Pith. sign in

REVIEW

TranSFormer: Slow-Fast Transformer for Machine Translation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.16982 v1 pith:7BQWQRPR submitted 2023-05-26 cs.CL cs.AI

TranSFormer: Slow-Fast Transformer for Machine Translation

classification cs.CL cs.AI
keywords transformerbranchmachinemodeltextbftranslationbeenbleu
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Learning multiscale Transformer models has been evidenced as a viable approach to augmenting machine translation systems. Prior research has primarily focused on treating subwords as basic units in developing such systems. However, the incorporation of fine-grained character-level features into multiscale Transformer has not yet been explored. In this work, we present a \textbf{S}low-\textbf{F}ast two-stream learning model, referred to as Tran\textbf{SF}ormer, which utilizes a ``slow'' branch to deal with subword sequences and a ``fast'' branch to deal with longer character sequences. This model is efficient since the fast branch is very lightweight by reducing the model width, and yet provides useful fine-grained features for the slow branch. Our TranSFormer shows consistent BLEU improvements (larger than 1 BLEU point) on several machine translation benchmarks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.