Semantically Smooth Bilingual Phrase Embeddings Based on Recursive Autoencoders

In this paper, we propose Semantically Smooth Bilingual Recursive Autoencoders to learn bilingual phrase embeddings. The intuition behind our work is to exploit the intrinsic geometric structure of the embedding space and enforce the learned phrase embeddings to be semantically smooth. Specifically,...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Neural processing letters Ročník 51; číslo 3; s. 2497 - 2512
Hlavní autori: Lin, Qian, Yang, Jing, Zhang, Xiangwen, Wang, Hongji, Lu, Yaojie, Su, Jinsong
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.06.2020
Springer Nature B.V
Predmet:
Artificial Intelligence
Bilingualism
Complex Systems
Computational Intelligence
Computer Science
Deep learning
Graph representations
Language
Machine translation
Probability
Probability distribution
Regularization
Semantics
Similarity
Statistical analysis
Translations
Bilingual phrase embeddings
Machine translation
Similarity constraints
ISSN:1370-4621, 1573-773X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In this paper, we propose Semantically Smooth Bilingual Recursive Autoencoders to learn bilingual phrase embeddings. The intuition behind our work is to exploit the intrinsic geometric structure of the embedding space and enforce the learned phrase embeddings to be semantically smooth. Specifically, we extend the conventional bilingual recursive autoencoders by preserving the translation and paraphrase probability distributions via regularization terms to simultaneously exploit richer explicit and implicit similarity constraints for bilingual phrase embeddings. To examine the effectiveness of our model, we incorporate two phrase-level similarity features based on the proposed model into a state-of-the-art phrase-based statistical machine translation system. Experiments on NIST Chinese–English test sets show that our model achieves substantial improvements over the baseline.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1370-4621
1573-773X
DOI:10.1007/s11063-020-10210-1