arXiv (Cornell University)· 2014· Preprint
Neural Machine Translation by Jointly Learning to Align and Translate
- 14,622citations
- 2014year
Short summary
A new neural machine translation model overcomes the fixed-length vector bottleneck of encoder-decoder architectures by learning to soft-align source sentence parts to target words, achieving state-of-the-art English-to-French translation performance.
AI-generated from the title and abstract; the full text is not read.
Key points
- Proposes a neural machine translation model that avoids a fixed-length vector bottleneck.
- Introduces a soft-alignment mechanism for dynamically searching relevant source sentence parts.
- Achieves translation performance comparable to state-of-the-art phrase-based systems on English-to-French.
- Qualitative analysis shows intuitive soft-alignments between source and target words.
AI-generated from the title and abstract; the full text is not read.
Abstract
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural machine translation often belong to a family of encoder-decoders and consists of an encoder that encodes a source sentence into a fixed-length vector from which a decoder generates a translation. In this paper, we conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and propose to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly. With this new approach, we achieve a translation performance comparable to the existing state-of-the-art phrase-based system on the task of English-to-French translation. Furthermore, qualitative analysis reveals that the (soft-)alignments found by the model agree well with our intuition.
The authors' abstract, as published at the source. arXiv (Cornell University), 2014 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Artificial Intelligence
Artificial IntelligenceComputer Science