May 5, 2019

1105 words 6 mins read

Paper Group NANR 27

That’ll Do Fine!: A Coarse Lexical Resource for English-Hindi MT, Using Polylingual Topic Models. Bidirectional LSTM for Named Entity Recognition in Twitter Messages. Adding syntactic structure to bilingual terminology for improved domain adaptation. Data Resource Acquisition from People at Various Stages of Cognitive Decline – Design and Explorat …

That’ll Do Fine!: A Coarse Lexical Resource for English-Hindi MT, Using Polylingual Topic Models


Title	That’ll Do Fine!: A Coarse Lexical Resource for English-Hindi MT, Using Polylingual Topic Models
Authors	Diptesh Kanojia, Aditya Joshi, Pushpak Bhattacharyya, Mark James Carman
Abstract	Parallel corpora are often injected with bilingual lexical resources for improved Indian language machine translation (MT). In absence of such lexical resources, multilingual topic models have been used to create coarse lexical resources in the past, using a Cartesian product approach. Our results show that for morphologically rich languages like Hindi, the Cartesian product approach is detrimental for MT. We then present a novel {`}sentential{'} approach to use this coarse lexical resource from a multilingual topic model. Our coarse lexical resource when injected with a parallel corpus outperforms a system trained using parallel corpus and a good quality lexical resource. As demonstrated by the quality of our coarse lexical resource and its benefit to MT, we believe that our sentential approach to create such a resource will help MT for resource-constrained languages. \|
Tasks	Machine Translation, Topic Models
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1349/
PDF	https://www.aclweb.org/anthology/L16-1349
PWC	https://paperswithcode.com/paper/thatll-do-fine-a-coarse-lexical-resource-for
Repo
Framework

Bidirectional LSTM for Named Entity Recognition in Twitter Messages


Title	Bidirectional LSTM for Named Entity Recognition in Twitter Messages
Authors	Nut Limsopatham, Nigel Collier
Abstract	In this paper, we present our approach for named entity recognition in Twitter messages that we used in our participation in the Named Entity Recognition in Twitter shared task at the COLING 2016 Workshop on Noisy User-generated text (WNUT). The main challenge that we aim to tackle in our participation is the short, noisy and colloquial nature of tweets, which makes named entity recognition in Twitter message a challenging task. In particular, we investigate an approach for dealing with this problem by enabling bidirectional long short-term memory (LSTM) to automatically learn orthographic features without requiring feature engineering. In comparison with other systems participating in the shared task, our system achieved the most effective performance on both the {`}segmentation and categorisation{'} and the {`}segmentation only{'} sub-tasks.
Tasks	Feature Engineering, Named Entity Recognition
Published	2016-12-01
URL	https://www.aclweb.org/anthology/W16-3920/
PDF	https://www.aclweb.org/anthology/W16-3920
PWC	https://paperswithcode.com/paper/bidirectional-lstm-for-named-entity
Repo
Framework

Adding syntactic structure to bilingual terminology for improved domain adaptation


Title	Adding syntactic structure to bilingual terminology for improved domain adaptation
Authors	Mikel Artetxe, Gorka Labaka, Chakaveh Saedi, Jo{~a}o Rodrigues, Jo{~a}o Silva, Ant{'o}nio Branco, Eneko Agirre
Abstract
Tasks	Domain Adaptation, Machine Translation
Published	2016-10-01
URL	https://www.aclweb.org/anthology/W16-6405/
PDF	https://www.aclweb.org/anthology/W16-6405
PWC	https://paperswithcode.com/paper/adding-syntactic-structure-to-bilingual
Repo
Framework

Data Resource Acquisition from People at Various Stages of Cognitive Decline – Design and Exploration Considerations


Title	Data Resource Acquisition from People at Various Stages of Cognitive Decline – Design and Exploration Considerations
Authors	Dimitrios Kokkinakis, Kristina Lundholm Fors, Arto Nordlund
Abstract
Tasks
Published	2016-11-01
URL	https://www.aclweb.org/anthology/W16-6104/
PDF	https://www.aclweb.org/anthology/W16-6104
PWC	https://paperswithcode.com/paper/data-resource-acquisition-from-people-at
Repo
Framework

Relating semantic similarity and semantic association to how humans label other people


Title	Relating semantic similarity and semantic association to how humans label other people
Authors	Kenneth Joseph, Kathleen M. Carley
Abstract
Tasks	Semantic Similarity, Semantic Textual Similarity, Topic Models
Published	2016-11-01
URL	https://www.aclweb.org/anthology/W16-5601/
PDF	https://www.aclweb.org/anthology/W16-5601
PWC	https://paperswithcode.com/paper/relating-semantic-similarity-and-semantic
Repo
Framework

A Vector Model for Type-Theoretical Semantics


Title	A Vector Model for Type-Theoretical Semantics
Authors	Konstantin Sokolov
Abstract
Tasks	Representation Learning
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-1627/
PDF	https://www.aclweb.org/anthology/W16-1627
PWC	https://paperswithcode.com/paper/a-vector-model-for-type-theoretical-semantics
Repo
Framework


Title	Twitter at the Grammys: A Social Media Corpus for Entity Linking and Disambiguation
Authors	Mark Dredze, Nicholas Andrews, Jay DeYoung
Abstract
Tasks	Coreference Resolution, Entity Linking
Published	2016-11-01
URL	https://www.aclweb.org/anthology/W16-6204/
PDF	https://www.aclweb.org/anthology/W16-6204
PWC	https://paperswithcode.com/paper/twitter-at-the-grammys-a-social-media-corpus
Repo
Framework

