{"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/mlmlm-link-prediction-with-mean-likelihood","title":"MLMLM: Link Prediction with Mean Likelihood Masked Language Model","arxiv_id":"2009.07058","date":"2020-09-15","proceeding":"Findings (ACL) 2021 8","authors":["Louis Clouatre","Philippe Trempe","Amal Zouaq","Sarath Chandar"],"abstract":"Knowledge Bases (KBs) are easy to query, verifiable, and interpretable. They however scale with man-hours and high-quality data. Masked Language Models (MLMs), such as BERT, scale with computing power as well as unstructured raw text data. The knowledge contained within those models is however not directly interpretable. We propose to perform link prediction with MLMs to address both the KBs scalability issues and the MLMs interpretability issues. To do that we introduce MLMLM, Mean Likelihood Masked Language Model, an approach comparing the mean likelihood of generating the different entities to perform link prediction in a tractable manner. We obtain State of the Art (SotA) results on the WN18RR dataset and the best non-entity-embedding based results on the FB15k-237 dataset. We also obtain convincing results on link prediction on previously unseen entities, making MLMLM a suitable approach to introducing new entities to a KB.","url_abs":"https://arxiv.org/abs/2009.07058v1","url_pdf":"https://arxiv.org/pdf/2009.07058v1.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":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"}],"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":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"interpretability","method_name":"Interpretability"},{"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-fb15k-237","task":"Link Prediction","dataset":"FB15k-237","model":"MLMLM","rank_in_archive_order":53,"of":75,"metrics":{"Hits@1":"0.1871","Hits@10":"0.4026","Hits@3":"0.2820","MR":"411","MRR":"0.2591"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18rr","task":"Link Prediction","dataset":"WN18RR","model":"MLMLM","rank_in_archive_order":14,"of":75,"metrics":{"Hits@1":"0.4391","Hits@10":"0.611","Hits@3":"0.5418","MR":"1603","MRR":"0.5017"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.07058","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}