October 15, 2019

1982 words 10 mins read

Paper Group NANR 140

Paper Group NANR 140

Textual Entailment based Question Generation. One vs. Many QA Matching with both Word-level and Sentence-level Attention Network. The University of Texas System Submission for the Code-Switching Workshop Shared Task 2018. Reconstruction-based Pairwise Depth Dataset for Depth Image Enhancement Using CNN. Combining Quality Estimation and Automatic Po …

Textual Entailment based Question Generation

Title Textual Entailment based Question Generation
Authors Takaaki Matsumoto, Kimihiro Hasegawa, Yukari Yamakawa, Teruko Mitamura
Abstract
Tasks Dependency Parsing, Natural Language Inference, Question Generation, Reading Comprehension, Semantic Role Labeling, Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6704/
PDF https://www.aclweb.org/anthology/W18-6704
PWC https://paperswithcode.com/paper/textual-entailment-based-question-generation
Repo
Framework

One vs. Many QA Matching with both Word-level and Sentence-level Attention Network

Title One vs. Many QA Matching with both Word-level and Sentence-level Attention Network
Authors Lu Wang, Shoushan Li, Changlong Sun, Luo Si, Xiaozhong Liu, Min Zhang, Guodong Zhou
Abstract Question-Answer (QA) matching is a fundamental task in the Natural Language Processing community. In this paper, we first build a novel QA matching corpus with informal text which is collected from a product reviewing website. Then, we propose a novel QA matching approach, namely One vs. Many Matching, which aims to address the novel scenario where one question sentence often has an answer with multiple sentences. Furthermore, we improve our matching approach by employing both word-level and sentence-level attentions for solving the noisy problem in the informal text. Empirical studies demonstrate the effectiveness of the proposed approach to question-answer matching.
Tasks Question Answering, Reading Comprehension
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1215/
PDF https://www.aclweb.org/anthology/C18-1215
PWC https://paperswithcode.com/paper/one-vs-many-qa-matching-with-both-word-level
Repo
Framework

The University of Texas System Submission for the Code-Switching Workshop Shared Task 2018

Title The University of Texas System Submission for the Code-Switching Workshop Shared Task 2018
Authors Florian Janke, Tongrui Li, Eric Rinc{'o}n, Gualberto Guzm{'a}n, Barbara Bullock, Almeida Jacqueline Toribio
Abstract This paper describes the system for the Named Entity Recognition Shared Task of the Third Workshop on Computational Approaches to Linguistic Code-Switching (CALCS) submitted by the Bilingual Annotations Tasks (BATs) research group of the University of Texas. Our system uses several features to train a Conditional Random Field (CRF) model for classifying input words as Named Entities (NEs) using the Inside-Outside-Beginning (IOB) tagging scheme. We participated in the Modern Standard Arabic-Egyptian Arabic (MSA-EGY) and English-Spanish (ENG-SPA) tasks, achieving weighted average F-scores of 65.62 and 54.16 respectively. We also describe the performance of a deep neural network (NN) trained on a subset of the CRF features, which did not surpass CRF performance.
Tasks Named Entity Recognition
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-3216/
PDF https://www.aclweb.org/anthology/W18-3216
PWC https://paperswithcode.com/paper/the-university-of-texas-system-submission-for
Repo
Framework

Reconstruction-based Pairwise Depth Dataset for Depth Image Enhancement Using CNN

Title Reconstruction-based Pairwise Depth Dataset for Depth Image Enhancement Using CNN
Authors Junho Jeon, Seungyong Lee
Abstract Raw depth images captured by consumer depth cameras suffer from noisy and missing values. Despite the success of CNN-based image processing on color image restoration, similar approaches for depth enhancement have not been much addressed yet because of the lack of raw-clean pairwise dataset. In this paper, we propose a pairwise depth image dataset generation method using dense 3D surface reconstruction with a filtering method to remove low quality pairs. We also present a multi-scale Laplacian pyramid based neural network and structure preserving loss functions to progressively reduce the noise and holes from coarse to fine scales. Experimental results show that our network trained with our pairwise dataset can enhance the input depth images to become comparable with 3D reconstructions obtained from depth streams, and can accelerate the convergence of dense 3D reconstruction results.
Tasks 3D Reconstruction, Image Enhancement, Image Restoration
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Junho_Jeon_Reconstruction-based_Pairwise_Depth_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Junho_Jeon_Reconstruction-based_Pairwise_Depth_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/reconstruction-based-pairwise-depth-dataset
Repo
Framework

Combining Quality Estimation and Automatic Post-editing to Enhance Machine Translation output

