{"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-knowledge-enhanced-contextual","title":"Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural Language Understanding","arxiv_id":"2311.06761","date":"2023-11-12","proceeding":null,"authors":["Ruyao Xu","Taolin Zhang","Chengyu Wang","Zhongjie Duan","Cen Chen","Minghui Qiu","Dawei Cheng","Xiaofeng He","Weining Qian"],"abstract":"Knowledge-Enhanced Pre-trained Language Models (KEPLMs) improve the performance of various downstream NLP tasks by injecting knowledge facts from large-scale Knowledge Graphs (KGs). However, existing methods for pre-training KEPLMs with relational triples are difficult to be adapted to close domains due to the lack of sufficient domain graph semantics. In this paper, we propose a Knowledge-enhanced lANGuAge Representation learning framework for various clOsed dOmains (KANGAROO) via capturing the implicit graph structure among the entities. Specifically, since the entity coverage rates of closed-domain KGs can be relatively low and may exhibit the global sparsity phenomenon for knowledge injection, we consider not only the shallow relational representations of triples but also the hyperbolic embeddings of deep hierarchical entity-class structures for effective knowledge fusion.Moreover, as two closed-domain entities under the same entity-class often have locally dense neighbor subgraphs counted by max point biconnected component, we further propose a data augmentation strategy based on contrastive learning over subgraphs to construct hard negative samples of higher quality. It makes the underlying KELPMs better distinguish the semantics of these neighboring entities to further complement the global semantic sparsity. In the experiments, we evaluate KANGAROO over various knowledge-aware and general NLP tasks in both full and few-shot learning settings, outperforming various KEPLM training paradigms performance in closed-domains significantly.","url_abs":"https://arxiv.org/abs/2311.06761v1","url_pdf":"https://arxiv.org/pdf/2311.06761v1.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":[],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.06761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06761"}},"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/alibaba/EasyNLP","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":8,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"found_in_text":{"samples":10,"ran":9,"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":"a727df5fd2f5599a","entry":"check_number_comma","repo":"alibaba/EasyNLP","repo_kind":"found_in_text","path":"easynlp/modelzoo/convert_slow_tokenizer.py","file_url":"https://github.com/alibaba/EasyNLP/blob/HEAD/easynlp/modelzoo/convert_slow_tokenizer.py","link_basis":"harvester_set","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":"a727df5fd2f5599a"}},{"code_sha256_prefix":"a4475703ff58ecf9","entry":"gelu_fast","repo":"alibaba/EasyNLP","repo_kind":"found_in_text","path":"easynlp/modelzoo/activations.py","file_url":"https://github.com/alibaba/EasyNLP/blob/HEAD/easynlp/modelzoo/activations.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a4475703ff58ecf9"}},{"code_sha256_prefix":"45bb87451230d5e8","entry":"gelu_new","repo":"alibaba/EasyNLP","repo_kind":"found_in_text","path":"easynlp/modelzoo/activations.py","file_url":"https://github.com/alibaba/EasyNLP/blob/HEAD/easynlp/modelzoo/activations.py","link_basis":"harvester_set","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":"45bb87451230d5e8"}},{"code_sha256_prefix":"a3af4655933264d7","entry":"get_linear_schedule_with_warmup","repo":"alibaba/EasyNLP","repo_kind":"found_in_text","path":"easynlp/core/optimizers.py","file_url":"https://github.com/alibaba/EasyNLP/blob/HEAD/easynlp/core/optimizers.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":"a3af4655933264d7"}},{"code_sha256_prefix":"f761e4504b526823","entry":"get_model_predictor","repo":"alibaba/EasyNLP","repo_kind":"found_in_text","path":"easynlp/core/predictor.py","file_url":"https://github.com/alibaba/EasyNLP/blob/HEAD/easynlp/core/predictor.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":"f761e4504b526823"}},{"code_sha256_prefix":"899d1e2736236351","entry":"is_remote_url","repo":"alibaba/EasyNLP","repo_kind":"found_in_text","path":"easynlp/modelzoo/file_utils.py","file_url":"https://github.com/alibaba/EasyNLP/blob/HEAD/easynlp/modelzoo/file_utils.py","link_basis":"harvester_set","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":"899d1e2736236351"}},{"code_sha256_prefix":"e21f72f1a9834aef","entry":"quick_gelu","repo":"alibaba/EasyNLP","repo_kind":"found_in_text","path":"easynlp/modelzoo/activations.py","file_url":"https://github.com/alibaba/EasyNLP/blob/HEAD/easynlp/modelzoo/activations.py","link_basis":"harvester_set","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":"e21f72f1a9834aef"}},{"code_sha256_prefix":"108f25573123b007","entry":"replace_return_docstrings","repo":"alibaba/EasyNLP","repo_kind":"found_in_text","path":"easynlp/modelzoo/file_utils.py","file_url":"https://github.com/alibaba/EasyNLP/blob/HEAD/easynlp/modelzoo/file_utils.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":"108f25573123b007"}},{"code_sha256_prefix":"56ffa4b32330ceab","entry":"torch_only_method","repo":"alibaba/EasyNLP","repo_kind":"found_in_text","path":"easynlp/modelzoo/file_utils.py","file_url":"https://github.com/alibaba/EasyNLP/blob/HEAD/easynlp/modelzoo/file_utils.py","link_basis":"harvester_set","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":"56ffa4b32330ceab"}},{"code_sha256_prefix":"9339ca51cea1f469","entry":"convert_slow_tokenizer","repo":"alibaba/EasyNLP","repo_kind":"found_in_text","path":"easynlp/modelzoo/convert_slow_tokenizer.py","file_url":"https://github.com/alibaba/EasyNLP/blob/HEAD/easynlp/modelzoo/convert_slow_tokenizer.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":"9339ca51cea1f469"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}