Word Alignment

51 papers with code • 7 benchmarks • 3 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.

Source: Neural Network-based Word Alignment through Score Aggregation

Greatest papers with code

Jointly Learning to Align and Translate with Transformer Models

pytorch/fairseq IJCNLP 2019

The state of the art in machine translation (MT) is governed by neural approaches, which typically provide superior translation accuracy over statistical approaches.

Machine Translation Translation +1

FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization

espnet/espnet 21 Oct 2020

FastEmit also improves streaming ASR accuracy from 4. 4%/8. 9% to 3. 1%/7. 5% WER, meanwhile reduces 90th percentile latency from 210 ms to only 30 ms on LibriSpeech.

automatic-speech-recognition Speech Recognition +1

Word Translation Without Parallel Data

facebookresearch/MUSE ICLR 2018

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.

Translation Unsupervised Machine Translation +2

Guided Alignment Training for Topic-Aware Neural Machine Translation

OpenNMT/OpenNMT-tf AMTA 2016

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.

Domain Adaptation Machine Translation +2

Addressing the Rare Word Problem in Neural Machine Translation

atpaino/deep-text-corrector IJCNLP 2015

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.

Machine Translation Translation +1

Bilingual Lexicon Induction through Unsupervised Machine Translation

artetxem/monoses ACL 2019

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.

Bilingual Lexicon Induction Language Modelling +4

SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings

masoudjs/simalign Findings of the Association for Computational Linguistics 2020

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.

Machine Translation Multilingual Word Embeddings +2

PortaSpeech: Portable and High-Quality Generative Text-to-Speech

keonlee9420/PortaSpeech NeurIPS 2021

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.

Word Alignment

Word Alignment by Fine-tuning Embeddings on Parallel Corpora

neulab/awesome-align EACL 2021

In addition, we demonstrate that we are able to train multilingual word aligners that can obtain robust performance on different language pairs.

Cross-Lingual Transfer Fine-tuning +3