{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gloss-free-sign-language-translation","title":"Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining","arxiv_id":"2307.14768","date":"2023-07-27","proceeding":"ICCV 2023 1","authors":["Benjia Zhou","Zhigang Chen","Albert Clapés","Jun Wan","Yanyan Liang","Sergio Escalera","Zhen Lei","Du Zhang"],"abstract":"Sign Language Translation (SLT) is a challenging task due to its cross-domain nature, involving the translation of visual-gestural language to text. Many previous methods employ an intermediate representation, i.e., gloss sequences, to facilitate SLT, thus transforming it into a two-stage task of sign language recognition (SLR) followed by sign language translation (SLT). However, the scarcity of gloss-annotated sign language data, combined with the information bottleneck in the mid-level gloss representation, has hindered the further development of the SLT task. To address this challenge, we propose a novel Gloss-Free SLT based on Visual-Language Pretraining (GFSLT-VLP), which improves SLT by inheriting language-oriented prior knowledge from pre-trained models, without any gloss annotation assistance. Our approach involves two stages: (i) integrating Contrastive Language-Image Pre-training (CLIP) with masked self-supervised learning to create pre-tasks that bridge the semantic gap between visual and textual representations and restore masked sentences, and (ii) constructing an end-to-end architecture with an encoder-decoder-like structure that inherits the parameters of the pre-trained Visual Encoder and Text Decoder from the first stage. The seamless combination of these novel designs forms a robust sign language representation and significantly improves gloss-free sign language translation. In particular, we have achieved unprecedented improvements in terms of BLEU-4 score on the PHOENIX14T dataset (>+5) and the CSL-Daily dataset (>+3) compared to state-of-the-art gloss-free SLT methods. Furthermore, our approach also achieves competitive results on the PHOENIX14T dataset when compared with most of the gloss-based methods. Our code is available at https://github.com/zhoubenjia/GFSLT-VLP.","url_abs":"https://arxiv.org/abs/2307.14768v1","url_pdf":"https://arxiv.org/pdf/2307.14768v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gloss-free-sign-language-translation","repo_url":"https://github.com/zhoubenjia/gfslt-vlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"gloss-free-sign-language-translation","task_name":"Gloss-free Sign Language Translation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"sign-language-recognition","task_name":"Sign Language Recognition"},{"task_slug":"sign-language-translation","task_name":"Sign Language Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.14768","atlas_url":"https://app.syntology.ai/?focus=2307.14768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.14768"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhoubenjia/gfslt-vlp","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"04805aa3e54efe47","entry":"cosine_scheduler","repo":"zhoubenjia/gfslt-vlp","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zhoubenjia/gfslt-vlp/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04805aa3e54efe47"}},{"code_sha256_prefix":"dd6acfc78ad9755a","entry":"make_head","repo":"zhoubenjia/gfslt-vlp","repo_kind":"official","path":"models.py","file_url":"https://github.com/zhoubenjia/gfslt-vlp/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd6acfc78ad9755a"}},{"code_sha256_prefix":"3ecbe9910f3ee824","entry":"sampler_func","repo":"zhoubenjia/gfslt-vlp","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zhoubenjia/gfslt-vlp/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ecbe9910f3ee824"}},{"code_sha256_prefix":"b5ec86d615fa1553","entry":"tokenize_13a","repo":"zhoubenjia/gfslt-vlp","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/zhoubenjia/gfslt-vlp/blob/HEAD/metrics.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5ec86d615fa1553"}},{"code_sha256_prefix":"7863c21b724029ba","entry":"tokenize_v14_international","repo":"zhoubenjia/gfslt-vlp","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/zhoubenjia/gfslt-vlp/blob/HEAD/metrics.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7863c21b724029ba"}},{"code_sha256_prefix":"803bc06bd832fbfe","entry":"tokenize_zh","repo":"zhoubenjia/gfslt-vlp","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/zhoubenjia/gfslt-vlp/blob/HEAD/metrics.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"803bc06bd832fbfe"}},{"code_sha256_prefix":"0fee20319bd8425a","entry":"count_parameters_in_MB","repo":"zhoubenjia/gfslt-vlp","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zhoubenjia/gfslt-vlp/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0fee20319bd8425a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}