October 15, 2019

1149 words 6 mins read

Paper Group NANR 156

Paper Group NANR 156

Neural Machine Translation of Logographic Language Using Sub-character Level Information. Aspect Based Sentiment Analysis into the Wild. Machine translation at Booking.com: what’s next?. A New Corpus to Support Text Mining for the Curation of Metabolites in the ChEBI Database. Accurate Text-Enhanced Knowledge Graph Representation Learning. STEVENDU …

Neural Machine Translation of Logographic Language Using Sub-character Level Information

Title Neural Machine Translation of Logographic Language Using Sub-character Level Information
Authors Longtu Zhang, Mamoru Komachi
Abstract Recent neural machine translation (NMT) systems have been greatly improved by encoder-decoder models with attention mechanisms and sub-word units. However, important differences between languages with logographic and alphabetic writing systems have long been overlooked. This study focuses on these differences and uses a simple approach to improve the performance of NMT systems utilizing decomposed sub-character level information for logographic languages. Our results indicate that our approach not only improves the translation capabilities of NMT systems between Chinese and English, but also further improves NMT systems between Chinese and Japanese, because it utilizes the shared information brought by similar sub-character units.
Tasks Machine Translation, Word Embeddings
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-6303/
PDF https://www.aclweb.org/anthology/W18-6303
PWC https://paperswithcode.com/paper/neural-machine-translation-of-logographic-1
Repo
Framework

Aspect Based Sentiment Analysis into the Wild

Title Aspect Based Sentiment Analysis into the Wild
Authors Caroline Brun, Vassilina Nikoulina
Abstract In this paper, we test state-of-the-art Aspect Based Sentiment Analysis (ABSA) systems trained on a widely used dataset on actual data. We created a new manually annotated dataset of user generated data from the same domain as the training dataset, but from other sources and analyse the differences between the new and the standard ABSA dataset. We then analyse the results in performance of different versions of the same system on both datasets. We also propose light adaptation methods to increase system robustness.
Tasks Aspect-Based Sentiment Analysis, Sentiment Analysis
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-6217/
PDF https://www.aclweb.org/anthology/W18-6217
PWC https://paperswithcode.com/paper/aspect-based-sentiment-analysis-into-the-wild
Repo
Framework

Machine translation at Booking.com: what’s next?

Title Machine translation at Booking.com: what’s next?
Authors Maxim Khalilov
Abstract
Tasks Automatic Post-Editing, Machine Translation
Published 2018-03-01
URL https://www.aclweb.org/anthology/W18-2104/
PDF https://www.aclweb.org/anthology/W18-2104
PWC https://paperswithcode.com/paper/machine-translation-at-bookingcom-whats-next
Repo
Framework

A New Corpus to Support Text Mining for the Curation of Metabolites in the ChEBI Database

Title A New Corpus to Support Text Mining for the Curation of Metabolites in the ChEBI Database
Authors Matthew Shardlow, Nhung Nguyen, Gareth Owen, Claire O{'}Donovan, Andrew Leach, John McNaught, Steve Turner, Sophia Ananiadou
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1042/
PDF https://www.aclweb.org/anthology/L18-1042
PWC https://paperswithcode.com/paper/a-new-corpus-to-support-text-mining-for-the
Repo
Framework

Accurate Text-Enhanced Knowledge Graph Representation Learning

Title Accurate Text-Enhanced Knowledge Graph Representation Learning
Authors Bo An, Bo Chen, Xianpei Han, Le Sun
Abstract Previous representation learning techniques for knowledge graph representation usually represent the same entity or relation in different triples with the same representation, without considering the ambiguity of relations and entities. To appropriately handle the semantic variety of entities/relations in distinct triples, we propose an accurate text-enhanced knowledge graph representation learning method, which can represent a relation/entity with different representations in different triples by exploiting additional textual information. Specifically, our method enhances representations by exploiting the entity descriptions and triple-specific relation mention. And a mutual attention mechanism between relation mention and entity description is proposed to learn more accurate textual representations for further improving knowledge graph representation. Experimental results show that our method achieves the state-of-the-art performance on both link prediction and triple classification tasks, and significantly outperforms previous text-enhanced knowledge representation models.
Tasks Graph Representation Learning, Knowledge Graphs, Link Prediction, Representation Learning
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1068/
PDF https://www.aclweb.org/anthology/N18-1068
PWC https://paperswithcode.com/paper/accurate-text-enhanced-knowledge-graph
Repo
Framework

STEVENDU2018’s system in VarDial 2018: Discriminating between Dutch and Flemish in Subtitles

Title STEVENDU2018’s system in VarDial 2018: Discriminating between Dutch and Flemish in Subtitles
Authors Steven Du, Yuan Yuan Wang
Abstract This paper introduces the submitted system for team STEVENDU2018 during VarDial 2018 Discriminating between Dutch and Flemish in Subtitles(DFS). Post evaluation analyses are also presented, the results obtained indicate that it is a challenging task to discriminate Dutch and Flemish.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-3926/
PDF https://www.aclweb.org/anthology/W18-3926
PWC https://paperswithcode.com/paper/stevendu2018s-system-in-vardial-2018
Repo
Framework

