{"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/delta-an-online-document-level-translation","title":"DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory","arxiv_id":"2410.08143","date":"2024-10-10","proceeding":null,"authors":["Yutong Wang","Jiali Zeng","Xuebo Liu","Derek F. Wong","Fandong Meng","Jie zhou","Min Zhang"],"abstract":"Large language models (LLMs) have achieved reasonable quality improvements in machine translation (MT). However, most current research on MT-LLMs still faces significant challenges in maintaining translation consistency and accuracy when processing entire documents. In this paper, we introduce DelTA, a Document-levEL Translation Agent designed to overcome these limitations. DelTA features a multi-level memory structure that stores information across various granularities and spans, including Proper Noun Records, Bilingual Summary, Long-Term Memory, and Short-Term Memory, which are continuously retrieved and updated by auxiliary LLM-based components. Experimental results indicate that DelTA significantly outperforms strong baselines in terms of translation consistency and quality across four open/closed-source LLMs and two representative document translation datasets, achieving an increase in consistency scores by up to 4.58 percentage points and in COMET scores by up to 3.16 points on average. DelTA employs a sentence-by-sentence translation strategy, ensuring no sentence omissions and offering a memory-efficient solution compared to the mainstream method. Furthermore, DelTA improves pronoun translation accuracy, and the summary component of the agent also shows promise as a tool for query-based summarization tasks. We release our code and data at https://github.com/YutongWang1216/DocMTAgent.","url_abs":"https://arxiv.org/abs/2410.08143v1","url_pdf":"https://arxiv.org/pdf/2410.08143v1.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":"delta-an-online-document-level-translation","repo_url":"https://github.com/yutongwang1216/docmtagent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"document-translation","task_name":"Document Translation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"proper-noun","task_name":"Proper Noun"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.08143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08143"}},"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/YutongWang1216/DocMTAgent","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/longyuewangdcu/GuoFeng-Webnovel","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yutongwang1216/docmtagent","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":5,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"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":"45a5b454d1aff7f6","entry":"get_unique_filename","repo":"yutongwang1216/docmtagent","repo_kind":"official","path":"demo/DelTA.py","file_url":"https://github.com/yutongwang1216/docmtagent/blob/HEAD/demo/DelTA.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"45a5b454d1aff7f6"}},{"code_sha256_prefix":"86db79fcd13b3e91","entry":"E2V","repo":"YutongWang1216/DocMTAgent","repo_kind":"official","path":"eval_consistency/eval_probability_en_to.py","file_url":"https://github.com/YutongWang1216/DocMTAgent/blob/HEAD/eval_consistency/eval_probability_en_to.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86db79fcd13b3e91"}},{"code_sha256_prefix":"729c43fab0e64a4e","entry":"cosine_similarity","repo":"yutongwang1216/docmtagent","repo_kind":"official","path":"infer/infer_gpt.py","file_url":"https://github.com/yutongwang1216/docmtagent/blob/HEAD/infer/infer_gpt.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"729c43fab0e64a4e"}},{"code_sha256_prefix":"fab7e1481b18f52d","entry":"cosine_similarity","repo":"YutongWang1216/DocMTAgent","repo_kind":"official","path":"infer/infer_qwen.py","file_url":"https://github.com/YutongWang1216/DocMTAgent/blob/HEAD/infer/infer_qwen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fab7e1481b18f52d"}},{"code_sha256_prefix":"f7b4c2775b6c6067","entry":"extract_progress_info","repo":"yutongwang1216/docmtagent","repo_kind":"official","path":"demo/DelTA.py","file_url":"https://github.com/yutongwang1216/docmtagent/blob/HEAD/demo/DelTA.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f7b4c2775b6c6067"}},{"code_sha256_prefix":"7a0ee94ef67550b6","entry":"find_max_idx","repo":"YutongWang1216/DocMTAgent","repo_kind":"official","path":"eval_consistency/eval_probability_en_to.py","file_url":"https://github.com/YutongWang1216/DocMTAgent/blob/HEAD/eval_consistency/eval_probability_en_to.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7a0ee94ef67550b6"}},{"code_sha256_prefix":"62e18537a0996069","entry":"max_prob_hyp_idx","repo":"YutongWang1216/DocMTAgent","repo_kind":"official","path":"eval_consistency/eval_probability_en_to.py","file_url":"https://github.com/YutongWang1216/DocMTAgent/blob/HEAD/eval_consistency/eval_probability_en_to.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"62e18537a0996069"}},{"code_sha256_prefix":"42592327bad2077f","entry":"sentence_tokenize","repo":"YutongWang1216/DocMTAgent","repo_kind":"official","path":"eval_consistency/src_tgt_tokenize_en_to.py","file_url":"https://github.com/YutongWang1216/DocMTAgent/blob/HEAD/eval_consistency/src_tgt_tokenize_en_to.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42592327bad2077f"}},{"code_sha256_prefix":"78259d0638edb74b","entry":"init_memory","repo":"YutongWang1216/DocMTAgent","repo_kind":"official","path":"infer/infer_qwen.py","file_url":"https://github.com/YutongWang1216/DocMTAgent/blob/HEAD/infer/infer_qwen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"78259d0638edb74b"}},{"code_sha256_prefix":"1d0626abcdce06be","entry":"invoke_chat","repo":"YutongWang1216/DocMTAgent","repo_kind":"official","path":"infer/infer_qwen.py","file_url":"https://github.com/YutongWang1216/DocMTAgent/blob/HEAD/infer/infer_qwen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d0626abcdce06be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}