May 5, 2019

1441 words 7 mins read

Paper Group NANR 115

UWaterloo at SemEval-2016 Task 5: Minimally Supervised Approaches to Aspect-Based Sentiment Analysis. Mining Parallel Corpora from Sina Weibo and Twitter. Automatic Anomaly Detection for Dysarthria across Two Speech Styles: Read vs Spontaneous Speech. Statistical Machine Translation between Related Languages. Collaborative Development of a Rule-Bas …

UWaterloo at SemEval-2016 Task 5: Minimally Supervised Approaches to Aspect-Based Sentiment Analysis


Title	UWaterloo at SemEval-2016 Task 5: Minimally Supervised Approaches to Aspect-Based Sentiment Analysis
Authors	Olga Vechtomova, Anni He
Abstract
Tasks	Aspect-Based Sentiment Analysis, Sentiment Analysis
Published	2016-06-01
URL	https://www.aclweb.org/anthology/S16-1060/
PDF	https://www.aclweb.org/anthology/S16-1060
PWC	https://paperswithcode.com/paper/uwaterloo-at-semeval-2016-task-5-minimally
Repo
Framework

Mining Parallel Corpora from Sina Weibo and Twitter


Title	Mining Parallel Corpora from Sina Weibo and Twitter
Authors	Wang Ling, Lu{'\i}s Marujo, Chris Dyer, Alan W. Black, Isabel Trancoso
Abstract
Tasks
Published	2016-06-01
URL	https://www.aclweb.org/anthology/J16-2005/
PDF	https://www.aclweb.org/anthology/J16-2005
PWC	https://paperswithcode.com/paper/mining-parallel-corpora-from-sina-weibo-and
Repo
Framework

Automatic Anomaly Detection for Dysarthria across Two Speech Styles: Read vs Spontaneous Speech


Title	Automatic Anomaly Detection for Dysarthria across Two Speech Styles: Read vs Spontaneous Speech
Authors	Imed Laaridh, Corinne Fredouille, Christine Meunier
Abstract	Perceptive evaluation of speech disorders is still the standard method in clinical practice for the diagnosing and the following of the condition progression of patients. Such methods include different tasks such as read speech, spontaneous speech, isolated words, sustained vowels, etc. In this context, automatic speech processing tools have proven pertinence in speech quality evaluation and assistive technology-based applications. Though, a very few studies have investigated the use of automatic tools on spontaneous speech. This paper investigates the behavior of an automatic phone-based anomaly detection system when applied on read and spontaneous French dysarthric speech. The behavior of the automatic tool reveals interesting inter-pathology differences across speech styles.
Tasks	Anomaly Detection
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1316/
PDF	https://www.aclweb.org/anthology/L16-1316
PWC	https://paperswithcode.com/paper/automatic-anomaly-detection-for-dysarthria
Repo
Framework


Title	Statistical Machine Translation between Related Languages
Authors	Pushpak Bhattacharyya, Mitesh M. Khapra, Anoop Kunchukuttan
Abstract
Tasks	Machine Translation
Published	2016-06-01
URL	https://www.aclweb.org/anthology/N16-4006/
PDF	https://www.aclweb.org/anthology/N16-4006
PWC	https://paperswithcode.com/paper/statistical-machine-translation-between
Repo
Framework

Collaborative Development of a Rule-Based Machine Translator between Croatian and Serbian


Title	Collaborative Development of a Rule-Based Machine Translator between Croatian and Serbian
Authors	Filip Klubi{\v{c}}ka, Gema Ram{'\i}rez-S{'a}nchez, Nikola Ljube{\v{s}}i{'c}
Abstract
Tasks	Machine Translation
Published	2016-01-01
URL	https://www.aclweb.org/anthology/W16-3422/
PDF	https://www.aclweb.org/anthology/W16-3422
PWC	https://paperswithcode.com/paper/collaborative-development-of-a-rule-based
Repo
Framework

A Word Embedding Approach to Identifying Verb-Noun Idiomatic Combinations


Title	A Word Embedding Approach to Identifying Verb-Noun Idiomatic Combinations
Authors	Waseem Gharbieh, Virendra Bhavsar, Paul Cook
Abstract
Tasks	Machine Translation, Word Embeddings, Word Sense Disambiguation
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-1817/
PDF	https://www.aclweb.org/anthology/W16-1817
PWC	https://paperswithcode.com/paper/a-word-embedding-approach-to-identifying-verb
Repo
Framework

