COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > NLIP Seminar Series > An Operation Sequence Model for Explainable Neural Machine Translation
An Operation Sequence Model for Explainable Neural Machine TranslationAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Andrew Caines. We propose to achieve explainable neural machine translation (NMT) by changing the output representation to explain itself. We present a novel approach to NMT which generates the target sentence by monotonically walking through the source sentence. Word reordering is modeled by operations which allow setting markers in the target sentence and move a target-side write head between those markers. In contrast to many modern neural models, our system emits explicit word alignment information which is often crucial to practical machine translation as it improves explainability. Our technique can outperform a plain text system in terms of BLEU score under the recent Transformer architecture on Japanese-English and Portuguese-English, and is within 0.5 BLEU difference on Spanish-English. This talk is part of the NLIP Seminar Series series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsCambridge Italian Research Network Bioinformatics jounal club for the -omics Open Knowledge MeetupsOther talksRecognition of the amyloid precursor protein by human γ-secretase Heliconical cholesteric liquid crystals: self-assembled tunable photonic bandgap materials - 1 The Cambridge Autism Genetics Symposium Are Your Selfies Carbon-Neutral? Human Rights and the Environmental Impact of Digital Technology Longitudinal analysis of intracortical microstructural profiles during adolescent development |