May 4, 2019

1177 words 6 mins read

Paper Group NANR 169

Combining Supervised and Unsupervised Enembles for Knowledge Base Population. Pomona at SemEval-2016 Task 11: Predicting Word Complexity Based on Corpus Frequency. Unsupervised Word Alignment by Agreement Under ITG Constraint. Yet Another Symmetrical and Real-time Word Alignment Method: Hierarchical Sub-sentential Alignment using F-measure. Proceed …

Combining Supervised and Unsupervised Enembles for Knowledge Base Population


Title	Combining Supervised and Unsupervised Enembles for Knowledge Base Population
Authors	Nazneen Fatema Rajani, Raymond Mooney
Abstract
Tasks	Entity Linking, Knowledge Base Population, Sentiment Analysis, Slot Filling, Word Sense Disambiguation
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1201/
PDF	https://www.aclweb.org/anthology/D16-1201
PWC	https://paperswithcode.com/paper/combining-supervised-and-unsupervised
Repo
Framework

Pomona at SemEval-2016 Task 11: Predicting Word Complexity Based on Corpus Frequency


Title	Pomona at SemEval-2016 Task 11: Predicting Word Complexity Based on Corpus Frequency
Authors	David Kauchak
Abstract
Tasks	Complex Word Identification, Lexical Simplification, Text Simplification
Published	2016-06-01
URL	https://www.aclweb.org/anthology/S16-1164/
PDF	https://www.aclweb.org/anthology/S16-1164
PWC	https://paperswithcode.com/paper/pomona-at-semeval-2016-task-11-predicting
Repo
Framework

Unsupervised Word Alignment by Agreement Under ITG Constraint


Title	Unsupervised Word Alignment by Agreement Under ITG Constraint
Authors	Hidetaka Kamigaito, Akihiro Tamura, Hiroya Takamura, Manabu Okumura, Eiichiro Sumita
Abstract
Tasks	Machine Translation, Word Alignment
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1210/
PDF	https://www.aclweb.org/anthology/D16-1210
PWC	https://paperswithcode.com/paper/unsupervised-word-alignment-by-agreement
Repo
Framework

Yet Another Symmetrical and Real-time Word Alignment Method: Hierarchical Sub-sentential Alignment using F-measure


Title	Yet Another Symmetrical and Real-time Word Alignment Method: Hierarchical Sub-sentential Alignment using F-measure
Authors	Hao Wang, Yves Lepage
Abstract
Tasks	Machine Translation, Word Alignment
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-2012/
PDF	https://www.aclweb.org/anthology/Y16-2012
PWC	https://paperswithcode.com/paper/yet-another-symmetrical-and-real-time-word
Repo
Framework

Proceedings of the Fourth Workshop on Metaphor in NLP


Title	Proceedings of the Fourth Workshop on Metaphor in NLP
Authors
Abstract
Tasks
Published	2016-06-01
URL	https://www.aclweb.org/anthology/W16-1100/
PDF	https://www.aclweb.org/anthology/W16-1100
PWC	https://paperswithcode.com/paper/proceedings-of-the-fourth-workshop-on-2
Repo
Framework

Domain Ontology Learning Enhanced by Optimized Relation Instance in DBpedia


Title	Domain Ontology Learning Enhanced by Optimized Relation Instance in DBpedia
Authors	Liumingjing Xiao, Chong Ruan, An Yang, Junhao Zhang, Junfeng Hu
Abstract	Ontologies are powerful to support semantic based applications and intelligent systems. While ontology learning are challenging due to its bottleneck in handcrafting structured knowledge sources and training data. To address this difficulty, many researchers turn to ontology enrichment and population using external knowledge sources such as DBpedia. In this paper, we propose a method using DBpedia in a different manner. We utilize relation instances in DBpedia to supervise the ontology learning procedure from unstructured text, rather than populate the ontology structure as a post-processing step. We construct three language resources in areas of computer science: enriched Wikipedia concept tree, domain ontology, and gold standard from NSFC taxonomy. Experiment shows that the result of ontology learning from corpus of computer science can be improved via the relation instances extracted from DBpedia in the same field. Furthermore, making distinction between the relation instances and applying a proper weighting scheme in the learning procedure lead to even better result.
Tasks
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1231/
PDF	https://www.aclweb.org/anthology/L16-1231
PWC	https://paperswithcode.com/paper/domain-ontology-learning-enhanced-by
Repo
Framework

Entity-balanced Gaussian pLSA for Automated Comparison


Title	Entity-balanced Gaussian pLSA for Automated Comparison
Authors	Danish Contractor, Parag Singla, {Mausam}
Abstract
Tasks	Decision Making
Published	2016-06-01
URL	https://www.aclweb.org/anthology/N16-1009/
PDF	https://www.aclweb.org/anthology/N16-1009
PWC	https://paperswithcode.com/paper/entity-balanced-gaussian-plsa-for-automated
Repo
Framework