Simplification of Example Sentences for Learners of Japanese Functional Expressions


Title	Simplification of Example Sentences for Learners of Japanese Functional Expressions
Authors	Jun Liu, Yuji Matsumoto
Abstract	Learning functional expressions is one of the difficulties for language learners, since functional expressions tend to have multiple meanings and complicated usages in various situations. In this paper, we report an experiment of simplifying example sentences of Japanese functional expressions especially for Chinese-speaking learners. For this purpose, we developed {`}Japanese Functional Expressions List{''} and {`}Simple Japanese Replacement List{''}. To evaluate the method, we conduct a small-scale experiment with Chinese-speaking learners on the effectiveness of the simplified example sentences. The experimental results indicate that simplified sentences are helpful in learning Japanese functional expressions.
Tasks
Published	2016-12-01
URL	https://www.aclweb.org/anthology/W16-4901/
PDF	https://www.aclweb.org/anthology/W16-4901
PWC	https://paperswithcode.com/paper/simplification-of-example-sentences-for
Repo
Framework

Large-Scale Acquisition of Commonsense Knowledge via a Quiz Game on a Dialogue System


Title	Large-Scale Acquisition of Commonsense Knowledge via a Quiz Game on a Dialogue System
Authors	Naoki Otani, Daisuke Kawahara, Sadao Kurohashi, Nobuhiro Kaji, Manabu Sassano
Abstract	Commonsense knowledge is essential for fully understanding language in many situations. We acquire large-scale commonsense knowledge from humans using a game with a purpose (GWAP) developed on a smartphone spoken dialogue system. We transform the manual knowledge acquisition process into an enjoyable quiz game and have collected over 150,000 unique commonsense facts by gathering the data of more than 70,000 players over eight months. In this paper, we present a simple method for maintaining the quality of acquired knowledge and an empirical analysis of the knowledge acquisition process. To the best of our knowledge, this is the first work to collect large-scale knowledge via a GWAP on a widely-used spoken dialogue system.
Tasks	Common Sense Reasoning, Question Answering
Published	2016-12-01
URL	https://www.aclweb.org/anthology/W16-4402/
PDF	https://www.aclweb.org/anthology/W16-4402
PWC	https://paperswithcode.com/paper/large-scale-acquisition-of-commonsense
Repo
Framework

Italian VerbNet: A Construction-based Approach to Italian Verb Classification


Title	Italian VerbNet: A Construction-based Approach to Italian Verb Classification
Authors	Lucia Busso, Aless Lenci, ro
Abstract	This paper proposes a new method for Italian verb classification -and a preliminary example of resulting classes- inspired by Levin (1993) and VerbNet (Kipper-Schuler, 2005), yet partially independent from these resources; we achieved such a result by integrating Levin and VerbNet{'}s models of classification with other theoretic frameworks and resources. The classification is rooted in the constructionist framework (Goldberg, 1995; 2006) and is distribution-based. It is also semantically characterized by a link to FrameNet{'}ssemanticframesto represent the event expressed by a class. However, the new Italian classes maintain the hierarchic {``}tree{''} structure and monotonic nature of VerbNet{'}s classes, and, where possible, the original names (e.g.: Verbs of Killing, Verbs of Putting, etc.). We therefore propose here a taxonomy compatible with VerbNet but at the same time adapted to Italian syntax and semantics. It also addresses a number of problems intrinsic to the original classifications, such as the role of argument alternations, here regarded simply as epiphenomena, consistently with the constructionist approach. \|
Tasks
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1419/
PDF	https://www.aclweb.org/anthology/L16-1419
PWC	https://paperswithcode.com/paper/italian-verbnet-a-construction-based-approach
Repo
Framework

