October 16, 2019

2211 words 11 mins read

Paper Group NANR 25

Paper Group NANR 25

Abstract Meaning Representation of Constructions: The More We Include, the Better the Representation. Embedding WordNet Knowledge for Textual Entailment. A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge. KOI at SemEval-2018 Task 5: Building Knowledge Graph of Incidents. WSNet: Learning Compact and Efficient Networks with …

Abstract Meaning Representation of Constructions: The More We Include, the Better the Representation

Title Abstract Meaning Representation of Constructions: The More We Include, the Better the Representation
Authors Claire Bonial, Bianca Badarau, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Tim O{'}Gorman, Martha Palmer, Nathan Schneider
Abstract
Tasks Machine Translation, Question Answering
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1266/
PDF https://www.aclweb.org/anthology/L18-1266
PWC https://paperswithcode.com/paper/abstract-meaning-representation-of
Repo
Framework

Embedding WordNet Knowledge for Textual Entailment

Title Embedding WordNet Knowledge for Textual Entailment
Authors Yunshi Lan, Jing Jiang
Abstract In this paper, we study how we can improve a deep learning approach to textual entailment by incorporating lexical entailment relations from WordNet. Our idea is to embed the lexical entailment knowledge contained in WordNet in specially-learned word vectors, which we call {``}entailment vectors.{''} We present a standard neural network model and a novel set-theoretic model to learn these entailment vectors from word pairs with known lexical entailment relations derived from WordNet. We further incorporate these entailment vectors into a decomposable attention model for textual entailment and evaluate the model on the SICK and the SNLI dataset. We find that using these special entailment word vectors, we can significantly improve the performance of textual entailment compared with a baseline that uses only standard word2vec vectors. The final performance of our model is close to or above the state of the art, but our method does not rely on any manually-crafted rules or extensive syntactic features. |
Tasks Feature Engineering, Natural Language Inference
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1023/
PDF https://www.aclweb.org/anthology/C18-1023
PWC https://paperswithcode.com/paper/embedding-wordnet-knowledge-for-textual
Repo
Framework

A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge

Title A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge
Authors Ali Emami, Adam Trischler, Kaheer Suleman, Jackie Chi Kit Cheung
Abstract We introduce an automatic system that performs well on two common-sense reasoning tasks, the Winograd Schema Challenge (WSC) and the Choice of Plausible Alternatives (COPA). Problem instances from these tasks require diverse, complex forms of inference and knowledge to solve. Our method uses a knowledge-hunting module to gather text from the web, which serves as evidence for candidate problem resolutions. Given an input problem, our system generates relevant queries to send to a search engine. It extracts and classifies knowledge from the returned results and weighs it to make a resolution. Our approach improves F1 performance on the WSC by 0.16 over the previous best and is competitive with the state-of-the-art on COPA, demonstrating its general applicability.
Tasks Common Sense Reasoning, Coreference Resolution, Information Retrieval
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-4004/
PDF https://www.aclweb.org/anthology/N18-4004
PWC https://paperswithcode.com/paper/a-generalized-knowledge-hunting-framework-for
Repo
Framework

KOI at SemEval-2018 Task 5: Building Knowledge Graph of Incidents

Title KOI at SemEval-2018 Task 5: Building Knowledge Graph of Incidents
Authors Paramita Mirza, Fariz Darari, Rahmad Mahendra
Abstract We present KOI (Knowledge of Incidents), a system that given news articles as input, builds a knowledge graph (KOI-KG) of incidental events. KOI-KG can then be used to efficiently answer questions such {``}How many killing incidents happened in 2017 that involve Sean?{''} The required steps in building the KG include: (i) document preprocessing involving word sense disambiguation, named-entity recognition, temporal expression recognition and normalization, and semantic role labeling; (ii) incidental event extraction and coreference resolution via document clustering; and (iii) KG construction and population. |
Tasks Coreference Resolution, Named Entity Recognition, Semantic Role Labeling, Word Sense Disambiguation
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1010/
PDF https://www.aclweb.org/anthology/S18-1010
PWC https://paperswithcode.com/paper/koi-at-semeval-2018-task-5-building-knowledge
Repo
Framework

WSNet: Learning Compact and Efficient Networks with Weight Sampling

Title WSNet: Learning Compact and Efficient Networks with Weight Sampling
Authors Xiaojie Jin, Yingzhen Yang, Ning Xu, Jianchao Yang, Jiashi Feng, Shuicheng Yan
Abstract We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks. Existing approaches conventionally learn full model parameters independently and then compress them via \emph{ad hoc} processing such as model pruning or filter factorization. Alternatively, WSNet proposes learning model parameters by sampling from a compact set of learnable parameters, which naturally enforces {parameter sharing} throughout the learning process. We demonstrate that such a novel weight sampling approach (and induced WSNet) promotes both weights and computation sharing favorably. By employing this method, we can more efficiently learn much smaller networks with competitive performance compared to baseline networks with equal numbers of convolution filters. Specifically, we consider learning compact and efficient 1D convolutional neural networks for audio classification. Extensive experiments on multiple audio classification datasets verify the effectiveness of WSNet. Combined with weight quantization, the resulted models are up to \textbf{180$\times$} smaller and theoretically up to \textbf{16$\times$} faster than the well-established baselines, without noticeable performance drop.
Tasks Audio Classification, Quantization
Published 2018-01-01
URL https://openreview.net/forum?id=H1I3M7Z0b
PDF https://openreview.net/pdf?id=H1I3M7Z0b
PWC https://paperswithcode.com/paper/wsnet-learning-compact-and-efficient-networks
Repo
Framework