Reshaped Wirtinger Flow for Solving Quadratic System of Equations


Title	Reshaped Wirtinger Flow for Solving Quadratic System of Equations
Authors	Huishuai Zhang, Yingbin Liang
Abstract	We study the problem of recovering a vector $\bx\in \bbR^n$ from its magnitude measurements $y_i=\langle \ba_i, \bx\rangle, i=1,…, m$. Our work is along the line of the Wirtinger flow (WF) approach \citet{candes2015phase}, which solves the problem by minimizing a nonconvex loss function via a gradient algorithm and can be shown to converge to a global optimal point under good initialization. In contrast to the smooth loss function used in WF, we adopt a nonsmooth but lower-order loss function, and design a gradient-like algorithm (referred to as reshaped-WF). We show that for random Gaussian measurements, reshaped-WF enjoys geometric convergence to a global optimal point as long as the number $m$ of measurements is at the order of $\cO(n)$, where $n$ is the dimension of the unknown $\bx$. This improves the sample complexity of WF, and achieves the same sample complexity as truncated-WF \citet{chen2015solving} but without truncation at gradient step. Furthermore, reshaped-WF costs less computationally than WF, and runs faster numerically than both WF and truncated-WF. Bypassing higher-order variables in the loss function and truncations in the gradient loop, analysis of reshaped-WF is simplified.
Tasks
Published	2016-12-01
URL	http://papers.nips.cc/paper/6319-reshaped-wirtinger-flow-for-solving-quadratic-system-of-equations
PDF	http://papers.nips.cc/paper/6319-reshaped-wirtinger-flow-for-solving-quadratic-system-of-equations.pdf
PWC	https://paperswithcode.com/paper/reshaped-wirtinger-flow-for-solving-quadratic
Repo
Framework

Supertagging With LSTMs


Title	Supertagging With LSTMs
Authors	Ashish Vaswani, Yonatan Bisk, Kenji Sagae, Ryan Musa
Abstract
Tasks	CCG Supertagging, Part-Of-Speech Tagging, Semantic Parsing
Published	2016-06-01
URL	https://www.aclweb.org/anthology/N16-1027/
PDF	https://www.aclweb.org/anthology/N16-1027
PWC	https://paperswithcode.com/paper/supertagging-with-lstms
Repo
Framework

Assessing Relative Sentence Complexity using an Incremental CCG Parser


Title	Assessing Relative Sentence Complexity using an Incremental CCG Parser
Authors	Bharat Ram Ambati, Siva Reddy, Mark Steedman
Abstract
Tasks	Language Modelling, Machine Translation, Speech Recognition
Published	2016-06-01
URL	https://www.aclweb.org/anthology/N16-1120/
PDF	https://www.aclweb.org/anthology/N16-1120
PWC	https://paperswithcode.com/paper/assessing-relative-sentence-complexity-using
Repo
Framework

Friends with Motives: Using Text to Infer Influence on SCOTUS


Title	Friends with Motives: Using Text to Infer Influence on SCOTUS
Authors	Yanchuan Sim, Bryan Routledge, Noah A. Smith
Abstract
Tasks	Decision Making
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1178/
PDF	https://www.aclweb.org/anthology/D16-1178
PWC	https://paperswithcode.com/paper/friends-with-motives-using-text-to-infer
Repo
Framework

Adapting the TANL tool suite to Universal Dependencies


Title	Adapting the TANL tool suite to Universal Dependencies
Authors	Maria Simi, Giuseppe Attardi
Abstract	TANL is a suite of tools for text analytics based on the software architecture paradigm of data driven pipelines. The strategies for upgrading TANL to the use of Universal Dependencies range from a minimalistic approach consisting of introducing pre/post-processing steps into the native pipeline to revising the whole pipeline. We explore the issue in the context of the Italian Treebank, considering both the efforts involved, how to avoid losing linguistically relevant information and the loss of accuracy in the process. In particular we compare different strategies for parsing and discuss the implications of simplifying the pipeline when detailed part-of-speech and morphological annotations are not available, as it is the case for less resourceful languages. The experiments are relative to the Italian linguistic pipeline, but the use of different parsers in our evaluations and the avoidance of language specific tagging make the results general enough to be useful in helping the transition to UD for other languages.
Tasks
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1264/
PDF	https://www.aclweb.org/anthology/L16-1264
PWC	https://paperswithcode.com/paper/adapting-the-tanl-tool-suite-to-universal
Repo
Framework

XRCE at SemEval-2016 Task 5: Feedbacked Ensemble Modeling on Syntactico-Semantic Knowledge for Aspect Based Sentiment Analysis


Title	XRCE at SemEval-2016 Task 5: Feedbacked Ensemble Modeling on Syntactico-Semantic Knowledge for Aspect Based Sentiment Analysis
Authors	Caroline Brun, Julien Perez, Claude Roux
Abstract
Tasks	Aspect-Based Sentiment Analysis, Dependency Parsing, Sentiment Analysis
Published	2016-06-01
URL	https://www.aclweb.org/anthology/S16-1044/
PDF	https://www.aclweb.org/anthology/S16-1044
PWC	https://paperswithcode.com/paper/xrce-at-semeval-2016-task-5-feedbacked
Repo
Framework

Proceedings of TextGraphs-10: the Workshop on Graph-based Methods for Natural Language Processing


Title	Proceedings of TextGraphs-10: the Workshop on Graph-based Methods for Natural Language Processing
Authors
Abstract
Tasks
Published	2016-06-01
URL	https://www.aclweb.org/anthology/W16-1400/
PDF	https://www.aclweb.org/anthology/W16-1400
PWC	https://paperswithcode.com/paper/proceedings-of-textgraphs-10-the-workshop-on
Repo
Framework

Effects of Creativity and Cluster Tightness on Short Text Clustering Performance


Title	Effects of Creativity and Cluster Tightness on Short Text Clustering Performance
Authors	Catherine Finegan-Dollak, Reed Coke, Rui Zhang, Xiangyi Ye, Dragomir Radev
Abstract
Tasks	Semantic Textual Similarity, Text Clustering, Word Embeddings
Published	2016-08-01
URL	https://www.aclweb.org/anthology/P16-1062/
PDF	https://www.aclweb.org/anthology/P16-1062
PWC	https://paperswithcode.com/paper/effects-of-creativity-and-cluster-tightness
Repo
Framework