.org/anthology/K16-2015
PWC	https://paperswithcode.com/paper/iit-bhu-submission-on-the-conll-2016-shared
Repo
Framework

Low-Rank Regression with Tensor Responses


Title	Low-Rank Regression with Tensor Responses
Authors	Guillaume Rabusseau, Hachem Kadri
Abstract	This paper proposes an efficient algorithm (HOLRR) to handle regression tasks where the outputs have a tensor structure. We formulate the regression problem as the minimization of a least square criterion under a multilinear rank constraint, a difficult non convex problem. HOLRR computes efficiently an approximate solution of this problem, with solid theoretical guarantees. A kernel extension is also presented. Experiments on synthetic and real data show that HOLRR computes accurate solutions while being computationally very competitive.
Tasks
Published	2016-12-01
URL	http://papers.nips.cc/paper/6302-low-rank-regression-with-tensor-responses
PDF	http://papers.nips.cc/paper/6302-low-rank-regression-with-tensor-responses.pdf
PWC	https://paperswithcode.com/paper/low-rank-regression-with-tensor-responses
Repo
Framework

A state-space model of cross-region dynamic connectivity in MEG/EEG


Title	A state-space model of cross-region dynamic connectivity in MEG/EEG
Authors	Ying Yang, Elissa Aminoff, Michael Tarr, Kass E. Robert
Abstract	Cross-region dynamic connectivity, which describes spatio-temporal dependence of neural activity among multiple brain regions of interest (ROIs), can provide important information for understanding cognition. For estimating such connectivity, magnetoencephalography (MEG) and electroencephalography (EEG) are well-suited tools because of their millisecond temporal resolution. However, localizing source activity in the brain requires solving an under-determined linear problem. In typical two-step approaches, researchers first solve the linear problem with general priors assuming independence across ROIs, and secondly quantify cross-region connectivity. In this work, we propose a one-step state-space model to improve estimation of dynamic connectivity. The model treats the mean activity in individual ROIs as the state variable, and describes non-stationary dynamic dependence across ROIs using time-varying auto-regression. Compared with a two-step method, which first obtains the commonly used minimum-norm estimates of source activity, and then fits the auto-regressive model, our state-space model yielded smaller estimation errors on simulated data where the model assumptions held. When applied on empirical MEG data from one participant in a scene-processing experiment, our state-space model also demonstrated intriguing preliminary results, indicating leading and lagged linear dependence between the early visual cortex and a higher-level scene-sensitive region, which could reflect feed-forward and feedback information flow within the visual cortex during scene processing.
Tasks	EEG
Published	2016-12-01
URL	http://papers.nips.cc/paper/6593-a-state-space-model-of-cross-region-dynamic-connectivity-in-megeeg
PDF	http://papers.nips.cc/paper/6593-a-state-space-model-of-cross-region-dynamic-connectivity-in-megeeg.pdf
PWC	https://paperswithcode.com/paper/a-state-space-model-of-cross-region-dynamic
Repo
Framework