Word Alignment

83 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.

Source: Neural Network-based Word Alignment through Score Aggregation

Most implemented papers

Multilingual Distributed Representations without Word Alignment

karlmoritz/bicvm 20 Dec 2013

Distributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP.

Conditional Random Field Autoencoders for Unsupervised Structured Prediction

ldmt-muri/alignment-with-openfst NeurIPS 2014

We introduce a framework for unsupervised learning of structured predictors with overlapping, global features.

Agreement-based Joint Training for Bidirectional Attention-based Neural Machine Translation

bagequan/tencent-transformer-with-disagreement 15 Dec 2015

The attentional mechanism has proven to be effective in improving end-to-end neural machine translation.

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.

A Web-Based Interactive Tool for Creating, Inspecting, Editing, and Publishing Etymological Datasets

digling/edictor EACL 2017

The paper presents the Etymological DICtionary ediTOR (EDICTOR), a free, interactive, web-based tool designed to aid historical linguists in creating, editing, analysing, and publishing etymological datasets.

Improving Discourse Relation Projection to Build Discourse Annotated Corpora

mjlaali/Europarl-ConcoDisco RANLP 2017

We then used this corpus to train a classifier to identify the discourse-usage of French discourse connectives and show a 15% improvement of F1-score compared to the classifier trained on the non-filtered annotations.

MIPA: Mutual Information Based Paraphrase Acquisition via Bilingual Pivoting

tmu-nlp/pmi-ppdb IJCNLP 2017

We present a pointwise mutual information (PMI)-based approach to formalize paraphrasability and propose a variant of PMI, called MIPA, for the paraphrase acquisition.