clm_d82d1000With 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.
arXiv 1409.0473 · cs.CL cs.LG cs.NE
Read on arXiv · arXiv non-exclusive license
Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.
clm_d82d1000With 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.
clm_14a57aebWe show this allows a model to cope better with long sentences.
clm_f5c7b3aaIn this paper, we show that the proposed approach of jointly learning to align and translate achieves significantly improved translation performance over the basic encoder–decoder approach.
clm_e32e0d22Here, we describe briefly the underlying framework, called RNN Encoder–Decoder, proposed by Cho et al. (2014a) and Sutskever et al. (2014) upon which we build a novel architecture that learns … (excerpt)
clm_4bdf2b4b1 We mean by the state-of-the-art performance, the performance of the conventional phrase-based system without using any neural network-based component.
clm_5dc149f4Hence, we propose to use a bidirectional RNN (BiRNN, Schuster and Paliwal, 1997), which has been successfully used recently in speech recognition (see, e.g., Graves et al., 2013).
clm_67dd9d1aIt is clear from the table that in all the cases, the proposed RNNsearch outperforms the conventional RNNencdec.
res_530a221aThis is a significant achievement, considering that Moses uses a separate monolingual corpus (418M words) in addition to the parallel corpora we used to train the RNNsearch and RNNencdec.
res_62c0a117On the other hand, both RNNsearch-30 and RNNsearch-50 are more robust to the length of the sentences.
res_dfffa427This superiority of the proposed model over the basic encoder–decoder is further confirmed by the fact that the RNNsearch-30 even outperforms RNNencdec-50 (see Table 1).
res_e1f2a17bNote that RNNsearch-50⋆ was trained much longer until the performance on the development set stopped improving.
clm_6a5348e0In this paper, we proposed a novel architecture that addresses this issue.
clm_708fc3ceThe experiment revealed that the proposed RNNsearch outperforms the conventional encoder–decoder model (RNNencdec) significantly, regardless of the sentence length and that it is much more robust to the length of … (excerpt)
clm_035ea1abThis will be required for the model to be more widely used and to match the performance of current state-of-the-art machine translation systems in all contexts.
Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1409.0473) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.