KNU CI System at SemEval-2018 Task4: Character Identification by Solving Sequence-Labeling Problem

Title KNU CI System at SemEval-2018 Task4: Character Identification by Solving Sequence-Labeling Problem
Authors Cheoneum Park, Heejun Song, Changki Lee
Abstract Character identification is an entity-linking task that finds words referring to the same person among the nouns mentioned in a conversation and turns them into one entity. In this paper, we define a sequence-labeling problem to solve character identification, and propose an attention-based recurrent neural network (RNN) encoder{–}decoder model. The in-put document for character identification on multiparty dialogues consists of several conversations, which increase the length of the input sequence. The RNN encoder{–}decoder model suffers from poor performance when the length of the input sequence is long. To solve this problem, we propose applying position encoding and the self-matching network to the RNN encoder{–}decoder model. Our experimental results demonstrate that of the four models proposed, Model 2 showed an F1 score of 86.00{%} and a label accuracy of 85.10{%} at the scene-level.
Tasks Coreference Resolution, Entity Linking
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1107/
PDF https://www.aclweb.org/anthology/S18-1107
PWC https://paperswithcode.com/paper/knu-ci-system-at-semeval-2018-task4-character
Repo
Framework

Exploring the Influence of Spelling Errors on Lexical Variation Measures

Title Exploring the Influence of Spelling Errors on Lexical Variation Measures
Authors Ryo Nagata, Taisei Sato, Hiroya Takamura
Abstract This paper explores the influence of spelling errors on lexical variation measures. Lexical richness measures such as Type-Token Ration (TTR) and Yule{'}s K are often used for learner English analysis and assessment. When applied to learner English, however, they can be unreliable because of the spelling errors appearing in it. Namely, they are, directly or indirectly, based on the counts of distinct word types, and spelling errors undesirably increase the number of distinct words. This paper introduces and examines the hypothesis that lexical richness measures become unstable in learner English because of spelling errors. Specifically, it tests the hypothesis on English learner corpora of three groups (middle school, high school, and college students). To be precise, it estimates the difference in TTR and Yule{'}s K caused by spelling errors, by calculating their values before and after spelling errors are manually corrected. Furthermore, it examines the results theoretically and empirically to deepen the understanding of the influence of spelling errors on them.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1202/
PDF https://www.aclweb.org/anthology/C18-1202
PWC https://paperswithcode.com/paper/exploring-the-influence-of-spelling-errors-on
Repo
Framework

Tackling the Story Ending Biases in The Story Cloze Test

Title Tackling the Story Ending Biases in The Story Cloze Test
Authors Rishi Sharma, James Allen, Bakhsh, Omid eh, Nasrin Mostafazadeh
Abstract The Story Cloze Test (SCT) is a recent framework for evaluating story comprehension and script learning. There have been a variety of models tackling the SCT so far. Although the original goal behind the SCT was to require systems to perform deep language understanding and commonsense reasoning for successful narrative understanding, some recent models could perform significantly better than the initial baselines by leveraging human-authorship biases discovered in the SCT dataset. In order to shed some light on this issue, we have performed various data analysis and analyzed a variety of top performing models presented for this task. Given the statistics we have aggregated, we have designed a new crowdsourcing scheme that creates a new SCT dataset, which overcomes some of the biases. We benchmark a few models on the new dataset and show that the top-performing model on the original SCT dataset fails to keep up its performance. Our findings further signify the importance of benchmarking NLP systems on various evolving test sets.
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-2119/
PDF https://www.aclweb.org/anthology/P18-2119
PWC https://paperswithcode.com/paper/tackling-the-story-ending-biases-in-the-story
Repo
Framework

A Linked Coptic Dictionary Online

Title A Linked Coptic Dictionary Online
Authors Frank Feder, Maxim Kupreyev, Emma Manning, Caroline T. Schroeder, Amir Zeldes
Abstract We describe a new project publishing a freely available online dictionary for Coptic. The dictionary encompasses comprehensive cross-referencing mechanisms, including linking entries to an online scanned edition of Crum{'}s Coptic Dictionary, internal cross-references and etymological information, translated searchable definitions in English, French and German, and linked corpus data which provides frequencies and corpus look-up for headwords and multiword expressions. Headwords are available for linking in external projects using a REST API. We describe the challenges in encoding our dictionary using TEI XML and implementing linking mechanisms to construct a Web interface querying frequency information, which draw on NLP tools to recognize inflected forms in context. We evaluate our dictionary{'}s coverage using digital corpora of Coptic available online.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4502/
PDF https://www.aclweb.org/anthology/W18-4502
PWC https://paperswithcode.com/paper/a-linked-coptic-dictionary-online
Repo
Framework

