{"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/semi-supervised-spoken-language","title":"Semi-Supervised Spoken Language Glossification","arxiv_id":"2406.08173","date":"2024-06-12","proceeding":null,"authors":["Huijie Yao","Wengang Zhou","Hao Zhou","Houqiang Li"],"abstract":"Spoken language glossification (SLG) aims to translate the spoken language text into the sign language gloss, i.e., a written record of sign language. In this work, we present a framework named $S$emi-$S$upervised $S$poken $L$anguage $G$lossification ($S^3$LG) for SLG. To tackle the bottleneck of limited parallel data in SLG, our $S^3$LG incorporates large-scale monolingual spoken language text into SLG training. The proposed framework follows the self-training structure that iteratively annotates and learns from pseudo labels. Considering the lexical similarity and syntactic difference between sign language and spoken language, our $S^3$LG adopts both the rule-based heuristic and model-based approach for auto-annotation. During training, we randomly mix these complementary synthetic datasets and mark their differences with a special token. As the synthetic data may be less quality, the $S^3$LG further leverages consistency regularization to reduce the negative impact of noise in the synthetic data. Extensive experiments are conducted on public benchmarks to demonstrate the effectiveness of the $S^3$LG. Our code is available at \\url{https://github.com/yaohj11/S3LG}.","url_abs":"https://arxiv.org/abs/2406.08173v1","url_pdf":"https://arxiv.org/pdf/2406.08173v1.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":"semi-supervised-spoken-language","repo_url":"https://github.com/yaohj11/s3lg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.08173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08173"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"deterministic:regex_extraction","url":"https://github.com/yaohj11/S3LG","reach":null}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":"4c756637a87da821","entry":"MultiHeadedAttention","repo":"yaohj11/S3LG","repo_kind":"official","path":"model/seq2seq/encoder.py","file_url":"https://github.com/yaohj11/S3LG/blob/HEAD/model/seq2seq/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c756637a87da821"}},{"code_sha256_prefix":"be8119c6581d2fb1","entry":"PositionalEncoding","repo":"yaohj11/S3LG","repo_kind":"official","path":"model/seq2seq/encoder.py","file_url":"https://github.com/yaohj11/S3LG/blob/HEAD/model/seq2seq/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be8119c6581d2fb1"}},{"code_sha256_prefix":"40933e301bb2d3be","entry":"PositionwiseFeedForward","repo":"yaohj11/S3LG","repo_kind":"official","path":"model/seq2seq/encoder.py","file_url":"https://github.com/yaohj11/S3LG/blob/HEAD/model/seq2seq/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40933e301bb2d3be"}},{"code_sha256_prefix":"63d68ab12286b7a4","entry":"TransformerEncoderLayer","repo":"yaohj11/S3LG","repo_kind":"official","path":"model/seq2seq/encoder.py","file_url":"https://github.com/yaohj11/S3LG/blob/HEAD/model/seq2seq/encoder.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":"63d68ab12286b7a4"}},{"code_sha256_prefix":"d672612bcc1e12f8","entry":"EncoderTransformer","repo":"yaohj11/S3LG","repo_kind":"official","path":"model/seq2seq/encoder.py","file_url":"https://github.com/yaohj11/S3LG/blob/HEAD/model/seq2seq/encoder.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":"d672612bcc1e12f8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}