{"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/language-models-as-hierarchy-encoders","title":"Language Models as Hierarchy Encoders","arxiv_id":"2401.11374","date":"2024-01-21","proceeding":null,"authors":["Yuan He","Zhangdie Yuan","Jiaoyan Chen","Ian Horrocks"],"abstract":"Interpreting hierarchical structures latent in language is a key limitation of current language models (LMs). While previous research has implicitly leveraged these hierarchies to enhance LMs, approaches for their explicit encoding are yet to be explored. To address this, we introduce a novel approach to re-train transformer encoder-based LMs as Hierarchy Transformer encoders (HiTs), harnessing the expansive nature of hyperbolic space. Our method situates the output embedding space of pre-trained LMs within a Poincar\\'e ball with a curvature that adapts to the embedding dimension, followed by training on hyperbolic clustering and centripetal losses. These losses are designed to effectively cluster related entities (input as texts) and organise them hierarchically. We evaluate HiTs against pre-trained LMs, standard fine-tuned LMs, and several hyperbolic embedding baselines, focusing on their capabilities in simulating transitive inference, predicting subsumptions, and transferring knowledge across hierarchies. The results demonstrate that HiTs consistently outperform all baselines in these tasks, underscoring the effectiveness and transferability of our re-trained hierarchy encoders.","url_abs":"https://arxiv.org/abs/2401.11374v4","url_pdf":"https://arxiv.org/pdf/2401.11374v4.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":"language-models-as-hierarchy-encoders","repo_url":"https://github.com/krr-oxford/hierarchytransformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.11374","atlas_url":"https://app.syntology.ai/?focus=2401.11374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11374"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/krr-oxford/hierarchytransformers","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"unverified":2},"by_repo_kind":{"official":{"samples":9,"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":"2f26d450134ce2b3","entry":"accurarcy","repo":"krr-oxford/hierarchytransformers","repo_kind":"official","path":"src/hierarchy_transformers/evaluation/metrics.py","file_url":"https://github.com/krr-oxford/hierarchytransformers/blob/HEAD/src/hierarchy_transformers/evaluation/metrics.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":"2f26d450134ce2b3"}},{"code_sha256_prefix":"63f0f58b5b3ba6d0","entry":"accurarcy_on_negatives","repo":"krr-oxford/hierarchytransformers","repo_kind":"official","path":"src/hierarchy_transformers/evaluation/metrics.py","file_url":"https://github.com/krr-oxford/hierarchytransformers/blob/HEAD/src/hierarchy_transformers/evaluation/metrics.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":"63f0f58b5b3ba6d0"}},{"code_sha256_prefix":"0d16bd94d30d0a7c","entry":"are_models_equal","repo":"krr-oxford/hierarchytransformers","repo_kind":"official","path":"src/hierarchy_transformers/utils.py","file_url":"https://github.com/krr-oxford/hierarchytransformers/blob/HEAD/src/hierarchy_transformers/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":"0d16bd94d30d0a7c"}},{"code_sha256_prefix":"018eaf80bea2d0e0","entry":"f1_score","repo":"krr-oxford/hierarchytransformers","repo_kind":"official","path":"src/hierarchy_transformers/evaluation/metrics.py","file_url":"https://github.com/krr-oxford/hierarchytransformers/blob/HEAD/src/hierarchy_transformers/evaluation/metrics.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":"018eaf80bea2d0e0"}},{"code_sha256_prefix":"db8b64cd4b0ab024","entry":"format_citation","repo":"krr-oxford/hierarchytransformers","repo_kind":"official","path":"src/hierarchy_transformers/utils.py","file_url":"https://github.com/krr-oxford/hierarchytransformers/blob/HEAD/src/hierarchy_transformers/utils.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":"db8b64cd4b0ab024"}},{"code_sha256_prefix":"d6008ccf36dffe15","entry":"get_torch_device","repo":"krr-oxford/hierarchytransformers","repo_kind":"official","path":"src/hierarchy_transformers/utils.py","file_url":"https://github.com/krr-oxford/hierarchytransformers/blob/HEAD/src/hierarchy_transformers/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":"d6008ccf36dffe15"}},{"code_sha256_prefix":"d0810caf1c11dd2b","entry":"zenodo_example_to_triplets","repo":"krr-oxford/hierarchytransformers","repo_kind":"official","path":"src/hierarchy_transformers/datasets/load.py","file_url":"https://github.com/krr-oxford/hierarchytransformers/blob/HEAD/src/hierarchy_transformers/datasets/load.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":"d0810caf1c11dd2b"}},{"code_sha256_prefix":"67ff2eddd3f6c090","entry":"load_hf_dataset","repo":"krr-oxford/hierarchytransformers","repo_kind":"official","path":"src/hierarchy_transformers/datasets/load.py","file_url":"https://github.com/krr-oxford/hierarchytransformers/blob/HEAD/src/hierarchy_transformers/datasets/load.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":"67ff2eddd3f6c090"}},{"code_sha256_prefix":"f0c1382e2d02e79c","entry":"load_zenodo_dataset","repo":"krr-oxford/hierarchytransformers","repo_kind":"official","path":"src/hierarchy_transformers/datasets/load.py","file_url":"https://github.com/krr-oxford/hierarchytransformers/blob/HEAD/src/hierarchy_transformers/datasets/load.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":"f0c1382e2d02e79c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}