Word Alignment

21 papers with code · Natural Language Processing

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

Benchmarks

Greatest papers with code

Word Translation Without Parallel Data

ICLR 2018 facebookresearch/MUSE

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.

UNSUPERVISED MACHINE TRANSLATION WORD ALIGNMENT WORD EMBEDDINGS

Guided Alignment Training for Topic-Aware Neural Machine Translation

6 Jul 2016OpenNMT/OpenNMT-tf

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 WORD ALIGNMENT

Addressing the Rare Word Problem in Neural Machine Translation

IJCNLP 2015 atpaino/deep-text-corrector

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 WORD ALIGNMENT

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

18 Apr 2020masoudjs/simalign

Statistical word aligners perform well, as do methods that extract alignments jointly with translations in NMT.

MACHINE TRANSLATION MULTILINGUAL WORD EMBEDDINGS WORD ALIGNMENT

Conversational Word Embedding for Retrieval-Based Dialog System

ACL 2020 wtma/PR-Embedding

Human conversations contain many types of information, e. g., knowledge, common sense, and language habits.

COMMON SENSE REASONING MACHINE TRANSLATION WORD ALIGNMENT

OpusFilter: A Configurable Parallel Corpus Filtering Toolbox

ACL 2020 Helsinki-NLP/OpusFilter

We demonstrate the effectiveness of OpusFilter on the example of a Finnish-English news translation task based on noisy web-crawled training data.

DOMAIN ADAPTATION LANGUAGE IDENTIFICATION WORD ALIGNMENT