Word Alignment is the task of finding the correspondence between source and target words in a pair of sentences that are translations of each other.
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
The state of the art in machine translation (MT) is governed by neural approaches, which typically provide superior translation accuracy over statistical approaches.
We finally describe experiments on the English-Esperanto low-resource language pair, on which there only exists a limited amount of parallel data, to show the potential impact of our method in fully unsupervised machine translation.
Ranked #2 on Word Alignment on en-es
In this paper, we propose an effective way for biasing the attention mechanism of a sequence-to-sequence neural machine translation (NMT) model towards the well-studied statistical word alignment models.
Our experiments on the WMT14 English to French translation task show that this method provides a substantial improvement of up to 2. 8 BLEU points over an equivalent NMT system that does not use this technique.
Ranked #25 on Machine Translation on WMT2014 English-French
A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation pairs through nearest neighbor or related retrieval methods.
We find that alignments created from embeddings are superior for four and comparable for two language pairs compared to those produced by traditional statistical aligners, even with abundant parallel data; e. g., contextualized embeddings achieve a word alignment F1 for English-German that is 5 percentage points higher than eflomal, a high-quality statistical aligner, trained on 100k parallel sentences.
Distributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP.