May 5, 2019

1317 words 7 mins read

Paper Group NANR 141

VCU at Semeval-2016 Task 14: Evaluating definitional-based similarity measure for semantic taxonomy enrichment. Crowdsourcing a Multi-lingual Speech Corpus: Recording, Transcription and Annotation of the CrowdIS Corpora. Semi-supervised Convolutional Networks for Translation Adaptation with Tiny Amount of In-domain Data. Conversion from Paninian Ka …

VCU at Semeval-2016 Task 14: Evaluating definitional-based similarity measure for semantic taxonomy enrichment


Title	VCU at Semeval-2016 Task 14: Evaluating definitional-based similarity measure for semantic taxonomy enrichment
Authors	Bridget McInnes
Abstract
Tasks	Information Retrieval, Semantic Textual Similarity, Word Sense Disambiguation
Published	2016-06-01
URL	https://www.aclweb.org/anthology/S16-1212/
PDF	https://www.aclweb.org/anthology/S16-1212
PWC	https://paperswithcode.com/paper/vcu-at-semeval-2016-task-14-evaluating
Repo
Framework

Crowdsourcing a Multi-lingual Speech Corpus: Recording, Transcription and Annotation of the CrowdIS Corpora


Title	Crowdsourcing a Multi-lingual Speech Corpus: Recording, Transcription and Annotation of the CrowdIS Corpora
Authors	Andrew Caines, Christian Bentz, Calbert Graham, Tim Polzehl, Paula Buttery
Abstract	We announce the release of the CROWDED CORPUS: a pair of speech corpora collected via crowdsourcing, containing a native speaker corpus of English (CROWDED{_}ENGLISH), and a corpus of German/English bilinguals (CROWDED{_}BILINGUAL). Release 1 of the CROWDED CORPUS contains 1000 recordings amounting to 33,400 tokens collected from 80 speakers and is freely available to other researchers. We recruited participants via the Crowdee application for Android. Recruits were prompted to respond to business-topic questions of the type found in language learning oral tests. We then used the CrowdFlower web application to pass these recordings to crowdworkers for transcription and annotation of errors and sentence boundaries. Finally, the sentences were tagged and parsed using standard natural language processing tools. We propose that crowdsourcing is a valid and economical method for corpus collection, and discuss the advantages and disadvantages of this approach.
Tasks
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1340/
PDF	https://www.aclweb.org/anthology/L16-1340
PWC	https://paperswithcode.com/paper/crowdsourcing-a-multi-lingual-speech-corpus
Repo
Framework

Semi-supervised Convolutional Networks for Translation Adaptation with Tiny Amount of In-domain Data


Title	Semi-supervised Convolutional Networks for Translation Adaptation with Tiny Amount of In-domain Data
Authors	Boxing Chen, Fei Huang
Abstract
Tasks	Domain Adaptation, Language Modelling, Machine Translation
Published	2016-08-01
URL	https://www.aclweb.org/anthology/K16-1031/
PDF	https://www.aclweb.org/anthology/K16-1031
PWC	https://paperswithcode.com/paper/semi-supervised-convolutional-networks-for
Repo
Framework

Conversion from Paninian Karakas to Universal Dependencies for Hindi Dependency Treebank


Title	Conversion from Paninian Karakas to Universal Dependencies for Hindi Dependency Treebank
Authors	T, Juhi on, Himani Chaudhry, Riyaz Ahmad Bhat, Dipti Sharma
Abstract
Tasks	Dependency Parsing
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-1716/
PDF	https://www.aclweb.org/anthology/W16-1716
PWC	https://paperswithcode.com/paper/conversion-from-paninian-karakas-to-universal
Repo
Framework

Adaptive Importance Sampling from Finite State Automata


Title	Adaptive Importance Sampling from Finite State Automata
Authors	Christoph Teichmann, Kasimir Wansing, Alex Koller, er
Abstract
Tasks
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2402/
PDF	https://www.aclweb.org/anthology/W16-2402
PWC	https://paperswithcode.com/paper/adaptive-importance-sampling-from-finite
Repo
Framework

