TY - GEN
T1 - A unified neural coherence model
AU - Moon, Han Cheol
AU - Mohiuddin, Tasnim
AU - Joty, Shafiq
AU - Chi, Xu
N1 - Publisher Copyright:
© 2019 Association for Computational Linguistics
PY - 2019
Y1 - 2019
N2 - Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In particular, the existing models under-perform on tasks that require the model to be sensitive to local contexts such as candidate ranking in conversational dialogue and in machine translation. In this paper, we propose a unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural framework. With extensive experiments on local and global discrimination tasks, we demonstrate that our proposed model outperforms existing models by a good margin, and establish a new state-of-the-art.
AB - Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In particular, the existing models under-perform on tasks that require the model to be sensitive to local contexts such as candidate ranking in conversational dialogue and in machine translation. In this paper, we propose a unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural framework. With extensive experiments on local and global discrimination tasks, we demonstrate that our proposed model outperforms existing models by a good margin, and establish a new state-of-the-art.
UR - http://www.scopus.com/inward/record.url?scp=85084299004&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85084299004
T3 - EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference
SP - 2262
EP - 2272
BT - EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference
PB - Association for Computational Linguistics
T2 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019
Y2 - 3 November 2019 through 7 November 2019
ER -