{"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/nugget-neural-agglomerative-embeddings-of","title":"Nugget: Neural Agglomerative Embeddings of Text","arxiv_id":"2310.01732","date":"2023-10-03","proceeding":null,"authors":["Guanghui Qin","Benjamin Van Durme"],"abstract":"Embedding text sequences is a widespread requirement in modern language understanding. Existing approaches focus largely on constant-size representations. This is problematic, as the amount of information contained in text often varies with the length of the input. We propose a solution called Nugget, which encodes language into a representation based on a dynamically selected subset of input tokens. These nuggets are learned through tasks like autoencoding and machine translation, and intuitively segment language into meaningful units. We demonstrate Nugget outperforms related approaches in tasks involving semantic comparison. Finally, we illustrate these compact units allow for expanding the contextual window of a language model (LM), suggesting new future LMs that can condition on significantly larger amounts of content.","url_abs":"https://arxiv.org/abs/2310.01732v1","url_pdf":"https://arxiv.org/pdf/2310.01732v1.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":"nugget-neural-agglomerative-embeddings-of","repo_url":"https://github.com/steventan0110/star","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.01732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01732"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/steventan0110/star","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":3,"unverified":2},"by_repo_kind":{"listed":{"samples":5,"ran":3,"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":"a97ee8a3a9639b95","entry":"cast_tuple","repo":"steventan0110/star","repo_kind":"listed","path":"src/models/utils.py","file_url":"https://github.com/steventan0110/star/blob/HEAD/src/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a97ee8a3a9639b95"}},{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":"steventan0110/star","repo_kind":"listed","path":"src/models/utils.py","file_url":"https://github.com/steventan0110/star/blob/HEAD/src/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"steventan0110/star","repo_kind":"listed","path":"src/models/utils.py","file_url":"https://github.com/steventan0110/star/blob/HEAD/src/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"f1edcca98ecd3016","entry":"chunk_data","repo":"steventan0110/star","repo_kind":"listed","path":"src/data_utils/preprocess_librispeech.py","file_url":"https://github.com/steventan0110/star/blob/HEAD/src/data_utils/preprocess_librispeech.py","link_basis":"harvester_set","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":"f1edcca98ecd3016"}},{"code_sha256_prefix":"025ba97a4016c2ea","entry":"match_target_amplitude","repo":"steventan0110/star","repo_kind":"listed","path":"src/data_utils/preprocess_librispeech.py","file_url":"https://github.com/steventan0110/star/blob/HEAD/src/data_utils/preprocess_librispeech.py","link_basis":"harvester_set","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":"025ba97a4016c2ea"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}