· 2014
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
- 6,641citations
- 2014year
Short summary
Neural machine translation (NMT) using encoder-decoder models performs well on short sentences but struggles with longer ones and unknown words, though a proposed gated recursive convolutional network can learn grammatical structure.
AI-generated from the title and abstract; the full text is not read.
Key points
- Encoder-decoder NMT models extract fixed-length representations from input sentences to generate translations.
- Performance of NMT degrades significantly with sentence length and the presence of unknown words.
- A newly proposed gated recursive convolutional network automatically learns grammatical structure.
AI-generated from the title and abstract; the full text is not read.
Abstract
Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks.The neural machine translation models often consist of an encoder and a decoder.The encoder extracts a fixed-length representation from a variable-length input sentence, and the decoder generates a correct translation from this representation.In this paper, we focus on analyzing the properties of the neural machine translation using two models; RNN Encoder-Decoder and a newly proposed gated recursive convolutional neural network.We show that the neural machine translation performs relatively well on short sentences without unknown words, but its performance degrades rapidly as the length of the sentence and the number of unknown words increase.Furthermore, we find that the proposed gated recursive convolutional network learns a grammatical structure of a sentence automatically.
The authors' abstract, as published at the source., 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