Capturing Long-range Contextual Dependencies with Memory-enhanced Conditional Random Fields

Fei Liu, Timothy Baldwin, Trevor Cohn


Abstract
Despite successful applications across a broad range of NLP tasks, conditional random fields (“CRFs”), in particular the linear-chain variant, are only able to model local features. While this has important benefits in terms of inference tractability, it limits the ability of the model to capture long-range dependencies between items. Attempts to extend CRFs to capture long-range dependencies have largely come at the cost of computational complexity and approximate inference. In this work, we propose an extension to CRFs by integrating external memory, taking inspiration from memory networks, thereby allowing CRFs to incorporate information far beyond neighbouring steps. Experiments across two tasks show substantial improvements over strong CRF and LSTM baselines.
Anthology ID:
I17-1056
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
555–565
Language:
URL:
https://aclanthology.org/I17-1056
DOI:
Bibkey:
Cite (ACL):
Fei Liu, Timothy Baldwin, and Trevor Cohn. 2017. Capturing Long-range Contextual Dependencies with Memory-enhanced Conditional Random Fields. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 555–565, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Capturing Long-range Contextual Dependencies with Memory-enhanced Conditional Random Fields (Liu et al., IJCNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/I17-1056.pdf
Code
 liufly/mecrf
Data
CoNLL 2003