Title Combining Quality Estimation and Automatic Post-editing to Enhance Machine Translation output
Authors Rajen Chatterjee, Matteo Negri, Marco Turchi, Fr{'e}d{'e}ric Blain, Lucia Specia
Abstract
Tasks Automatic Post-Editing, Machine Translation
Published 2018-03-01
URL https://www.aclweb.org/anthology/W18-1804/
PDF https://www.aclweb.org/anthology/W18-1804
PWC https://paperswithcode.com/paper/combining-quality-estimation-and-automatic
Repo
Framework

Context and Copying in Neural Machine Translation

Title Context and Copying in Neural Machine Translation
Authors Rebecca Knowles, Philipp Koehn
Abstract Neural machine translation systems with subword vocabularies are capable of translating or copying unknown words. In this work, we show that they learn to copy words based on both the context in which the words appear as well as features of the words themselves. In contexts that are particularly copy-prone, they even copy words that they have already learned they should translate. We examine the influence of context and subword features on this and other types of copying behavior.
Tasks Machine Translation
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1339/
PDF https://www.aclweb.org/anthology/D18-1339
PWC https://paperswithcode.com/paper/context-and-copying-in-neural-machine
Repo
Framework

An Argument-Annotated Corpus of Scientific Publications

Title An Argument-Annotated Corpus of Scientific Publications
Authors Anne Lauscher, Goran Glava{\v{s}}, Simone Paolo Ponzetto
Abstract Argumentation is an essential feature of scientific language. We present an annotation study resulting in a corpus of scientific publications annotated with argumentative components and relations. The argumentative annotations have been added to the existing Dr. Inventor Corpus, already annotated for four other rhetorical aspects. We analyze the annotated argumentative structures and investigate the relations between argumentation and other rhetorical aspects of scientific writing, such as discourse roles and citation contexts.
Tasks Argument Mining
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5206/
PDF https://www.aclweb.org/anthology/W18-5206
PWC https://paperswithcode.com/paper/an-argument-annotated-corpus-of-scientific
Repo
Framework

Generic refinement of expressive grammar formalisms with an application to discontinuous constituent parsing

Title Generic refinement of expressive grammar formalisms with an application to discontinuous constituent parsing
Authors Kilian Gebhardt
Abstract We formulate a generalization of Petrov et al. (2006){'}s split/merge algorithm for interpreted regular tree grammars (Koller and Kuhlmann, 2011), which capture a large class of grammar formalisms. We evaluate its effectiveness empirically on the task of discontinuous constituent parsing with two mildly context-sensitive grammar formalisms: linear context-free rewriting systems (Vijay-Shanker et al., 1987) as well as hybrid grammars (Nederhof and Vogler, 2014).
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1258/
PDF https://www.aclweb.org/anthology/C18-1258
PWC https://paperswithcode.com/paper/generic-refinement-of-expressive-grammar
Repo
Framework

If you’ve seen some, you’ve seen them all: Identifying variants of multiword expressions

Title If you’ve seen some, you’ve seen them all: Identifying variants of multiword expressions
Authors Caroline Pasquer, Agata Savary, Carlos Ramisch, Jean-Yves Antoine
Abstract Multiword expressions, especially verbal ones (VMWEs), show idiosyncratic variability, which is challenging for NLP applications, hence the need for VMWE identification. We focus on the task of variant identification, i.e. identifying variants of previously seen VMWEs, whatever their surface form. We model the problem as a classification task. Syntactic subtrees with previously seen combinations of lemmas are first extracted, and then classified on the basis of features relevant to morpho-syntactic variation of VMWEs. Feature values are both absolute, i.e. hold for a particular VMWE candidate, and relative, i.e. based on comparing a candidate with previously seen VMWEs. This approach outperforms a baseline by 4 percent points of F-measure on a French corpus.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1219/
PDF https://www.aclweb.org/anthology/C18-1219
PWC https://paperswithcode.com/paper/if-youve-seen-some-youve-seen-them-all
Repo
Framework

MindLab Neural Network Approach at BioASQ 6B

Title MindLab Neural Network Approach at BioASQ 6B
Authors Andr{'e}s Rosso-Mateus, Fabio A. Gonz{'a}lez, Manuel Montes-y-G{'o}mez
Abstract Biomedical Question Answering is concerned with the development of methods and systems that automatically find answers to natural language posed questions. In this work, we describe the system used in the BioASQ Challenge task 6b for document retrieval and snippet retrieval (with particular emphasis in this subtask). The proposed model makes use of semantic similarity patterns that are evaluated and measured by a convolutional neural network architecture. Subsequently, the snippet ranking performance is improved with a pseudo-relevance feedback approach in a later step. Based on the preliminary results, we reached the second position in snippet retrieval sub-task.
Tasks Information Retrieval, Question Answering, Semantic Similarity, Semantic Textual Similarity
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5305/
PDF https://www.aclweb.org/anthology/W18-5305
PWC https://paperswithcode.com/paper/mindlab-neural-network-approach-at-bioasq-6b
Repo
Framework

