Pith. sign in

REVIEW 3 cited by

Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2205.11631 v2 pith:BXQX3GG5 submitted 2022-05-23 cs.CL

Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer

Javier Ferrando , Gerard I. G\'allego , Belen Alastruey , Carlos Escolano , Marta R. Costa-juss\`a This is my paper
classification cs.CL
keywords sourcemethodsentencetargetattributionsinputinterpretabilitymachine
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In Neural Machine Translation (NMT), each token prediction is conditioned on the source sentence and the target prefix (what has been previously translated at a decoding step). However, previous work on interpretability in NMT has mainly focused solely on source sentence tokens' attributions. Therefore, we lack a full understanding of the influences of every input token (source sentence and target prefix) in the model predictions. In this work, we propose an interpretability method that tracks input tokens' attributions for both contexts. Our method, which can be extended to any encoder-decoder Transformer-based model, allows us to better comprehend the inner workings of current NMT models. We apply the proposed method to both bilingual and multilingual Transformers and present insights into their behaviour.

discussion (0)

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

Forward citations

Cited by 3 Pith papers

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

  1. VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation

    cs.CL 2026-05 unverdicted novelty 7.0

    VIDA provides 2,500 visually-dependent ambiguous translation examples and span-level disambiguation metrics; CoT-SFT on LVLMs improves out-of-distribution performance over standard SFT.

  2. VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation

    cs.CL 2026-05 unverdicted novelty 6.0

    VIDA provides 2,500 visually-dependent ambiguous MT instances and LLM-judge metrics; chain-of-thought SFT improves disambiguation accuracy over standard SFT, especially out-of-distribution.

  3. Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models

    cs.LG 2025-08 unverdicted novelty 3.0

    A systematic literature review of explainability in multimodal attention models finds most studies focus on vision-language tasks with attention-based explanations, but evaluation methods lack consistency and modality...