May 5, 2019

1314 words 7 mins read

Paper Group NAWR 9

Embeddings for Word Sense Disambiguation: An Evaluation Study. An Automatic Prosody Tagger for Spontaneous Speech. Better call Saul: Flexible Programming for Learning and Inference in NLP. Coarse-grained Argumentation Features for Scoring Persuasive Essays. QA-It: Classifying Non-Referential It for Question Answer Pairs. pke: an open source python- …

Embeddings for Word Sense Disambiguation: An Evaluation Study


Title	Embeddings for Word Sense Disambiguation: An Evaluation Study
Authors	Ignacio Iacobacci, Mohammad Taher Pilehvar, Roberto Navigli
Abstract
Tasks	Machine Translation, Sentiment Analysis, Word Embeddings, Word Sense Disambiguation
Published	2016-08-01
URL	https://www.aclweb.org/anthology/P16-1085/
PDF	https://www.aclweb.org/anthology/P16-1085
PWC	https://paperswithcode.com/paper/embeddings-for-word-sense-disambiguation-an
Repo	https://github.com/iiacobac/ims_wsd_emb
Framework	none

An Automatic Prosody Tagger for Spontaneous Speech


Title	An Automatic Prosody Tagger for Spontaneous Speech
Authors	M{'o}nica Dom{'\i}nguez, Mireia Farr{'u}s, Leo Wanner
Abstract	Speech prosody is known to be central in advanced communication technologies. However, despite the advances of theoretical studies in speech prosody, so far, no large scale prosody annotated resources that would facilitate empirical research and the development of empirical computational approaches are available. This is to a large extent due to the fact that current common prosody annotation conventions offer a descriptive framework of intonation contours and phrasing based on labels. This makes it difficult to reach a satisfactory inter-annotator agreement during the annotation of gold standard annotations and, subsequently, to create consistent large scale annotations. To address this problem, we present an annotation schema for prominence and boundary labeling of prosodic phrases based upon acoustic parameters and a tagger for prosody annotation at the prosodic phrase level. Evaluation proves that inter-annotator agreement reaches satisfactory values, from 0.60 to 0.80 Cohen{'}s kappa, while the prosody tagger achieves acceptable recall and f-measure figures for five spontaneous samples used in the evaluation of monologue and dialogue formats in English and Spanish. The work presented in this paper is a first step towards a semi-automatic acquisition of large corpora for empirical prosodic analysis.
Tasks
Published	2016-12-01
URL	https://www.aclweb.org/anthology/C16-1037/
PDF	https://www.aclweb.org/anthology/C16-1037
PWC	https://paperswithcode.com/paper/an-automatic-prosody-tagger-for-spontaneous
Repo	https://github.com/monikaUPF/modularProsodyTagger
Framework	none

Better call Saul: Flexible Programming for Learning and Inference in NLP


Title	Better call Saul: Flexible Programming for Learning and Inference in NLP
Authors	Parisa Kordjamshidi, Daniel Khashabi, Christos Christodoulopoulos, Bhargav Mangipudi, Sameer Singh, Dan Roth
Abstract	We present a novel way for designing complex joint inference and learning models using Saul (Kordjamshidi et al., 2015), a recently-introduced declarative learning-based programming language (DeLBP). We enrich Saul with components that are necessary for a broad range of learning based Natural Language Processing tasks at various levels of granularity. We illustrate these advances using three different, well-known NLP problems, and show how these generic learning and inference modules can directly exploit Saul{'}s graph-based data representation. These properties allow the programmer to easily switch between different model formulations and configurations, and consider various kinds of dependencies and correlations among variables of interest with minimal programming effort. We argue that Saul provides an extremely useful paradigm both for the design of advanced NLP systems and for supporting advanced research in NLP.
Tasks	Part-Of-Speech Tagging, Probabilistic Programming, Semantic Role Labeling
Published	2016-12-01
URL	https://www.aclweb.org/anthology/C16-1285/
PDF	https://www.aclweb.org/anthology/C16-1285
PWC	https://paperswithcode.com/paper/better-call-saul-flexible-programming-for
Repo	https://github.com/IllinoisCogComp/saul
Framework	none

