clm_765de187In this paper, we present a general end-to-end ap proach to sequence learning that makes minimal assumptions on the sequence structure.
arXiv 1409.3215 · cs.CL cs.LG
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_765de187In this paper, we present a general end-to-end ap proach to sequence learning that makes minimal assumptions on the sequence structure.
res_3a7f25aaOur main result is that on an English to French translation task from the WMT’14 dataset, the translationsproduced by the LSTM achieve a BLEU score of 34.8 on the entire … (excerpt)
res_516e4bc4For comparison, a phrase- based SMT system achieves a BLEU score of 33.3 on the same dataset.
res_7a1ff2e6When we used the LSTM to rerank the 1000 hypotheses produced by the aforementione d SMT system, its BLEU score increases to 36.5, which is close to the previous b … (excerpt)
clm_61f0c1abIn this paper, we show that a straig htforward application of the Long Short-Term Memory (LSTM) architecture [16] can solve gener al sequence to sequence problems.
res_b12c9d87Our approach is closely relat ed to Kalchbrenner and Blunsom [18] who were the first to map the entire input sentence to vector, and is related to Cho et al. … (excerpt)
res_3bc410caOn the WMT’14 En glish to French translation task, we obtained a BLEU score of 34.81 by directly extracting translations from an ensemble of 5 de ep LSTMs (with 384M … (excerpt)
res_1fcebab2The 34.81 BLEU score was achieved by an LSTM with a vocabulary of 80k words, so the score was penalized whenever the reference translation contained a word not cov ered … (excerpt)
clm_16450f6aThis result shows that a relatively unoptimized small-vocabulary neural net work architecture which has much room for improvement outperforms a phrase-based SMT system.
res_73b01852By doing so, we obtained a BLEU score of 36.5, which improves the baseline by 3.2 BLEU points and is close to the previous best published result on this task … (excerpt)
clm_cc2aefdcSecond, we found that deep LSTMs significantly outperformed shallow LSTMs, so we chose an LSTM with four layers.
res_ac4570bdThe resulting implementation achieved a speed of 6,300 (both English and French) words per second with a minibatch size of 128.
res_8b850891While the decoded translations of the LSTM ensemble do not outperform the best WMT’14 system, it is the first time that a pure neural translation system outperforms a phrase-based SMT … (excerpt)
res_4a2a3308There is no degradation on sentences with less than 35 words, there is only a minor degradation on the longest sentences.
clm_244e4735In this work, we showed that a large deep LSTM, that has a limit ed vocabulary and that makes almost no assumption about problem structure can outperform a standard SMT-based … (excerpt)
clm_c2329a95We were surprised by the extent of the improvement obtained b y reversing the words in the source sentences.
clm_9d9504ecMost importantly, we demonstrated that a simple, straightf orward and a relatively unoptimized approach can outperform an SMT system, so further work will lik ely lead to even greater translation … (excerpt)
Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1409.3215) 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.