{"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/learning-high-quality-and-general-purpose","title":"Learning High-Quality and General-Purpose Phrase Representations","arxiv_id":"2401.10407","date":"2024-01-18","proceeding":null,"authors":["Lihu Chen","Gaël Varoquaux","Fabian M. Suchanek"],"abstract":"Phrase representations play an important role in data science and natural language processing, benefiting various tasks like Entity Alignment, Record Linkage, Fuzzy Joins, and Paraphrase Classification. The current state-of-the-art method involves fine-tuning pre-trained language models for phrasal embeddings using contrastive learning. However, we have identified areas for improvement. First, these pre-trained models tend to be unnecessarily complex and require to be pre-trained on a corpus with context sentences. Second, leveraging the phrase type and morphology gives phrase representations that are both more precise and more flexible. We propose an improved framework to learn phrase representations in a context-free fashion. The framework employs phrase type classification as an auxiliary task and incorporates character-level information more effectively into the phrase representation. Furthermore, we design three granularities of data augmentation to increase the diversity of training samples. Our experiments across a wide range of tasks show that our approach generates superior phrase embeddings compared to previous methods while requiring a smaller model size. [PEARL-small]: https://huggingface.co/Lihuchen/pearl_small; [PEARL-base]: https://huggingface.co/Lihuchen/pearl_base; [Code and Dataset]: https://github.com/tigerchen52/PEARL","url_abs":"https://arxiv.org/abs/2401.10407v2","url_pdf":"https://arxiv.org/pdf/2401.10407v2.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-high-quality-and-general-purpose","repo_url":"https://github.com/tigerchen52/pearl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"CC0-1.0"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"entity-alignment","task_name":"Entity Alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.10407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10407"}},"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/tigerchen52/PEARL","reach":{"status":"ok","spdx":"CC0-1.0"}}],"summary":{"ran":7},"by_repo_kind":{"official":{"samples":7,"ran":7,"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":"fe3531ab11577559","entry":"l2norm","repo":"tigerchen52/PEARL","repo_kind":"official","path":"source/loss.py","file_url":"https://github.com/tigerchen52/PEARL/blob/HEAD/source/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fe3531ab11577559"}},{"code_sha256_prefix":"8ed13dd365985641","entry":"lalign","repo":"tigerchen52/PEARL","repo_kind":"official","path":"source/loss.py","file_url":"https://github.com/tigerchen52/PEARL/blob/HEAD/source/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ed13dd365985641"}},{"code_sha256_prefix":"b6568df1b507ffa3","entry":"load_dataset","repo":"tigerchen52/PEARL","repo_kind":"official","path":"source/utils.py","file_url":"https://github.com/tigerchen52/PEARL/blob/HEAD/source/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b6568df1b507ffa3"}},{"code_sha256_prefix":"d1215a5e20ec2db3","entry":"load_phrase_con","repo":"tigerchen52/PEARL","repo_kind":"official","path":"source/utils.py","file_url":"https://github.com/tigerchen52/PEARL/blob/HEAD/source/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d1215a5e20ec2db3"}},{"code_sha256_prefix":"1662a4a4c8a115e8","entry":"load_predict_dataset","repo":"tigerchen52/PEARL","repo_kind":"official","path":"source/utils.py","file_url":"https://github.com/tigerchen52/PEARL/blob/HEAD/source/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1662a4a4c8a115e8"}},{"code_sha256_prefix":"3e20a05dc35b87aa","entry":"lunif","repo":"tigerchen52/PEARL","repo_kind":"official","path":"source/loss.py","file_url":"https://github.com/tigerchen52/PEARL/blob/HEAD/source/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e20a05dc35b87aa"}},{"code_sha256_prefix":"e53465ccba8de2d5","entry":"register","repo":"tigerchen52/PEARL","repo_kind":"official","path":"source/registry.py","file_url":"https://github.com/tigerchen52/PEARL/blob/HEAD/source/registry.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e53465ccba8de2d5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}