Coarse-grained Argumentation Features for Scoring Persuasive Essays


Title	Coarse-grained Argumentation Features for Scoring Persuasive Essays
Authors	Debanjan Ghosh, Aquila Khanam, Yubo Han, Smar Muresan, a
Abstract
Tasks
Published	2016-08-01
URL	https://www.aclweb.org/anthology/P16-2089/
PDF	https://www.aclweb.org/anthology/P16-2089
PWC	https://paperswithcode.com/paper/coarse-grained-argumentation-features-for
Repo	https://github.com/debanjanghosh/argessay_ACL2016
Framework	none

QA-It: Classifying Non-Referential It for Question Answer Pairs


Title	QA-It: Classifying Non-Referential It for Question Answer Pairs
Authors	Timothy Lee, Alex Lutz, Jinho D. Choi
Abstract
Tasks	Coreference Resolution, Question Answering
Published	2016-08-01
URL	https://www.aclweb.org/anthology/P16-3020/
PDF	https://www.aclweb.org/anthology/P16-3020
PWC	https://paperswithcode.com/paper/qa-it-classifying-non-referential-it-for
Repo	https://github.com/emorynlp/qa-it
Framework	none

pke: an open source python-based keyphrase extraction toolkit


Title	pke: an open source python-based keyphrase extraction toolkit
Authors	Florian Boudin
Abstract	We describe pke, an open source python-based keyphrase extraction toolkit. It provides an end-to-end keyphrase extraction pipeline in which each component can be easily modified or extented to develop new approaches. pke also allows for easy benchmarking of state-of-the-art keyphrase extraction approaches, and ships with supervised models trained on the SemEval-2010 dataset.
Tasks	Text Categorization
Published	2016-12-01
URL	https://www.aclweb.org/anthology/C16-2015/
PDF	https://www.aclweb.org/anthology/C16-2015
PWC	https://paperswithcode.com/paper/pke-an-open-source-python-based-keyphrase
Repo	https://github.com/boudinfl/pke
Framework	none

Porting an Open Information Extraction System from English to German


Title	Porting an Open Information Extraction System from English to German
Authors	Tobias Falke, Gabriel Stanovsky, Iryna Gurevych, Ido Dagan
Abstract
Tasks	Open Information Extraction, Question Answering, Reading Comprehension
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1086/
PDF	https://www.aclweb.org/anthology/D16-1086
PWC	https://paperswithcode.com/paper/porting-an-open-information-extraction-system
Repo	https://github.com/UKPLab/props-de
Framework	none

Transition-Based Syntactic Linearization with Lookahead Features


Title	Transition-Based Syntactic Linearization with Lookahead Features
Authors	Ratish Puduppully, Yue Zhang, Manish Shrivastava
Abstract
Tasks	Language Modelling, Machine Translation, Structured Prediction
Published	2016-06-01
URL	https://www.aclweb.org/anthology/N16-1058/
PDF	https://www.aclweb.org/anthology/N16-1058
PWC	https://paperswithcode.com/paper/transition-based-syntactic-linearization-with
Repo	https://github.com/SUTDNLP/ZGen
Framework	none

Beyond Canonical Texts: A Computational Analysis of Fanfiction


Title	Beyond Canonical Texts: A Computational Analysis of Fanfiction
Authors	Smitha Milli, David Bamman
Abstract
Tasks
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1218/
PDF	https://www.aclweb.org/anthology/D16-1218
PWC	https://paperswithcode.com/paper/beyond-canonical-texts-a-computational
Repo	https://github.com/smilli/fanfiction
Framework	none

A Trainable Spaced Repetition Model for Language Learning


Title	A Trainable Spaced Repetition Model for Language Learning
Authors	Burr Settles, Brendan Meeder
Abstract
Tasks	Language Acquisition
Published	2016-08-01
URL	https://www.aclweb.org/anthology/P16-1174/
PDF	https://www.aclweb.org/anthology/P16-1174
PWC	https://paperswithcode.com/paper/a-trainable-spaced-repetition-model-for
Repo	https://github.com/duolingo/halflife-regression
Framework	none

