Neural Semantic Encoders

Tsendsuren Munkhdalai, Hong Yu


Abstract
We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read, compose and write operations. NSE can also access 1 multiple and shared memories. In this paper, we demonstrated the effectiveness and the flexibility of NSE on five different natural language tasks: natural language inference, question answering, sentence classification, document sentiment analysis and machine translation where NSE achieved state-of-the-art performance when evaluated on publically available benchmarks. For example, our shared-memory model showed an encouraging result on neural machine translation, improving an attention-based baseline by approximately 1.0 BLEU.
Anthology ID:
E17-1038
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
397–407
Language:
URL:
https://aclanthology.org/E17-1038
DOI:
Bibkey:
Cite (ACL):
Tsendsuren Munkhdalai and Hong Yu. 2017. Neural Semantic Encoders. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 397–407, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Neural Semantic Encoders (Munkhdalai & Yu, EACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/E17-1038.pdf
Code
 tsendeemts/nse +  additional community code
Data
SNLISSTSST-2WMT 2014WikiQA