{"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/when-does-aggregating-multiple-skills-with","title":"When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP","arxiv_id":"2305.14007","date":"2023-05-23","proceeding":null,"authors":["Jingwei Ni","Zhijing Jin","Qian Wang","Mrinmaya Sachan","Markus Leippold"],"abstract":"Multi-task learning (MTL) aims at achieving a better model by leveraging data and knowledge from multiple tasks. However, MTL does not always work -- sometimes negative transfer occurs between tasks, especially when aggregating loosely related skills, leaving it an open question when MTL works. Previous studies show that MTL performance can be improved by algorithmic tricks. However, what tasks and skills should be included is less well explored. In this work, we conduct a case study in Financial NLP where multiple datasets exist for skills relevant to the domain, such as numeric reasoning and sentiment analysis. Due to the task difficulty and data scarcity in the Financial NLP domain, we explore when aggregating such diverse skills from multiple datasets with MTL can work. Our findings suggest that the key to MTL success lies in skill diversity, relatedness between tasks, and choice of aggregation size and shared capacity. Specifically, MTL works well when tasks are diverse but related, and when the size of the task aggregation and the shared capacity of the model are balanced to avoid overwhelming certain tasks.","url_abs":"https://arxiv.org/abs/2305.14007v1","url_pdf":"https://arxiv.org/pdf/2305.14007v1.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":"when-does-aggregating-multiple-skills-with","repo_url":"https://github.com/edisonni-hku/mtl4finance","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"when-does-aggregating-multiple-skills-with","repo_url":"https://github.com/EdisonNi-hku/when-does-mtl-work","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"open-question","task_name":"Open-Ended Question Answering"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.14007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14007"}},"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/EdisonNi-hku/MTL4Finance","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"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":"211753ba29188d4e","entry":"gelu","repo":"EdisonNi-hku/MTL4Finance","repo_kind":"official","path":"code/models/modeling_task_embeddings.py","file_url":"https://github.com/EdisonNi-hku/MTL4Finance/blob/HEAD/code/models/modeling_task_embeddings.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"code_sha256_prefix":"0c145728a35789fa","entry":"load_tf_weights_in_bert","repo":"EdisonNi-hku/MTL4Finance","repo_kind":"official","path":"code/models/modeling_task_embeddings.py","file_url":"https://github.com/EdisonNi-hku/MTL4Finance/blob/HEAD/code/models/modeling_task_embeddings.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c145728a35789fa"}},{"code_sha256_prefix":"d30d6c3098df2c42","entry":"prune_linear_layer","repo":"EdisonNi-hku/MTL4Finance","repo_kind":"official","path":"code/models/modeling_task_embeddings.py","file_url":"https://github.com/EdisonNi-hku/MTL4Finance/blob/HEAD/code/models/modeling_task_embeddings.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"code_sha256_prefix":"dc6efad1894cabda","entry":"compute_metrics_sequence_classification","repo":"EdisonNi-hku/MTL4Finance","repo_kind":"official","path":"code/compute_metrics.py","file_url":"https://github.com/EdisonNi-hku/MTL4Finance/blob/HEAD/code/compute_metrics.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":"dc6efad1894cabda"}},{"code_sha256_prefix":"6e821c762a936642","entry":"gelu","repo":"EdisonNi-hku/MTL4Finance","repo_kind":"official","path":"code/models/models_pal.py","file_url":"https://github.com/EdisonNi-hku/MTL4Finance/blob/HEAD/code/models/models_pal.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":"6e821c762a936642"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}