Did you offend me? Classification of Offensive Tweets in Hinglish Language

Title Did you offend me? Classification of Offensive Tweets in Hinglish Language
Authors Puneet Mathur, Ramit Sawhney, Meghna Ayyar, Rajiv Shah
Abstract The use of code-switched languages (\textit{e.g.}, Hinglish, which is derived by the blending of Hindi with the English language) is getting much popular on Twitter due to their ease of communication in native languages. However, spelling variations and absence of grammar rules introduce ambiguity and make it difficult to understand the text automatically. This paper presents the Multi-Input Multi-Channel Transfer Learning based model (MIMCT) to detect offensive (hate speech or abusive) Hinglish tweets from the proposed Hinglish Offensive Tweet (HOT) dataset using transfer learning coupled with multiple feature inputs. Specifically, it takes multiple primary word embedding along with secondary extracted features as inputs to train a multi-channel CNN-LSTM architecture that has been pre-trained on English tweets through transfer learning. The proposed MIMCT model outperforms the baseline supervised classification models, transfer learning based CNN and LSTM models to establish itself as the state of the art in the unexplored domain of Hinglish offensive text classification.
Tasks Text Classification, Transfer Learning
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-5118/
PDF https://www.aclweb.org/anthology/W18-5118
PWC https://paperswithcode.com/paper/did-you-offend-me-classification-of-offensive
Repo
Framework

FEUP at SemEval-2018 Task 5: An Experimental Study of a Question Answering System

Title FEUP at SemEval-2018 Task 5: An Experimental Study of a Question Answering System
Authors Carla Abreu, Eug{'e}nio Oliveira
Abstract We present the approach developed at the Faculty of Engineering of the University of Porto to participate in SemEval-2018 Task 5: Counting Events and Participants within Highly Ambiguous Data covering a very long tail.The work described here presents the experimental system developed to extract entities from news articles for the sake of Question Answering. We propose a supervised learning approach to enable the recognition of two different types of entities: Locations and Participants. We also discuss the use of distance-based algorithms (using Levenshtein distance and Q-grams) for the detection of documents{'} closeness based on the entities extracted. For the experiments, we also used a multi-agent system that improved the performance.
Tasks Named Entity Recognition, Question Answering
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1109/
PDF https://www.aclweb.org/anthology/S18-1109
PWC https://paperswithcode.com/paper/feup-at-semeval-2018-task-5-an-experimental
Repo
Framework

Chahta Anumpa: A multimodal corpus of the Choctaw Language

Title Chahta Anumpa: A multimodal corpus of the Choctaw Language
Authors Jacqueline Brixey, Eli Pincus, Ron Artstein
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1532/
PDF https://www.aclweb.org/anthology/L18-1532
PWC https://paperswithcode.com/paper/chahta-anumpa-a-multimodal-corpus-of-the
Repo
Framework

Expanding Abbreviations in a Strongly Inflected Language: Are Morphosyntactic Tags Sufficient?

Title Expanding Abbreviations in a Strongly Inflected Language: Are Morphosyntactic Tags Sufficient?
Authors Piotr {.Z}elasko
Abstract
Tasks Language Modelling
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1295/
PDF https://www.aclweb.org/anthology/L18-1295
PWC https://paperswithcode.com/paper/expanding-abbreviations-in-a-strongly
Repo
Framework

Universal Dependencies Version 2 for Japanese

Title Universal Dependencies Version 2 for Japanese
Authors Masayuki Asahara, Hiroshi Kanayama, Takaaki Tanaka, Yusuke Miyao, Sumire Uematsu, Shinsuke Mori, Yuji Matsumoto, Mai Omura, Yugo Murawaki
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1287/
PDF https://www.aclweb.org/anthology/L18-1287
PWC https://paperswithcode.com/paper/universal-dependencies-version-2-for-japanese
Repo
Framework

An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence Assumption

Title An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence Assumption
Authors Xiyu Yu, Tongliang Liu, Mingming Gong, Kayhan Batmanghelich, Dacheng Tao
Abstract In this paper, we study the mixture proportion estimation (MPE) problem in a new setting: given samples from the mixture and the component distributions, we identify the proportions of the components in the mixture distribution. To address this problem, we make use of a linear independence assumption, i.e., the component distributions are independent from each other, which is much weaker than assumptions exploited in the previous MPE methods. Based on this assumption, we propose a method (1) that uniquely identifies the mixture proportions, (2) whose output provably converges to the optimal solution, and (3) that is computationally efficient. We show the superiority of the proposed method over the state-of-the-art methods in two applications including learning with label noise and semi-supervised learning on both synthetic and real-world datasets.
Tasks
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Yu_An_Efficient_and_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Yu_An_Efficient_and_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/an-efficient-and-provable-approach-for
Repo
Framework
comments powered by Disqus