Code-Switched Named Entity Recognition with Embedding Attention

Title Code-Switched Named Entity Recognition with Embedding Attention
Authors Changhan Wang, Kyunghyun Cho, Douwe Kiela
Abstract We describe our work for the CALCS 2018 shared task on named entity recognition on code-switched data. Our system ranked first place for MS Arabic-Egyptian named entity recognition and third place for English-Spanish.
Tasks Language Identification, Named Entity Recognition, Word Embeddings
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-3221/
PDF https://www.aclweb.org/anthology/W18-3221
PWC https://paperswithcode.com/paper/code-switched-named-entity-recognition-with
Repo
Framework

GHH at SemEval-2018 Task 10: Discovering Discriminative Attributes in Distributional Semantics

Title GHH at SemEval-2018 Task 10: Discovering Discriminative Attributes in Distributional Semantics
Authors Mohammed Attia, Younes Samih, Manaal Faruqui, Wolfgang Maier
Abstract This paper describes our system submission to the SemEval 2018 Task 10 on Capturing Discriminative Attributes. Given two concepts and an attribute, the task is to determine whether the attribute is semantically related to one concept and not the other. In this work we assume that discriminative attributes can be detected by discovering the association (or lack of association) between a pair of words. The hypothesis we test in this contribution is whether the semantic difference between two pairs of concepts can be treated in terms of measuring the distance between words in a vector space, or can simply be obtained as a by-product of word co-occurrence counts.
Tasks Word Embeddings
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1155/
PDF https://www.aclweb.org/anthology/S18-1155
PWC https://paperswithcode.com/paper/ghh-at-semeval-2018-task-10-discovering
Repo
Framework

Platforms for Non-speakers Annotating Names in Any Language

Title Platforms for Non-speakers Annotating Names in Any Language
Authors Ying Lin, Cash Costello, Boliang Zhang, Di Lu, Heng Ji, James Mayfield, Paul McNamee
Abstract We demonstrate two annotation platforms that allow an English speaker to annotate names for any language without knowing the language. These platforms provided high-quality {'}{`}silver standard{''} annotations for low-resource language name taggers (Zhang et al., 2017) that achieved state-of-the-art performance on two surprise languages (Oromo and Tigrinya) at LoreHLT20171 and ten languages at TAC-KBP EDL2017 (Ji et al., 2017). We discuss strengths and limitations and compare other methods of creating silver- and gold-standard annotations using native speakers. We will make our tools publicly available for research use. |
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-4001/
PDF https://www.aclweb.org/anthology/P18-4001
PWC https://paperswithcode.com/paper/platforms-for-non-speakers-annotating-names
Repo
Framework

Coded Illumination and Imaging for Fluorescence Based Classification

Title Coded Illumination and Imaging for Fluorescence Based Classification
Authors Yuta Asano, Misaki Meguro, Chao Wang, Antony Lam, Yinqiang Zheng, Takahiro Okabe, Imari Sato
Abstract The quick detection of specific substances in objects such as produce items via non-destructive visual cues is vital to ensuring the quality and safety of consumer products. At the same time, it is well-known that the fluorescence excitation-emission characteristics of many organic objects can serve as a kind of ``fingerprint’’ for detecting the presence of specific substances in classification tasks such as determining if something is safe to consume. However, conventional capture of the fluorescence excitation-emission matrix can take on the order of minutes and can only be done for point measurements. In this paper, we propose a coded illumination approach whereby light spectra are learned such that key visual fluorescent features can be easily seen for material classification. We show that under a single coded illuminant, we can capture one RGB image and perform pixel-level classifications of materials at high accuracy. This is demonstrated through effective classification of different types of honey and alcohol using real images. |
Tasks Material Classification
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Yuta_Asano_Coded_Illumination_and_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Yuta_Asano_Coded_Illumination_and_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/coded-illumination-and-imaging-for
Repo
Framework

Improving Event Coreference Resolution by Modeling Correlations between Event Coreference Chains and Document Topic Structures

Title Improving Event Coreference Resolution by Modeling Correlations between Event Coreference Chains and Document Topic Structures
Authors Prafulla Kumar Choubey, Ruihong Huang
Abstract This paper proposes a novel approach for event coreference resolution that models correlations between event coreference chains and document topical structures through an Integer Linear Programming formulation. We explicitly model correlations between the main event chains of a document with topic transition sentences, inter-coreference chain correlations, event mention distributional characteristics and sub-event structure, and use them with scores obtained from a local coreference relation classifier for jointly resolving multiple event chains in a document. Our experiments across KBP 2016 and 2017 datasets suggest that each of the structures contribute to improving event coreference resolution performance.
Tasks Coreference Resolution, Question Answering
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-1045/
PDF https://www.aclweb.org/anthology/P18-1045
PWC https://paperswithcode.com/paper/improving-event-coreference-resolution-by
Repo
Framework
comments powered by Disqus