← Back to all news
arXiv AI By Oline Ranum, Edward Fish, Simon Hadfield, Richard Bowden

Beyond BLEU: A Case for Redefining Sign Language Translation Benchmarks

Read the original on arXiv AI →

The paper argues that BLEU-4, the prevailing metric for sign language translation (SLT), may not accurately reflect sign language proficiency because SLT models can exploit spurious correlations and spoken-language priors. By evaluating six SLT models on Phoenix-2014T and CSL-Daily, the authors show that higher BLEU-4 scores do not necessarily indicate better spatio-temporal understanding. They propose a new open-weight LLM QA protocol inspired by language-learning assessment, which better preserves salient content, aligns more closely with human rankings, and reveals differences between gloss-free and gloss-supervised systems that BLEU-4 obscures.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computer Vision
Sep 4

SignSeek: Learning Transferable Representations for Sign Dictionary Retrieval

SignSeek is a new method for learning transferable sign representations that enables efficient retrieval of signs from dictionaries using only a query video. It employs contrastive learning with saliency‑guided articulator masking, aligning same‑gloss signs across signers while focusing on the single most critical articulator per sign. Trained on 266K samples from multiple sign languages, SignSeek achieves state‑of‑the‑art cross‑corpus retrieval performance and zero‑shot generalisation to unseen British Sign Language, also improving isolated sign recognition and subtitle alignment.

By Sobhan Asasi, Ozge Mercanoglu Sincan, Richard Bowden
ragdiffusionfine-tuningbenchmarkssafety
More like this →
arXiv AI
Jun 19

Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models

arXiv:2605. 31393v2 Announce Type: replace-cross Abstract: Sign language translation (SLT) remains constrained by the limited availability of paired sign-video/text corpora and by the heavy-tailed vocabularies typical of real-world datasets.

By Pedro Dal Bianco, Jean Paul Nunes Reinhold, Oscar Stanchi, Facundo Quiroga, Franco Ronchetti, Ulisses Brisolara Corr\^ea
llmsfine-tuningefficiency
More like this →
arXiv Computation and Language
Sep 3

SignBind-LLM: Multi-Stage Modality Fusion for Sign Language Translation

SignBind-LLM introduces a modular framework for sign language translation that separates continuous signing, fingerspelling, and lipreading into dedicated expert streams. Each expert is pre‑trained independently on about two million pseudo‑gloss sequences, eliminating the need for manual gloss annotation. A lightweight transformer fuses the expert outputs, and a pre‑trained language model converts the fused pseudo‑glosses into fluent English, achieving state‑of‑the‑art performance on multiple benchmarks with lower training cost.

By Marshall Thomas, Edward Fish, Richard Bowden
llmsbenchmarkssafety
More like this →