{"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/imputing-out-of-vocabulary-embeddings-with","title":"Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost","arxiv_id":"2203.07860","date":"2022-03-15","proceeding":null,"authors":["Lihu Chen","Gaël Varoquaux","Fabian M. Suchanek"],"abstract":"State-of-the-art NLP systems represent inputs with word embeddings, but these are brittle when faced with Out-of-Vocabulary (OOV) words. To address this issue, we follow the principle of mimick-like models to generate vectors for unseen words, by learning the behavior of pre-trained embeddings using only the surface form of words. We present a simple contrastive learning framework, LOVE, which extends the word representation of an existing pre-trained language model (such as BERT), and makes it robust to OOV with few additional parameters. Extensive evaluations demonstrate that our lightweight model achieves similar or even better performances than prior competitors, both on original datasets and on corrupted variants. Moreover, it can be used in a plug-and-play fashion with FastText and BERT, where it significantly improves their robustness.","url_abs":"https://arxiv.org/abs/2203.07860v2","url_pdf":"https://arxiv.org/pdf/2203.07860v2.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":"imputing-out-of-vocabulary-embeddings-with","repo_url":"https://github.com/tigerchen52/love","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"},{"method_slug":"fasttext","method_name":"fastText"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2203.07860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07860"}},"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/makcedward/nlpaug","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/tigerchen52/LOVE","reach":null}],"summary":{"ran":3,"ran_violates":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"found_in_text":{"samples":4,"ran":4,"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":"dfbad4ecd9e1c2c8","entry":"PAM","repo":"tigerchen52/LOVE","repo_kind":"official","path":"model.py","file_url":"https://github.com/tigerchen52/LOVE/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dfbad4ecd9e1c2c8"}},{"code_sha256_prefix":"64c0f6a050045fc9","entry":"SAM","repo":"tigerchen52/LOVE","repo_kind":"official","path":"model.py","file_url":"https://github.com/tigerchen52/LOVE/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"64c0f6a050045fc9"}},{"code_sha256_prefix":"91a10b4dd01e7076","entry":"WordEmbeddings","repo":"makcedward/nlpaug","repo_kind":"found_in_text","path":"nlpaug/model/word_embs/word_embeddings.py","file_url":"https://github.com/makcedward/nlpaug/blob/HEAD/nlpaug/model/word_embs/word_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"91a10b4dd01e7076"}},{"code_sha256_prefix":"38b8d075d6dff46c","entry":"l1_norm","repo":"makcedward/nlpaug","repo_kind":"found_in_text","path":"nlpaug/model/word_embs/word_embeddings.py","file_url":"https://github.com/makcedward/nlpaug/blob/HEAD/nlpaug/model/word_embs/word_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38b8d075d6dff46c"}},{"code_sha256_prefix":"2cc7ef3fe9847cad","entry":"l2_norm","repo":"makcedward/nlpaug","repo_kind":"found_in_text","path":"nlpaug/model/word_embs/word_embeddings.py","file_url":"https://github.com/makcedward/nlpaug/blob/HEAD/nlpaug/model/word_embs/word_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2cc7ef3fe9847cad"}},{"code_sha256_prefix":"be631ec5276e2561","entry":"standard_norm","repo":"makcedward/nlpaug","repo_kind":"found_in_text","path":"nlpaug/model/word_embs/word_embeddings.py","file_url":"https://github.com/makcedward/nlpaug/blob/HEAD/nlpaug/model/word_embs/word_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be631ec5276e2561"}},{"code_sha256_prefix":"861e6106454d754b","entry":"Pamelaformer","repo":"tigerchen52/LOVE","repo_kind":"official","path":"model.py","file_url":"https://github.com/tigerchen52/LOVE/blob/HEAD/model.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":"861e6106454d754b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}