82 papers with code • 7 benchmarks • 4 datasets
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.
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.
SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings
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.
We introduce MultiATIS++, a new multilingual NLU corpus that extends the Multilingual ATIS corpus to nine languages across four language families, and evaluate our method using the corpus.
In addition, we demonstrate that we are able to train multilingual word aligners that can obtain robust performance on different language pairs.
Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel.
ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective Feedback
The quantitative evaluation demonstrates that our backbone translation models achieve state-of-the-art translation performance and our quality estimation well correlates with both BLEU and human judgment.
Recent dominant methods for video-language pre-training (VLP) learn transferable representations from the raw pixels in an end-to-end manner to achieve advanced performance on downstream video-language retrieval.
Most existing word alignment methods rely on manual alignment datasets or parallel corpora, which limits their usefulness.