Product Review Summarization by Exploiting Phrase Properties


Title	Product Review Summarization by Exploiting Phrase Properties
Authors	Naitong Yu, Minlie Huang, Yuanyuan Shi, Xiaoyan Zhu
Abstract	We propose a phrase-based approach for generating product review summaries. The main idea of our method is to leverage phrase properties to choose a subset of optimal phrases for generating the final summary. Specifically, we exploit two phrase properties, popularity and specificity. Popularity describes how popular the phrase is in the original reviews. Specificity describes how descriptive a phrase is in comparison to generic comments. We formalize the phrase selection procedure as an optimization problem and solve it using integer linear programming (ILP). An aspect-based bigram language model is used for generating the final summary with the selected phrases. Experiments show that our summarizer outperforms the other baselines.
Tasks	Abstractive Text Summarization, Language Modelling
Published	2016-12-01
URL	https://www.aclweb.org/anthology/C16-1106/
PDF	https://www.aclweb.org/anthology/C16-1106
PWC	https://paperswithcode.com/paper/product-review-summarization-by-exploiting
Repo
Framework

A Recurrent Neural Networks Approach for Estimating the Quality of Machine Translation Output


Title	A Recurrent Neural Networks Approach for Estimating the Quality of Machine Translation Output
Authors	Hyun Kim, Jong-Hyeok Lee
Abstract
Tasks	Feature Selection, Machine Translation
Published	2016-06-01
URL	https://www.aclweb.org/anthology/N16-1059/
PDF	https://www.aclweb.org/anthology/N16-1059
PWC	https://paperswithcode.com/paper/a-recurrent-neural-networks-approach-for
Repo
Framework

On Mixtures of Markov Chains


Title	On Mixtures of Markov Chains
Authors	Rishi Gupta, Ravi Kumar, Sergei Vassilvitskii
Abstract	We study the problem of reconstructing a mixture of Markov chains from the trajectories generated by random walks through the state space. Under mild non-degeneracy conditions, we show that we can uniquely reconstruct the underlying chains by only considering trajectories of length three, which represent triples of states. Our algorithm is spectral in nature, and is easy to implement.
Tasks
Published	2016-12-01
URL	http://papers.nips.cc/paper/6078-on-mixtures-of-markov-chains
PDF	http://papers.nips.cc/paper/6078-on-mixtures-of-markov-chains.pdf
PWC	https://paperswithcode.com/paper/on-mixtures-of-markov-chains
Repo
Framework

NUIG-UNLP at SemEval-2016 Task 1: Soft Alignment and Deep Learning for Semantic Textual Similarity


Title	NUIG-UNLP at SemEval-2016 Task 1: Soft Alignment and Deep Learning for Semantic Textual Similarity
Authors	John Philip McCrae, Kartik Asooja, Nitish Aggarwal, Paul Buitelaar
Abstract
Tasks	Machine Translation, Semantic Textual Similarity, Word Embeddings
Published	2016-06-01
URL	https://www.aclweb.org/anthology/S16-1110/
PDF	https://www.aclweb.org/anthology/S16-1110
PWC	https://paperswithcode.com/paper/nuig-unlp-at-semeval-2016-task-1-soft
Repo
Framework

Natural Language Communication with Robots


Title	Natural Language Communication with Robots
Authors	Yonatan Bisk, Deniz Yuret, Daniel Marcu
Abstract
Tasks	Machine Translation
Published	2016-06-01
URL	https://www.aclweb.org/anthology/N16-1089/
PDF	https://www.aclweb.org/anthology/N16-1089
PWC	https://paperswithcode.com/paper/natural-language-communication-with-robots
Repo
Framework

Two Architectures for Parallel Processing of Huge Amounts of Text


Title	Two Architectures for Parallel Processing of Huge Amounts of Text
Authors	Mathijs Kattenberg, Zuhaitz Beloki, Aitor Soroa, Xabier Artola, Antske Fokkens, Paul Huygen, Kees Verstoep
Abstract	This paper presents two alternative NLP architectures to analyze massive amounts of documents, using parallel processing. The two architectures focus on different processing scenarios, namely batch-processing and streaming processing. The batch-processing scenario aims at optimizing the overall throughput of the system, i.e., minimizing the overall time spent on processing all documents. The streaming architecture aims to minimize the time to process real-time incoming documents and is therefore especially suitable for live feeds. The paper presents experiments with both architectures, and reports the overall gain when they are used for batch as well as for streaming processing. All the software described in the paper is publicly available under free licenses.
Tasks
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1714/
PDF	https://www.aclweb.org/anthology/L16-1714
PWC	https://paperswithcode.com/paper/two-architectures-for-parallel-processing-of
Repo
Framework