May 5, 2019

1135 words 6 mins read

Paper Group NANR 113

Supervised Distributional Hypernym Discovery via Domain Adaptation. Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Sparsity. IRT-based Aggregation Model of Crowdsourced Pairwise Comparison for Evaluating Machine Translations. Emotion Distribution Learning from Texts. Generating Abbreviations for Chinese Named Entities U …

Supervised Distributional Hypernym Discovery via Domain Adaptation


Title	Supervised Distributional Hypernym Discovery via Domain Adaptation
Authors	Luis Espinosa-Anke, Jose Camacho-Collados, Claudio Delli Bovi, Horacio Saggion
Abstract
Tasks	Domain Adaptation, Hypernym Discovery, Information Retrieval, Knowledge Graphs, Natural Language Inference, Open Information Extraction, Question Answering, Word Sense Disambiguation
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1041/
PDF	https://www.aclweb.org/anthology/D16-1041
PWC	https://paperswithcode.com/paper/supervised-distributional-hypernym-discovery
Repo
Framework

Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Sparsity


Title	Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Sparsity
Authors	Vinayak Athavale, Shreenivas Bharadwaj, Monik Pamecha, Ameya Prabhu, Manish Shrivastava
Abstract
Tasks	Feature Engineering, Machine Translation, Morphological Analysis, Named Entity Recognition, Question Answering
Published	2016-12-01
URL	https://www.aclweb.org/anthology/W16-6320/
PDF	https://www.aclweb.org/anthology/W16-6320
PWC	https://paperswithcode.com/paper/towards-deep-learning-in-hindi-ner-an-1
Repo
Framework

IRT-based Aggregation Model of Crowdsourced Pairwise Comparison for Evaluating Machine Translations


Title	IRT-based Aggregation Model of Crowdsourced Pairwise Comparison for Evaluating Machine Translations
Authors	Naoki Otani, Toshiaki Nakazawa, Daisuke Kawahara, Sadao Kurohashi
Abstract
Tasks	Machine Translation, Text Matching
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1049/
PDF	https://www.aclweb.org/anthology/D16-1049
PWC	https://paperswithcode.com/paper/irt-based-aggregation-model-of-crowdsourced
Repo
Framework

Emotion Distribution Learning from Texts


Title	Emotion Distribution Learning from Texts
Authors	Deyu Zhou, Xuan Zhang, Yin Zhou, Quan Zhao, Xin Geng
Abstract
Tasks	Emotion Classification, Emotion Recognition, Multi-Label Learning, Product Recommendation, Text Classification
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1061/
PDF	https://www.aclweb.org/anthology/D16-1061
PWC	https://paperswithcode.com/paper/emotion-distribution-learning-from-texts
Repo
Framework

Generating Abbreviations for Chinese Named Entities Using Recurrent Neural Network with Dynamic Dictionary


Title	Generating Abbreviations for Chinese Named Entities Using Recurrent Neural Network with Dynamic Dictionary
Authors	Qi Zhang, Jin Qian, Ya Guo, Yaqian Zhou, Xuanjing Huang
Abstract
Tasks	Named Entity Recognition, Opinion Mining
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1069/
PDF	https://www.aclweb.org/anthology/D16-1069
PWC	https://paperswithcode.com/paper/generating-abbreviations-for-chinese-named
Repo
Framework

Transferring User Interests Across Websites with Unstructured Text for Cold-Start Recommendation


Title	Transferring User Interests Across Websites with Unstructured Text for Cold-Start Recommendation
Authors	Yu-Yang Huang, Shou-De Lin
Abstract
Tasks	Recommendation Systems, Transfer Learning
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1077/
PDF	https://www.aclweb.org/anthology/D16-1077
PWC	https://paperswithcode.com/paper/transferring-user-interests-across-websites
Repo
Framework

Modeling Skip-Grams for Event Detection with Convolutional Neural Networks


Title	Modeling Skip-Grams for Event Detection with Convolutional Neural Networks
Authors	Thien Huu Nguyen, Ralph Grishman
Abstract
Tasks	Domain Adaptation, Feature Engineering
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1085/
PDF	https://www.aclweb.org/anthology/D16-1085
PWC	https://paperswithcode.com/paper/modeling-skip-grams-for-event-detection-with
Repo
Framework

Neural Network for Heterogeneous Annotations


Title	Neural Network for Heterogeneous Annotations
Authors	Hongshen Chen, Yue Zhang, Qun Liu
Abstract
Tasks	Dependency Parsing, Domain Adaptation, Feature Engineering, Multiview Learning
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1070/
PDF	https://www.aclweb.org/anthology/D16-1070
PWC	https://paperswithcode.com/paper/neural-network-for-heterogeneous-annotations
Repo
Framework

Richer Interpolative Smoothing Based on Modified Kneser-Ney Language Modeling


Title	Richer Interpolative Smoothing Based on Modified Kneser-Ney Language Modeling
Authors	Ehsan Shareghi, Trevor Cohn, Gholamreza Haffari
Abstract
Tasks	Language Modelling, Machine Translation, Speech Recognition
Published	2016-11-01
URL	https://www.aclweb.org/anthology/D16-1094/
PDF	https://www.aclweb.org/anthology/D16-1094
PWC	https://paperswithcode.com/paper/richer-interpolative-smoothing-based-on
Repo
Framework