Human versus Machine Attention in Document Classification: A Dataset with Crowdsourced Annotations


Title	Human versus Machine Attention in Document Classification: A Dataset with Crowdsourced Annotations
Authors	Nikolaos Pappas, Andrei Popescu-Belis
Abstract
Tasks	Document Classification, Multiple Instance Learning, Sentiment Analysis
Published	2016-11-01
URL	https://www.aclweb.org/anthology/W16-6213/
PDF	https://www.aclweb.org/anthology/W16-6213
PWC	https://paperswithcode.com/paper/human-versus-machine-attention-in-document
Repo
Framework

Integrating WordNet for Multiple Sense Embeddings in Vector Semantics


Title	Integrating WordNet for Multiple Sense Embeddings in Vector Semantics
Authors	David Foley, Jugal Kalita
Abstract
Tasks	Word Sense Disambiguation
Published	2016-12-01
URL	https://www.aclweb.org/anthology/W16-6302/
PDF	https://www.aclweb.org/anthology/W16-6302
PWC	https://paperswithcode.com/paper/integrating-wordnet-for-multiple-sense
Repo
Framework

Proceedings of the 12th Workshop on Multiword Expressions


Title	Proceedings of the 12th Workshop on Multiword Expressions
Authors
Abstract
Tasks
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-1800/
PDF	https://www.aclweb.org/anthology/W16-1800
PWC	https://paperswithcode.com/paper/proceedings-of-the-12th-workshop-on-multiword
Repo
Framework

The TALP–UPC Spanish–English WMT Biomedical Task: Bilingual Embeddings and Char-based Neural Language Model Rescoring in a Phrase-based System


Title	The TALP–UPC Spanish–English WMT Biomedical Task: Bilingual Embeddings and Char-based Neural Language Model Rescoring in a Phrase-based System
Authors	Marta R. Costa-juss{`a}, Cristina Espa{~n}a-Bonet, Pranava Madhyastha, Carlos Escolano, Jos{'e} A. R. Fonollosa
Abstract
Tasks	Language Modelling, Machine Translation, Word Embeddings
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2336/
PDF	https://www.aclweb.org/anthology/W16-2336
PWC	https://paperswithcode.com/paper/the-talpaupc-spanishaenglish-wmt-biomedical
Repo
Framework

網路新興語言&耍'之語意辨析：以批踢踢語料庫為本(On the semantic analysis of the verb shua3 in Taiwan Mandarin: The PTT corpus-based study)[In Chinese]


Title	網路新興語言&耍'之語意辨析：以批踢踢語料庫為本(On the semantic analysis of the verb shua3 in Taiwan Mandarin: The PTT corpus-based study)[In Chinese]
Authors	Hsueh-ying Hu, Siaw-Fong Chung
Abstract
Tasks
Published	2016-10-01
URL	https://www.aclweb.org/anthology/O16-1017/
PDF	https://www.aclweb.org/anthology/O16-1017
PWC	https://paperswithcode.com/paper/c2e-eeae-ea1eae34-i14a1e-e-eaaocoon-the
Repo
Framework

Exploring Topic Discriminating Power of Words in Latent Dirichlet Allocation


Title	Exploring Topic Discriminating Power of Words in Latent Dirichlet Allocation
Authors	Kai Yang, Yi Cai, Zhenhong Chen, Ho-fung Leung, Raymond Lau
Abstract	Latent Dirichlet Allocation (LDA) and its variants have been widely used to discover latent topics in textual documents. However, some of topics generated by LDA may be noisy with irrelevant words scattering across these topics. We name this kind of words as topic-indiscriminate words, which tend to make topics more ambiguous and less interpretable by humans. In our work, we propose a new topic model named TWLDA, which assigns low weights to words with low topic discriminating power (ability). Our experimental results show that the proposed approach, which effectively reduces the number of topic-indiscriminate words in discovered topics, improves the effectiveness of LDA.
Tasks	Topic Models
Published	2016-12-01
URL	https://www.aclweb.org/anthology/C16-1211/
PDF	https://www.aclweb.org/anthology/C16-1211
PWC	https://paperswithcode.com/paper/exploring-topic-discriminating-power-of-words
Repo
Framework

MUSEEC: A Multilingual Text Summarization Tool


Title	MUSEEC: A Multilingual Text Summarization Tool
Authors	Marina Litvak, Natalia Vanetik, Mark Last, Elena Churkin
Abstract
Tasks	Abstractive Text Summarization, Document Summarization, Sentence Compression, Text Summarization
Published	2016-08-01
URL	https://www.aclweb.org/anthology/P16-4013/
PDF	https://www.aclweb.org/anthology/P16-4013
PWC	https://paperswithcode.com/paper/museec-a-multilingual-text-summarization-tool
Repo
Framework

Learning to Identify Subjective Sentences


Title	Learning to Identify Subjective Sentences
Authors	Girish K. Palshikar, Manoj Apte, P, Deepak ita, Vikram Singh
Abstract
Tasks	Opinion Mining, Sentiment Analysis
Published	2016-12-01
URL	https://www.aclweb.org/anthology/W16-6330/
PDF	https://www.aclweb.org/anthology/W16-6330
PWC	https://paperswithcode.com/paper/learning-to-identify-subjective-sentences
Repo
Framework