Proceedings of the 11th Workshop on Innovative Use of NLP for Building Educational Applications


Title	Proceedings of the 11th Workshop on Innovative Use of NLP for Building Educational Applications
Authors
Abstract
Tasks
Published	2016-06-01
URL	https://www.aclweb.org/anthology/W16-0500/
PDF	https://www.aclweb.org/anthology/W16-0500
PWC	https://paperswithcode.com/paper/proceedings-of-the-11th-workshop-on
Repo
Framework

Code-Switching Ubique Est - Language Identification and Part-of-Speech Tagging for Historical Mixed Text


Title	Code-Switching Ubique Est - Language Identification and Part-of-Speech Tagging for Historical Mixed Text
Authors	Sarah Schulz, Mareike Keller
Abstract
Tasks	Language Identification, Part-Of-Speech Tagging
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2105/
PDF	https://www.aclweb.org/anthology/W16-2105
PWC	https://paperswithcode.com/paper/code-switching-ubique-est-language
Repo
Framework

Towards Building a SentiWordNet for Tamil


Title	Towards Building a SentiWordNet for Tamil
Authors	Abishek Kannan, Gaurav Mohanty, Radhika Mamidi
Abstract
Tasks	Sentiment Analysis
Published	2016-12-01
URL	https://www.aclweb.org/anthology/W16-6305/
PDF	https://www.aclweb.org/anthology/W16-6305
PWC	https://paperswithcode.com/paper/towards-building-a-sentiwordnet-for-tamil
Repo
Framework

Robust Co-occurrence Quantification for Lexical Distributional Semantics


Title	Robust Co-occurrence Quantification for Lexical Distributional Semantics
Authors	Dmitrijs Milajevs, Mehrnoosh Sadrzadeh, Matthew Purver
Abstract
Tasks	Dimensionality Reduction
Published	2016-08-01
URL	https://www.aclweb.org/anthology/P16-3009/
PDF	https://www.aclweb.org/anthology/P16-3009
PWC	https://paperswithcode.com/paper/robust-co-occurrence-quantification-for
Repo
Framework

Recurrent Neural Network with Word Embedding for Complaint Classification


Title	Recurrent Neural Network with Word Embedding for Complaint Classification
Authors	Panuwat Assawinjaipetch, Kiyoaki Shirai, Virach Sornlertlamvanich, Sanparith Marukata
Abstract	Complaint classification aims at using information to deliver greater insights to enhance user experience after purchasing the products or services. Categorized information can help us quickly collect emerging problems in order to provide a support needed. Indeed, the response to the complaint without the delay will grant users highest satisfaction. In this paper, we aim to deliver a novel approach which can clarify the complaints precisely with the aim to classify each complaint into nine predefined classes i.e. acces-sibility, company brand, competitors, facilities, process, product feature, staff quality, timing respec-tively and others. Given the idea that one word usually conveys ambiguity and it has to be interpreted by its context, the word embedding technique is used to provide word features while applying deep learning techniques for classifying a type of complaints. The dataset we use contains 8,439 complaints of one company.
Tasks	Language Modelling, Named Entity Recognition, Relation Extraction, Sentiment Analysis, Speech Recognition, Text Classification
Published	2016-12-01
URL	https://www.aclweb.org/anthology/W16-5205/
PDF	https://www.aclweb.org/anthology/W16-5205
PWC	https://paperswithcode.com/paper/recurrent-neural-network-with-word-embedding
Repo
Framework

LAPPS/Galaxy: Current State and Next Steps


Title	LAPPS/Galaxy: Current State and Next Steps
Authors	Nancy Ide, Keith Suderman, Eric Nyberg, James Pustejovsky, Marc Verhagen
Abstract	The US National Science Foundation (NSF) SI2-funded LAPPS/Galaxy project has developed an open-source platform for enabling complex analyses while hiding complexities associated with underlying infrastructure, that can be accessed through a web interface, deployed on any Unix system, or run from the cloud. It provides sophisticated tool integration and history capabilities, a workflow system for building automated multi-step analyses, state-of-the-art evaluation capabilities, and facilities for sharing and publishing analyses. This paper describes the current facilities available in LAPPS/Galaxy and outlines the project{'}s ongoing activities to enhance the framework.
Tasks
Published	2016-12-01
URL	https://www.aclweb.org/anthology/W16-5202/
PDF	https://www.aclweb.org/anthology/W16-5202
PWC	https://paperswithcode.com/paper/lappsgalaxy-current-state-and-next-steps
Repo
Framework

