Word Alignment
84 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
Benchmarks
These leaderboards are used to track progress in Word Alignment
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
WMT 2016 News
MUSE
Europarl ConcoDisco Dataset
Bangla Word Analogy
Most implemented papers
Improving Discourse Relation Projection to Build Discourse Annotated Corpora
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
We present a pointwise mutual information (PMI)-based approach to formalize paraphrasability and propose a variant of PMI, called MIPA, for the paraphrase acquisition.
An Operation Sequence Model for Explainable Neural Machine Translation
We propose to achieve explainable neural machine translation (NMT) by changing the output representation to explain itself.
CEA LIST: Processing Low-Resource Languages for CoNLL 2018
tdozat/Parser-v2
•
•
CONLL 2018
In this paper, we describe the system used for our first participation at the CoNLL 2018 shared task.
PD3: Better Low-Resource Cross-Lingual Transfer By Combining Direct Transfer and Annotation Projection
UKPLab/emnlp2018-argmin-workshop-pd3
•
•
WS 2018
We consider unsupervised cross-lingual transfer on two tasks, viz., sentence-level argumentation mining and standard POS tagging.
Adding Interpretable Attention to Neural Translation Models Improves Word Alignment
Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a result.
Phonetically-Oriented Word Error Alignment for Speech Recognition Error Analysis in Speech Translation
We propose a variation to the commonly used Word Error Rate (WER) metric for speech recognition evaluation which incorporates the alignment of phonemes, in the absence of time boundary information.