A Parser for LTAG and Frame Semantics

Title A Parser for LTAG and Frame Semantics
Authors David Arps, Simon Petitjean
Abstract
Tasks Semantic Parsing
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1351/
PDF https://www.aclweb.org/anthology/L18-1351
PWC https://paperswithcode.com/paper/a-parser-for-ltag-and-frame-semantics
Repo
Framework

A Flexible, Efficient and Accurate Framework for Community Question Answering Pipelines

Title A Flexible, Efficient and Accurate Framework for Community Question Answering Pipelines
Authors Salvatore Romeo, Giovanni Da San Martino, Alberto Barr{'o}n-Cede{~n}o, Aless Moschitti, ro
Abstract Although deep neural networks have been proving to be excellent tools to deliver state-of-the-art results, when data is scarce and the tackled tasks involve complex semantic inference, deep linguistic processing and traditional structure-based approaches, such as tree kernel methods, are an alternative solution. Community Question Answering is a research area that benefits from deep linguistic analysis to improve the experience of the community of forum users. In this paper, we present a UIMA framework to distribute the computation of cQA tasks over computer clusters such that traditional systems can scale to large datasets and deliver fast processing.
Tasks Community Question Answering, Question Answering
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-4023/
PDF https://www.aclweb.org/anthology/P18-4023
PWC https://paperswithcode.com/paper/a-flexible-efficient-and-accurate-framework
Repo
Framework

NLP Corpus Observatory – Looking for Constellations in Parallel Corpora to Improve Learners’ Collocational Skills

Title NLP Corpus Observatory – Looking for Constellations in Parallel Corpora to Improve Learners’ Collocational Skills
Authors Gerold Schneider, Johannes Gra{"e}n
Abstract
Tasks
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-7108/
PDF https://www.aclweb.org/anthology/W18-7108
PWC https://paperswithcode.com/paper/nlp-corpus-observatory-a-looking-for
Repo
Framework

ANCOR-AS: Enriching the ANCOR Corpus with Syntactic Annotations

Title ANCOR-AS: Enriching the ANCOR Corpus with Syntactic Annotations
Authors Lo{"\i}c Grobol, Isabelle Tellier, {'E}ric de la Clergerie, Marco Dinarelli, L, Fr{'e}d{'e}ric ragin
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1064/
PDF https://www.aclweb.org/anthology/L18-1064
PWC https://paperswithcode.com/paper/ancor-as-enriching-the-ancor-corpus-with
Repo
Framework

PhotoshopQuiA: A Corpus of Non-Factoid Questions and Answers for Why-Question Answering

Title PhotoshopQuiA: A Corpus of Non-Factoid Questions and Answers for Why-Question Answering
Authors Andrei Dulceanu, Thang Le Dinh, Walter Chang, Trung Bui, Doo Soon Kim, Manh Chien Vu, Seokhwan Kim
Abstract
Tasks Answer Selection, Community Question Answering, Question Answering
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1438/
PDF https://www.aclweb.org/anthology/L18-1438
PWC https://paperswithcode.com/paper/photoshopquia-a-corpus-of-non-factoid
Repo
Framework

ParCorFull: a Parallel Corpus Annotated with Full Coreference

Title ParCorFull: a Parallel Corpus Annotated with Full Coreference
Authors Ekaterina Lapshinova-Koltunski, Christian Hardmeier, Pauline Krielke
Abstract
Tasks Coreference Resolution, Machine Translation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1065/
PDF https://www.aclweb.org/anthology/L18-1065
PWC https://paperswithcode.com/paper/parcorfull-a-parallel-corpus-annotated-with
Repo
Framework

CPJD Corpus: Crowdsourced Parallel Speech Corpus of Japanese Dialects

Title CPJD Corpus: Crowdsourced Parallel Speech Corpus of Japanese Dialects
Authors Shinnosuke Takamichi, Hiroshi Saruwatari
Abstract
Tasks Machine Translation, Speech Recognition, Speech Synthesis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1067/
PDF https://www.aclweb.org/anthology/L18-1067
PWC https://paperswithcode.com/paper/cpjd-corpus-crowdsourced-parallel-speech
Repo
Framework

The LREC Workshops Map

Title The LREC Workshops Map
Authors Roberto Bartolini, Sara Goggi, Monica Monachini, Gabriella Pardelli
Abstract
Tasks Machine Translation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1088/
PDF https://www.aclweb.org/anthology/L18-1088
PWC https://paperswithcode.com/paper/the-lrec-workshops-map
Repo
Framework

Chinese Relation Classification using Long Short Term Memory Networks

Title Chinese Relation Classification using Long Short Term Memory Networks
Authors Linrui Zhang, Dan Moldovan
Abstract
Tasks Relation Classification, Relation Extraction
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1077/
PDF https://www.aclweb.org/anthology/L18-1077
PWC https://paperswithcode.com/paper/chinese-relation-classification-using-long
Repo
Framework
comments powered by Disqus