A Neural Approach to Automated Essay Scoring


Title	A Neural Approach to Automated Essay Scoring
Authors	Kaveh Taghipour, Hwee Tou Ng
Abstract
Tasks	Feature Engineering, Machine Translation
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1193/
PDF	https://www.aclweb.org/anthology/D16-1193
PWC	https://paperswithcode.com/paper/a-neural-approach-to-automated-essay-scoring
Repo	https://github.com/nusnlp/nea
Framework	none

Speed-Accuracy Tradeoffs in Tagging with Variable-Order CRFs and Structured Sparsity


Title	Speed-Accuracy Tradeoffs in Tagging with Variable-Order CRFs and Structured Sparsity
Authors	Tim Vieira, Ryan Cotterell, Jason Eisner
Abstract
Tasks	Part-Of-Speech Tagging
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1206/
PDF	https://www.aclweb.org/anthology/D16-1206
PWC	https://paperswithcode.com/paper/speed-accuracy-tradeoffs-in-tagging-with
Repo	https://github.com/timvieira/vocrf
Framework	none

Demonyms and Compound Relational Nouns in Nominal Open IE


Title	Demonyms and Compound Relational Nouns in Nominal Open IE
Authors	Harinder Pal, {Mausam}
Abstract
Tasks	Open Information Extraction, Semantic Role Labeling
Published	2016-06-01
URL	https://www.aclweb.org/anthology/W16-1307/
PDF	https://www.aclweb.org/anthology/W16-1307
PWC	https://paperswithcode.com/paper/demonyms-and-compound-relational-nouns-in
Repo	https://github.com/knowitall/chunkedextractor
Framework	none

MultiVec: a Multilingual and Multilevel Representation Learning Toolkit for NLP


Title	MultiVec: a Multilingual and Multilevel Representation Learning Toolkit for NLP
Authors	Alex B{'e}rard, re, Christophe Servan, Olivier Pietquin, Laurent Besacier
Abstract	We present MultiVec, a new toolkit for computing continuous representations for text at different granularity levels (word-level or sequences of words). MultiVec includes word2vec{'}s features, paragraph vector (batch and online) and bivec for bilingual distributed representations. MultiVec also includes different distance measures between words and sequences of words. The toolkit is written in C++ and is aimed at being fast (in the same order of magnitude as word2vec), easy to use, and easy to extend. It has been evaluated on several NLP tasks: the analogical reasoning task, sentiment analysis, and crosslingual document classification.
Tasks	Document Classification, Representation Learning, Sentiment Analysis
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1662/
PDF	https://www.aclweb.org/anthology/L16-1662
PWC	https://paperswithcode.com/paper/multivec-a-multilingual-and-multilevel
Repo	https://github.com/eske/multivec
Framework	none

JATE 2.0: Java Automatic Term Extraction with Apache Solr


Title	JATE 2.0: Java Automatic Term Extraction with Apache Solr
Authors	Ziqi Zhang, Jie Gao, Fabio Ciravegna
Abstract	Automatic Term Extraction (ATE) or Recognition (ATR) is a fundamental processing step preceding many complex knowledge engineering tasks. However, few methods have been implemented as public tools and in particular, available as open-source freeware. Further, little effort is made to develop an adaptable and scalable framework that enables customization, development, and comparison of algorithms under a uniform environment. This paper introduces JATE 2.0, a complete remake of the free Java Automatic Term Extraction Toolkit (Zhang et al., 2008) delivering new features including: (1) highly modular, adaptable and scalable ATE thanks to integration with Apache Solr, the open source free-text indexing and search platform; (2) an extended collection of state-of-the-art algorithms. We carry out experiments on two well-known benchmarking datasets and compare the algorithms along the dimensions of effectiveness (precision) and efficiency (speed and memory consumption). To the best of our knowledge, this is by far the only free ATE library offering a flexible architecture and the most comprehensive collection of algorithms.
Tasks
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1359/
PDF	https://www.aclweb.org/anthology/L16-1359
PWC	https://paperswithcode.com/paper/jate-20-java-automatic-term-extraction-with
Repo	https://github.com/ziqizhang/jate
Framework	none