May 5, 2019

904 words 5 mins read

Paper Group NANR 89

The Challenge of Simultaneous Speech Translation. Endurant vs Perdurant: Ontological Motivation for Language Variations. The grammar and semantics of disjuncts in World Englishes. Accuracy of Automatic Cross-Corpus Emotion Labeling for Conversational Speech Corpus Commonization. Secondary Predicates in Native and Nonnative Grammars. Event Based Emo …

The Challenge of Simultaneous Speech Translation


Title	The Challenge of Simultaneous Speech Translation
Authors	Anoop Sarkar
Abstract
Tasks
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-1003/
PDF	https://www.aclweb.org/anthology/Y16-1003
PWC	https://paperswithcode.com/paper/the-challenge-of-simultaneous-speech
Repo
Framework

Endurant vs Perdurant: Ontological Motivation for Language Variations


Title	Endurant vs Perdurant: Ontological Motivation for Language Variations
Authors	Chu-Ren Huang
Abstract
Tasks
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-1006/
PDF	https://www.aclweb.org/anthology/Y16-1006
PWC	https://paperswithcode.com/paper/endurant-vs-perdurant-ontological-motivation
Repo
Framework

The grammar and semantics of disjuncts in World Englishes


Title	The grammar and semantics of disjuncts in World Englishes
Authors	Shirley Dita
Abstract
Tasks
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-1008/
PDF	https://www.aclweb.org/anthology/Y16-1008
PWC	https://paperswithcode.com/paper/the-grammar-and-semantics-of-disjuncts-in
Repo
Framework

Accuracy of Automatic Cross-Corpus Emotion Labeling for Conversational Speech Corpus Commonization


Title	Accuracy of Automatic Cross-Corpus Emotion Labeling for Conversational Speech Corpus Commonization
Authors	Hiroki Mori, Atsushi Nagaoka, Yoshiko Arimoto
Abstract	There exists a major incompatibility in emotion labeling framework among emotional speech corpora, that is, category-based and dimension-based. Commonizing these requires inter-corpus emotion labeling according to both frameworks, but doing this by human annotators is too costly for most cases. This paper examines the possibility of automatic cross-corpus emotion labeling. In order to evaluate the effectiveness of the automatic labeling, a comprehensive emotion annotation for two conversational corpora, UUDB and OGVC, was performed. With a state-of-the-art machine learning technique, dimensional and categorical emotion estimation models were trained and tested against the two corpora. For the emotion dimension estimation, the automatic cross-corpus emotion labeling for the different corpus was effective for the dimensions of aroused-sleepy, dominant-submissive and interested-indifferent, showing only slight performance degradation against the result for the same corpus. On the other hand, the performance for the emotion category estimation was not sufficient.
Tasks
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1634/
PDF	https://www.aclweb.org/anthology/L16-1634
PWC	https://paperswithcode.com/paper/accuracy-of-automatic-cross-corpus-emotion
Repo
Framework

Secondary Predicates in Native and Nonnative Grammars


Title	Secondary Predicates in Native and Nonnative Grammars
Authors	Enchao Shi
Abstract
Tasks	Language Acquisition
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-2003/
PDF	https://www.aclweb.org/anthology/Y16-2003
PWC	https://paperswithcode.com/paper/secondary-predicates-in-native-and-nonnative
Repo
Framework

Event Based Emotion Classification for News Articles


Title	Event Based Emotion Classification for News Articles
Authors	Minglei Li, Da Wang, Qin Lu, Yunfei Long
Abstract
Tasks	Emotion Classification, Emotion Recognition, Sentiment Analysis
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-2013/
PDF	https://www.aclweb.org/anthology/Y16-2013
PWC	https://paperswithcode.com/paper/event-based-emotion-classification-for-news
Repo
Framework

The interaction of politeness systems in Korean learners of French


Title	The interaction of politeness systems in Korean learners of French
Authors	Darcy Sperlich, Jaiho Leem, Eui-Jeen Ahn
Abstract
Tasks
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-2014/
PDF	https://www.aclweb.org/anthology/Y16-2014
PWC	https://paperswithcode.com/paper/the-interaction-of-politeness-systems-in
Repo
Framework

Sentiment Clustering with Topic and Temporal Information from Large Email Dataset


Title	Sentiment Clustering with Topic and Temporal Information from Large Email Dataset
Authors	Sisi Liu, Ickjai Lee, Guochen Cai
Abstract
Tasks	Sentiment Analysis, Stock Market Prediction
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-3007/
PDF	https://www.aclweb.org/anthology/Y16-3007
PWC	https://paperswithcode.com/paper/sentiment-clustering-with-topic-and-temporal
Repo
Framework