Generating summaries of hospitalizations: A new metric to assess the complexity of medical terms and their definitions


Title	Generating summaries of hospitalizations: A new metric to assess the complexity of medical terms and their definitions
Authors	Sabita Acharya, Barbara Di Eugenio, Andrew D. Boyd, Karen Dunn Lopez, Richard Cameron, Gail M Keenan
Abstract
Tasks	Text Generation
Published	2016-09-01
URL	https://www.aclweb.org/anthology/W16-6604/
PDF	https://www.aclweb.org/anthology/W16-6604
PWC	https://paperswithcode.com/paper/generating-summaries-of-hospitalizations-a
Repo
Framework

Task demands and individual variation in referring expressions


Title	Task demands and individual variation in referring expressions
Authors	Adriana Baltaretu, Thiago Castro Ferreira
Abstract
Tasks	Text Generation
Published	2016-09-01
URL	https://www.aclweb.org/anthology/W16-6615/
PDF	https://www.aclweb.org/anthology/W16-6615
PWC	https://paperswithcode.com/paper/task-demands-and-individual-variation-in
Repo
Framework

Statistical Natural Language Generation from Tabular Non-textual Data


Title	Statistical Natural Language Generation from Tabular Non-textual Data
Authors	Joy Mahapatra, Sudip Kumar Naskar, B, Sivaji yopadhyay
Abstract
Tasks	Text Generation
Published	2016-09-01
URL	https://www.aclweb.org/anthology/W16-6624/
PDF	https://www.aclweb.org/anthology/W16-6624
PWC	https://paperswithcode.com/paper/statistical-natural-language-generation-from
Repo
Framework

Literal and Metaphorical Senses in Compositional Distributional Semantic Models


Title	Literal and Metaphorical Senses in Compositional Distributional Semantic Models
Authors	E.Dario Guti{'e}rrez, Ekaterina Shutova, Tyler Marghetis, Benjamin Bergen
Abstract
Tasks
Published	2016-08-01
URL	https://www.aclweb.org/anthology/P16-1018/
PDF	https://www.aclweb.org/anthology/P16-1018
PWC	https://paperswithcode.com/paper/literal-and-metaphorical-senses-in
Repo
Framework

Interoperability of Annotation Schemes: Using the Pepper Framework to Display AWA Documents in the ANNIS Interface


Title	Interoperability of Annotation Schemes: Using the Pepper Framework to Display AWA Documents in the ANNIS Interface
Authors	Talvany Carlotto, Zuhaitz Beloki, Xabier Artola, Aitor Soroa
Abstract	Natural language processing applications are frequently integrated to solve complex linguistic problems, but the lack of interoperability between these tools tends to be one of the main issues found in that process. That is often caused by the different linguistic formats used across the applications, which leads to attempts to both establish standard formats to represent linguistic information and to create conversion tools to facilitate this integration. Pepper is an example of the latter, as a framework that helps the conversion between different linguistic annotation formats. In this paper, we describe the use of Pepper to convert a corpus linguistically annotated by the annotation scheme AWA into the relANNIS format, with the ultimate goal of interacting with AWA documents through the ANNIS interface. The experiment converted 40 megabytes of AWA documents, allowed their use on the ANNIS interface, and involved making architectural decisions during the mapping from AWA into relANNIS using Pepper. The main issues faced during this process were due to technical issues mainly caused by the integration of the different systems and projects, namely AWA, Pepper and ANNIS.
Tasks
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1639/
PDF	https://www.aclweb.org/anthology/L16-1639
PWC	https://paperswithcode.com/paper/interoperability-of-annotation-schemes-using
Repo
Framework

Building a Monolingual Parallel Corpus for Text Simplification Using Sentence Similarity Based on Alignment between Word Embeddings


Title	Building a Monolingual Parallel Corpus for Text Simplification Using Sentence Similarity Based on Alignment between Word Embeddings
Authors	Tomoyuki Kajiwara, Mamoru Komachi
Abstract	Methods for text simplification using the framework of statistical machine translation have been extensively studied in recent years. However, building the monolingual parallel corpus necessary for training the model requires costly human annotation. Monolingual parallel corpora for text simplification have therefore been built only for a limited number of languages, such as English and Portuguese. To obviate the need for human annotation, we propose an unsupervised method that automatically builds the monolingual parallel corpus for text simplification using sentence similarity based on word embeddings. For any sentence pair comprising a complex sentence and its simple counterpart, we employ a many-to-one method of aligning each word in the complex sentence with the most similar word in the simple sentence and compute sentence similarity by averaging these word similarities. The experimental results demonstrate the excellent performance of the proposed method in a monolingual parallel corpus construction task for English text simplification. The results also demonstrated the superior accuracy in text simplification that use the framework of statistical machine translation trained using the corpus built by the proposed method to that using the existing corpora.
Tasks	Machine Translation, Text Simplification, Word Embeddings
Published	2016-12-01
URL	https://www.aclweb.org/anthology/C16-1109/
PDF	https://www.aclweb.org/anthology/C16-1109
PWC	https://paperswithcode.com/paper/building-a-monolingual-parallel-corpus-for
Repo
Framework