{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learning-span-level-interactions-for-aspect","title":"Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction","arxiv_id":"2107.12214","date":"2021-07-26","proceeding":"ACL 2021 5","authors":["Lu Xu","Yew Ken Chia","Lidong Bing"],"abstract":"Aspect Sentiment Triplet Extraction (ASTE) is the most recent subtask of ABSA which outputs triplets of an aspect target, its associated sentiment, and the corresponding opinion term. Recent models perform the triplet extraction in an end-to-end manner but heavily rely on the interactions between each target word and opinion word. Thereby, they cannot perform well on targets and opinions which contain multiple words. Our proposed span-level approach explicitly considers the interaction between the whole spans of targets and opinions when predicting their sentiment relation. Thus, it can make predictions with the semantics of whole spans, ensuring better sentiment consistency. To ease the high computational cost caused by span enumeration, we propose a dual-channel span pruning strategy by incorporating supervision from the Aspect Term Extraction (ATE) and Opinion Term Extraction (OTE) tasks. This strategy not only improves computational efficiency but also distinguishes the opinion and target spans more properly. Our framework simultaneously achieves strong performance for the ASTE as well as ATE and OTE tasks. In particular, our analysis shows that our span-level approach achieves more significant improvements over the baselines on triplets with multi-word targets or opinions.","url_abs":"https://arxiv.org/abs/2107.12214v1","url_pdf":"https://arxiv.org/pdf/2107.12214v1.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":"learning-span-level-interactions-for-aspect","repo_url":"https://github.com/chiayewken/Span-ASTE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"learning-span-level-interactions-for-aspect","repo_url":"https://github.com/wireless911/span-aste","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"aspect-sentiment-triplet-extraction","task_name":"Aspect Sentiment Triplet Extraction"},{"task_slug":"aspect-based-sentiment-analysis","task_name":"Aspect-Based Sentiment Analysis (ABSA)"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"term-extraction","task_name":"Term Extraction"},{"task_slug":null,"task_name":"Triplet"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/aspect-sentiment-triplet-extraction-on-aste","task":"Aspect Sentiment Triplet Extraction","dataset":"ASTE-Data-V2","model":"SPAN-ASTE","rank_in_archive_order":6,"of":11,"metrics":{"F1":"71.85"},"uses_additional_data":false},{"leaderboard":"/sota/aspect-sentiment-triplet-extraction-on-1","task":"Aspect Sentiment Triplet Extraction","dataset":"MuseASTE","model":"Span-ASTE","rank_in_archive_order":3,"of":4,"metrics":{"F1":"0.241"},"uses_additional_data":false},{"leaderboard":"/sota/aspect-based-sentiment-analysis-absa-on-aste","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"ASTE","model":"Span-ASTE","rank_in_archive_order":10,"of":13,"metrics":{"F1 (L14)":"59.38","F1 (R15)":"63.27","F1 (R16)":"70.26","F1(R14)":"71.85"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.12214","atlas_url":"https://app.syntology.ai/?focus=2107.12214","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2107.12214"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2107.12214\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2107.12214"},"call":"get_concepts_for_paper(arxiv_id=\"2107.12214\")"}],"by_repo":[{"repo":"chiayewken/Span-ASTE","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"wireless911/span-aste","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4b13494a9ce31f884f353fb90490811dabd98f31511a1d46e20ca2f600cce773","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}