Work

End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification

Year: 2018

Type: conference-paper

Abstract: Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time.Non-autoregressive models enable the decoder to generate all output symbols independently in parallel.We present a novel nonautoregressive architecture based on connectionist temporal classification and evaluate it on the task of neural machine translation.Unlike other non-autoregressive methods which operate in several steps, our model can be trained end-to-end.We conduct experiments on the WMT English-Romanian and English-German datasets.Our models achieve a significant speedup over the autoregressive models, keeping the translation quality comparable to other non-autoregressive models.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/d18-1336

Authors: Jindřich Libovický, Jindřich Helcl

Institution: Charles University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Univerzita Karlova v Praze, Grantová Agentura České Republiky

Award: Center for Large Scale Multi-modal Data Interpretation