Learning Context-Sensitive Convolutional Filters for Text Processing

Dinghan Shen, Martin Renqiang Min, Yitong Li, Lawrence Carin

[How to correct problems with metadata yourself]

Abstract
Convolutional neural networks (CNNs) have recently emerged as a popular building block for natural language processing (NLP). Despite their success, most existing CNN models employed in NLP share the same learned (and static) set of filters for all input sentences. In this paper, we consider an approach of using a small meta network to learn context-sensitive convolutional filters for text processing. The role of meta network is to abstract the contextual information of a sentence or document into a set of input-sensitive filters. We further generalize this framework to model sentence pairs, where a bidirectional filter generation mechanism is introduced to encapsulate co-dependent sentence representations. In our benchmarks on four different tasks, including ontology classification, sentiment analysis, answer sentence selection, and paraphrase identification, our proposed model, a modified CNN with context-sensitive filters, consistently outperforms the standard CNN and attention-based CNN baselines. By visualizing the learned context-sensitive filters, we further validate and rationalize the effectiveness of proposed framework.
Anthology ID:
D18-1210
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1839–1848
Language:
URL:
https://aclanthology.org/D18-1210
DOI:
10.18653/v1/D18-1210
Bibkey:
Cite (ACL):
Dinghan Shen, Martin Renqiang Min, Yitong Li, and Lawrence Carin. 2018. Learning Context-Sensitive Convolutional Filters for Text Processing. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1839–1848, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Learning Context-Sensitive Convolutional Filters for Text Processing (Shen et al., EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/D18-1210.pdf
Video:
 https://preview.aclanthology.org/teach-a-man-to-fish/D18-1210.mp4
Data
DBpedia, WikiQA, Yelp
PDF Search Video