A Unified Neural Coherence Model

by   Han Cheol Moon, et al.
Agency for Science, Technology and Research

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 underperform 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.


page 1

page 2

page 3

page 4


CohEval: Benchmarking Coherence Models

Although coherence modeling has come a long way in developing novel mode...

Text Coherence Analysis Based on Deep Neural Network

In this paper, we propose a novel deep coherence model (DCM) using a con...

Context is Key: New Approaches to Neural Coherence Modeling

We formulate coherence modeling as a regression task and propose two nov...

Coherence Models for Dialogue

Coherence across multiple turns is a major challenge for state-of-the-ar...

Coherence Modeling of Asynchronous Conversations: A Neural Entity Grid Approach

We propose a novel coherence model for written asynchronous conversation...

Modeling Bilingual Conversational Characteristics for Neural Chat Translation

Neural chat translation aims to translate bilingual conversational text,...

Sentence Pair Scoring: Towards Unified Framework for Text Comprehension

We review the task of Sentence Pair Scoring, popular in the literature i...

Please sign up or login with your details

Forgot password? Click here to reset