Entity Linking via Explicit Mention-Mention Coreference Modeling
Learning representations of entity mentions is a core component of modern entity linking systems for both candidate generation and making linking predictions. In this paper, we present and empirically analyze a novel training approach for learning mention and entity representations that is based on building minimum spanning arborescences (i.e., directed spanning trees) over mentions and entities across documents to explicitly model mention coreference relationships. We demonstrate the efficacy of our approach by showing significant improvements in both candidate generation recall and linking accuracy on the Zero-Shot Entity Linking dataset and MedMentions, the largest publicly available biomedical dataset. In addition, we show that our improvements in candidate generation yield higher quality re-ranking models downstream, setting a new SOTA result in linking accuracy on MedMentions. Finally, we demonstrate that our improved mention representations are also effective for the discovery of new entities via cross-document coreference.
Code (1)
Tasks
Entity LinkingRe-RankingSimilar Papers 제목 키워드 기반
Entity Linking via Explicit Mention-Mention Coreference Modeling
Learning representations of entity mentions is a core component of modern entity linking systems for both candidate generation and making linking predictions. In this paper, we present and empirically analyze a novel tra…
Entity LinkingRe-RankingThey Exist! Introducing Plural Mentions to Coreference Resolution and Entity Linking
This paper analyzes arguably the most challenging yet under-explored aspect of resolution tasks such as coreference resolution and entity linking, that is the resolution of plural mentions. Unlike singular mentions each …
coreference-resolutionCoreference ResolutionEntity LinkingMachine Translation+2Towards Consistent Document-level Entity Linking: Joint Models for Entity Linking and Coreference Resolution
We consider the task of document-level entity linking (EL), where it is important to make consistent decisions for entity mentions over the full document jointly. We aim to leverage explicit "connections" among mentions …
coreference-resolutionCoreference ResolutionEntity LinkingStructured PredictionRobust Coreference Resolution and Entity Linking on Dialogues: Character Identification on TV Show Transcripts
This paper presents a novel approach to character identification, that is an entity linking task that maps mentions to characters in dialogues from TV show transcripts. We first augment and correct several cases of annot…
coreference-resolutionCoreference ResolutionEntity LinkingEntity Resolution+1Joint Coreference Resolution and Character Linking for Multiparty Conversation
Character linking, the task of linking mentioned people in conversations to the real world, is crucial for understanding the conversations. For the efficiency of communication, humans often choose to use pronouns (e.g., …
coreference-resolutionCoreference ResolutionEntity Linking