Automatic Identifying Entity Type in Linked Data


Title	Automatic Identifying Entity Type in Linked Data
Authors	Qingliang Miao, Ruiyu Fang, Shuangyong Song, Zhongguang Zheng, Lu Fang, Yao Meng, Jun Sun
Abstract
Tasks	Entity Linking, Question Answering
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-3009/
PDF	https://www.aclweb.org/anthology/Y16-3009
PWC	https://paperswithcode.com/paper/automatic-identifying-entity-type-in-linked
Repo
Framework

Budgeted stream-based active learning via adaptive submodular maximization


Title	Budgeted stream-based active learning via adaptive submodular maximization
Authors	Kaito Fujii, Hisashi Kashima
Abstract	Active learning enables us to reduce the annotation cost by adaptively selecting unlabeled instances to be labeled. For pool-based active learning, several effective methods with theoretical guarantees have been developed through maximizing some utility function satisfying adaptive submodularity. In contrast, there have been few methods for stream-based active learning based on adaptive submodularity. In this paper, we propose a new class of utility functions, policy-adaptive submodular functions, and prove this class includes many existing adaptive submodular functions appearing in real world problems. We provide a general framework based on policy-adaptive submodularity that makes it possible to convert existing pool-based methods to stream-based methods and give theoretical guarantees on their performance. In addition we empirically demonstrate their effectiveness comparing with existing heuristics on common benchmark datasets.
Tasks	Active Learning
Published	2016-12-01
URL	http://papers.nips.cc/paper/6038-budgeted-stream-based-active-learning-via-adaptive-submodular-maximization
PDF	http://papers.nips.cc/paper/6038-budgeted-stream-based-active-learning-via-adaptive-submodular-maximization.pdf
PWC	https://paperswithcode.com/paper/budgeted-stream-based-active-learning-via
Repo
Framework

Designing CzeDLex – A Lexicon of Czech Discourse Connectives


Title	Designing CzeDLex – A Lexicon of Czech Discourse Connectives
Authors	Ji{\v{r}}{'\i} M{'\i}rovsk{'y}, Pavl{'\i}na J{'\i}nov{'a}, Magdal{'e}na Rysov{'a}, Lucie Pol{'a}kov{'a}
Abstract
Tasks
Published	2016-10-01
URL	https://www.aclweb.org/anthology/Y16-3017/
PDF	https://www.aclweb.org/anthology/Y16-3017
PWC	https://paperswithcode.com/paper/designing-czedlex-a-a-lexicon-of-czech
Repo
Framework

Non-uniform Language Detection in Technical Writing


Title	Non-uniform Language Detection in Technical Writing
Authors	Weibo Wang, Abidalrahman Moh{'}d, Aminul Islam, Axel Soto, Evangelos Milios
Abstract
Tasks
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1194/
PDF	https://www.aclweb.org/anthology/D16-1194
PWC	https://paperswithcode.com/paper/non-uniform-language-detection-in-technical
Repo
Framework

Towards a dialogue system that supports rich visualizations of data


Title	Towards a dialogue system that supports rich visualizations of data
Authors	Abhinav Kumar, Jillian Aurisano, Barbara Di Eugenio, Andrew Johnson, Alberto Gonzalez, Jason Leigh
Abstract
Tasks
Published	2016-09-01
URL	https://www.aclweb.org/anthology/W16-3639/
PDF	https://www.aclweb.org/anthology/W16-3639
PWC	https://paperswithcode.com/paper/towards-a-dialogue-system-that-supports-rich
Repo
Framework

FBK-HLT-NLP at SemEval-2016 Task 2: A Multitask, Deep Learning Approach for Interpretable Semantic Textual Similarity


Title	FBK-HLT-NLP at SemEval-2016 Task 2: A Multitask, Deep Learning Approach for Interpretable Semantic Textual Similarity
Authors	Simone Magnolini, Anna Feltracco, Bernardo Magnini
Abstract
Tasks	Image Captioning, Semantic Textual Similarity
Published	2016-06-01
URL	https://www.aclweb.org/anthology/S16-1121/
PDF	https://www.aclweb.org/anthology/S16-1121
PWC	https://paperswithcode.com/paper/fbk-hlt-nlp-at-semeval-2016-task-2-a
Repo
Framework

Word Embedding Calculus in Meaningful Ultradense Subspaces


Title	Word Embedding Calculus in Meaningful Ultradense Subspaces
Authors	Sascha Rothe, Hinrich Sch{"u}tze
Abstract
Tasks	Word Embeddings
Published	2016-08-01
URL	https://www.aclweb.org/anthology/P16-2083/
PDF	https://www.aclweb.org/anthology/P16-2083
PWC	https://paperswithcode.com/paper/word-embedding-calculus-in-meaningful
Repo
Framework