SOTAVerified

Confidence through Attention

2017-10-10MTSummit 2017Code Available0· sign in to hype

Matīss Rikters, Mark Fishel

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Attention distributions of the generated translations are a useful bi-product of attention-based recurrent neural network translation models and can be treated as soft alignments between the input and output tokens. In this work, we use attention distributions as a confidence metric for output translations. We present two strategies of using the attention distributions: filtering out bad translations from a large back-translated corpus, and selecting the best translation in a hybrid setup of two different translation systems. While manual evaluation indicated only a weak correlation between our confidence score and human judgments, the use-cases showed improvements of up to 2.22 BLEU points for filtering and 0.99 points for hybrid translation, tested on English<->German and English<->Latvian translation.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
WMT 2017 Latvian-EnglishAttention-based Hybrid NMT combinationBLEU14.83Unverified

Reproductions