Pith. sign in

REVIEW 1 cited by

Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks

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 1810.12546 v1 pith:PLSGVRNR submitted 2018-10-30 cs.CL

classification cs.CL
keywords translationlanguagemachineneuralrecurrenttwin-gatedexperimentsnatural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we propose an additionsubtraction twin-gated recurrent network (ATR) to simplify neural machine translation. The recurrent units of ATR are heavily simplified to have the smallest number of weight matrices among units of all existing gated RNNs. With the simple addition and subtraction operation, we introduce a twin-gated mechanism to build input and forget gates which are highly correlated. Despite this simplification, the essential non-linearities and capability of modeling long-distance dependencies are preserved. Additionally, the proposed ATR is more transparent than LSTM/GRU due to the simplification. Forward self-attention can be easily established in ATR, which makes the proposed network interpretable. Experiments on WMT14 translation tasks demonstrate that ATR-based neural machine translation can yield competitive performance on English- German and English-French language pairs in terms of both translation quality and speed. Further experiments on NIST Chinese-English translation, natural language inference and Chinese word segmentation verify the generality and applicability of ATR on different natural language processing tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. GhostRNN: Reducing State Redundancy in RNN with Cheap Operations

    cs.CL 2024-11 conditional novelty 4.0 of 10

    GhostRNN compresses RNN hidden states by generating ghost states from a small set of intrinsic states with cheap linear operations, cutting parameters by about 40% with similar accuracy.

Pith tools