{"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/unbalanced-optimal-transport-for-unbalanced","title":"Unbalanced Optimal Transport for Unbalanced Word Alignment","arxiv_id":"2306.04116","date":"2023-06-07","proceeding":null,"authors":["Yuki Arase","Han Bao","Sho Yokoi"],"abstract":"Monolingual word alignment is crucial to model semantic interactions between sentences. In particular, null alignment, a phenomenon in which words have no corresponding counterparts, is pervasive and critical in handling semantically divergent sentences. Identification of null alignment is useful on its own to reason about the semantic similarity of sentences by indicating there exists information inequality. To achieve unbalanced word alignment that values both alignment and null alignment, this study shows that the family of optimal transport (OT), i.e., balanced, partial, and unbalanced OT, are natural and powerful approaches even without tailor-made techniques. Our extensive experiments covering unsupervised and supervised settings indicate that our generic OT-based alignment methods are competitive against the state-of-the-arts specially designed for word alignment, remarkably on challenging datasets with high null alignment frequencies.","url_abs":"https://arxiv.org/abs/2306.04116v1","url_pdf":"https://arxiv.org/pdf/2306.04116v1.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":"unbalanced-optimal-transport-for-unbalanced","repo_url":"https://github.com/yukiar/otalign","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"word-alignment","task_name":"Word Alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.04116","atlas_url":"https://app.syntology.ai/?focus=2306.04116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04116"}},"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":"deterministic:regex_extraction","url":"https://github.com/yukiar/OTAlign","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"samples":14,"ran":0,"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":"a24d62116715875f","entry":"BERTScore_Alignment","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/baseline.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/baseline.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":"a24d62116715875f"}},{"code_sha256_prefix":"66c04783570df92e","entry":"alignment_collate","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/util.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":"66c04783570df92e"}},{"code_sha256_prefix":"634f8a5bd7f32333","entry":"apply_distortion","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/model_parts.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/model_parts.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":"634f8a5bd7f32333"}},{"code_sha256_prefix":"87ca66890dc85cc7","entry":"entropic_partial_wasserstein","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/my_pot.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/my_pot.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":"87ca66890dc85cc7"}},{"code_sha256_prefix":"68c9ecf45685f549","entry":"eval_null_alignments","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/unsupervised_alignment.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/unsupervised_alignment.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":"68c9ecf45685f549"}},{"code_sha256_prefix":"75743674e5649573","entry":"evaluate","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/unsupervised_alignment.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/unsupervised_alignment.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":"75743674e5649573"}},{"code_sha256_prefix":"df7c9ece1e6d1859","entry":"evaluate_total_score","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/unsupervised_alignment.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/unsupervised_alignment.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":"df7c9ece1e6d1859"}},{"code_sha256_prefix":"1d47d9d817fa012b","entry":"load_Edinburgh_corpus","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/preprocess/edinburgh.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/preprocess/edinburgh.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":"1d47d9d817fa012b"}},{"code_sha256_prefix":"d724980d92a0a2fa","entry":"load_MSR_RTE_corpus","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/preprocess/msr_rte.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/preprocess/msr_rte.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":"d724980d92a0a2fa"}},{"code_sha256_prefix":"71d53f8be599aefb","entry":"load_annotation","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/preprocess/edinburgh.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/preprocess/edinburgh.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":"71d53f8be599aefb"}},{"code_sha256_prefix":"6988d5e2da254801","entry":"read_Word_Alignment_Dataset","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/util.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":"6988d5e2da254801"}},{"code_sha256_prefix":"d51893d58237db4c","entry":"select_from_list","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/preprocess/edinburgh.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/preprocess/edinburgh.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":"d51893d58237db4c"}},{"code_sha256_prefix":"3cd9511aa0c35e35","entry":"send_batch_to_gpu","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/util.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":"3cd9511aa0c35e35"}},{"code_sha256_prefix":"7dc737c4d7d6bb93","entry":"sinkhorn_knopp_unbalanced","repo":"yukiar/OTAlign","repo_kind":"official","path":"src/my_pot.py","file_url":"https://github.com/yukiar/OTAlign/blob/HEAD/src/my_pot.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":"7dc737c4d7d6bb93"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}