Very quaffable and great fun: Applying NLP to wine reviews


Title	Very quaffable and great fun: Applying NLP to wine reviews
Authors	Iris Hendrickx, Els Lefever, Ilja Croijmans, Asifa Majid, Antal van den Bosch
Abstract
Tasks
Published	2016-08-01
URL	https://www.aclweb.org/anthology/P16-2050/
PDF	https://www.aclweb.org/anthology/P16-2050
PWC	https://paperswithcode.com/paper/very-quaffable-and-great-fun-applying-nlp-to
Repo
Framework

Particle Swarm Optimization Submission for WMT16 Tuning Task


Title	Particle Swarm Optimization Submission for WMT16 Tuning Task
Authors	Viktor Kocur, Ond{\v{r}}ej Bojar
Abstract
Tasks	Machine Translation
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2344/
PDF	https://www.aclweb.org/anthology/W16-2344
PWC	https://paperswithcode.com/paper/particle-swarm-optimization-submission-for
Repo
Framework

Bilingual Autoencoders with Global Descriptors for Modeling Parallel Sentences


Title	Bilingual Autoencoders with Global Descriptors for Modeling Parallel Sentences
Authors	Biao Zhang, Deyi Xiong, Jinsong Su, Hong Duan, Min Zhang
Abstract	Parallel sentence representations are important for bilingual and cross-lingual tasks in natural language processing. In this paper, we explore a bilingual autoencoder approach to model parallel sentences. We extract sentence-level global descriptors (e.g. min, max) from word embeddings, and construct two monolingual autoencoders over these descriptors on the source and target language. In order to tightly connect the two autoencoders with bilingual correspondences, we force them to share the same decoding parameters and minimize a corpus-level semantic distance between the two languages. Being optimized towards a joint objective function of reconstruction and semantic errors, our bilingual antoencoder is able to learn continuous-valued latent representations for parallel sentences. Experiments on both intrinsic and extrinsic evaluations on statistical machine translation tasks show that our autoencoder achieves substantial improvements over the baselines.
Tasks	Information Retrieval, Machine Translation, Word Embeddings
Published	2016-12-01
URL	https://www.aclweb.org/anthology/C16-1240/
PDF	https://www.aclweb.org/anthology/C16-1240
PWC	https://paperswithcode.com/paper/bilingual-autoencoders-with-global
Repo
Framework

Asynchronous Parallel Learning for Neural Networks and Structured Models with Dense Features


Title	Asynchronous Parallel Learning for Neural Networks and Structured Models with Dense Features
Authors	Xu Sun
Abstract	Existing asynchronous parallel learning methods are only for the sparse feature models, and they face new challenges for the dense feature models like neural networks (e.g., LSTM, RNN). The problem for dense features is that asynchronous parallel learning brings gradient errors derived from overwrite actions. We show that gradient errors are very common and inevitable. Nevertheless, our theoretical analysis shows that the learning process with gradient errors can still be convergent towards the optimum of objective functions for many practical applications. Thus, we propose a simple method \textit{AsynGrad} for asynchronous parallel learning with gradient error. Base on various dense feature models (LSTM, dense-CRF) and various NLP tasks, experiments show that \textit{AsynGrad} achieves substantial improvement on training speed, and without any loss on accuracy.
Tasks	Low-Rank Matrix Completion, Matrix Completion
Published	2016-12-01
URL	https://www.aclweb.org/anthology/C16-1019/
PDF	https://www.aclweb.org/anthology/C16-1019
PWC	https://paperswithcode.com/paper/asynchronous-parallel-learning-for-neural
Repo
Framework