Topic
Weak entity
About: Weak entity is a research topic. Over the lifetime, 584 publications have been published within this topic receiving 12928 citations.
Papers published on a yearly basis
Papers
24 Jul 2011
TL;DR: Experimental results show that the proposed graph-based collective EL method can achieve significant performance improvement over the traditional EL methods, and the purely collective nature of the inference algorithm, in which evidence for related EL decisions can be reinforced into high-probability decisions.
Abstract: Entity Linking (EL) is the task of linking name mentions in Web text with their referent entities in a knowledge base. Traditional EL methods usually link name mentions in a document by assuming them to be independent. However, there is often additional interdependence between different EL decisions, i.e., the entities in the same document should be semantically related to each other. In these cases, Collective Entity Linking, in which the name mentions in the same document are linked jointly by exploiting the interdependence between them, can improve the entity linking accuracy. This paper proposes a graph-based collective EL method, which can model and exploit the global interdependence between different EL decisions. Specifically, we first propose a graph-based representation, called Referent Graph, which can model the global interdependence between different EL decisions. Then we propose a collective inference algorithm, which can jointly infer the referent entities of all name mentions by exploiting the interdependence captured in Referent Graph. The key benefit of our method comes from: 1) The global interdependence model of EL decisions; 2) The purely collective nature of the inference algorithm, in which evidence for related EL decisions can be reinforced into high-probability decisions. Experimental results show that our method can achieve significant performance improvement over the traditional EL methods.
451 citations
Patent•
14 Feb 2005TL;DR: In this paper, the authors present a world model made up of interrelated entity models, each of which corresponds to an entity in the real world, such as a person, place, business, other tangible thing, community, event, or thought.
Abstract: Systems and methods for information retrieval and communication employ a world model. The world model is made up of interrelated entity models, each of which corresponds to an entity in the real world, such as a person, place, business, other tangible thing, community, event, or thought. Each entity model provides a communication channel via which a user can contact a real-world person responsible for that entity model. Entity models also provide feedback information, enabling users to easily share their experiences and opinions of the corresponding real-world entity.
362 citations
Patent•
4 Feb 2003
TL;DR: In this paper, a method for identifying an entity from a plurality of entity references, each entity reference being linked with a separate ghost entity, is provided, which comprises the steps of comparing an entity reference of a first ghost entity with an entity relation of a second ghost entity to determine a match probability between the entity reference between the first ghost entities and the entity references of the second ghost entities.
Abstract: Disclosed herein are various exemplary systems and methods for linking entity references to entities and identifying associations between entities. In particular, a method for identifying an entity from a plurality of entity references, each entity reference being linked with a separate ghost entity, is provided. The method comprises the steps of comparing an entity reference of a first ghost entity with an entity reference of a second ghost entity to determine a match probability between the entity reference of the first ghost entity and the entity reference of the second ghost entity, linking the entity reference of the first ghost entity additionally with the second ghost entity and the entity reference of the second ghost entity additionally with the first ghost entity when the match probability is greater than or equal to a match threshold and repeating the steps of comparing and linking for one or more ghost entity pairings possible from the ghost entities. The method further comprises determining, for one or more entity references linked to a ghost entity, a score for the entity reference based at least in part on a match probability between the entity reference and a value representing the one or more entity references linked to the ghost entity and identifying the ghost entity as an actual entity based at least in part on one or more scores for the one or more entity references linked to the ghost entity.
359 citations
1 Jan 2013
TL;DR: This work discusses the key challenges present in this task and presents a high-performing system that links entities using max-margin ranking and summarizes recent work in this area and describes several open research problems.
Abstract: In the menagerie of tasks for information extraction, entity linking is a new beast that has drawn a lot of attention from NLP practitioners and researchers recently. Entity Linking, also referred to as record linkage or entity resolution, involves aligning a textual mention of a named-entity to an appropriate entry in a knowledge base, which may or may not contain the entity. This has manifold applications ranging from linking patient health records to maintaining personal credit files, prevention of identity crimes, and supporting law enforcement. We discuss the key challenges present in this task and we present a high-performing system that links entities using max-margin ranking. We also summarize recent work in this area and describe several open research problems.
238 citations
Proceedings Article•
25 Jul 2015TL;DR: A new neural network approach is presented that takes consideration of the semantic representations of mention, context and entity, encodes them in continuous vector space and effectively leverages them for entity disambiguation.
Abstract: Given a query consisting of a mention (name string) and a background document, entity disambiguation calls for linking the mention to an entity from reference knowledge base like Wikipedia. Existing studies typically use hand-crafted features to represent mention, context and entity, which is laborintensive and weak to discover explanatory factors of data. In this paper, we address this problem by presenting a new neural network approach. The model takes consideration of the semantic representations of mention, context and entity, encodes them in continuous vector space and effectively leverages them for entity disambiguation. Specifically, we model variable-sized contexts with convolutional neural network, and embed the positions of context words to factor in the distance between context word and mention. Furthermore, we employ neural tensor network to model the semantic interactions between context and mention. We conduct experiments for entity disambiguation on two benchmark datasets from TAC-KBP 2009 and 2010. Experimental results show that our method yields state-of-the-art performances on both datasets.
224 citations
Related Topics (5)
Performance Metrics
| Year | Papers |
|---|---|
| 2021 | 1 |
| 2018 | 3 |
| 2017 | 25 |
| 2016 | 46 |
| 2015 | 53 |
| 2014 | 55 |