A Large-Scale Exploration of Effective Global Features for a Joint Entity Detection and Tracking Model

By Hal Daumé Iii, Daniel Marcu. 2005

107 citations recorded by the source corpus.

Entity detection and tracking (EDT) is the task of identifying textual mentions of real-world entities in documents, extending the named entity detection and coreference resolution task by considering mentions other than names (pronouns, definite descriptions, etc.). Like NE tagging and coreference resolution, most solutions to the EDT task separate out the mention detection aspect from the coreference aspect. By doing so, these solutions are limited to using only local features for learning. In contrast, by modeling both aspects of the EDT task simultaneously, we are able to learn using highly complex, non-local features. We develop a new joint EDT model and explore the utility of many features, demonstrating their effectiveness on this task.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Toward Gender-Inclusive Coreference Resolution (2019, background): “The result is that although we do not know exactly what decisions are baked in to all systems, the vast majority in our study (including two papers by one of the authors (Daumé and Marcu, 2005; Orita et al., 2015)) come”
Search-based structured prediction (2009, neutral): “In many applications, such as entity detection and tracking [15], this is not true.”
Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules (2013, unknown): “Finally, recent work has shown the importance of performing coreference resolution jointly for all mentions in a document (McCallum and Wellner 2004; Daum´e III and Marcu 2005; Denis and Baldridge 2007; Haghighi and Klein 2007; Culotta et al. 2007; Poon and Domingos 2008; Haghighi and Klein 2010;…”
Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task (2011, methodology): “…new sieves that exploit semantics from WordNet, Wikipedia infoboxes, and Freebase records, drawing on previous coreference work using these databases (Ng & Cardie, 2002; Daum´e & Marcu, 2005; Ponzetto & Strube, 2006; Ng, 2007; Yang & Su, 2007; Bengston & Roth, 2008; Huang et al., 2009; inter alia).”
A Joint Model for Entity Analysis: Coreference, Typing, and Linking (2014, methodology): “…slower than the union of the individual 2 Our model could potentially be extended to handle relation extraction or mention detection, which has also been addressed in past joint modeling efforts (Daum´e and Marcu, 2005; Li and Ji, 2014), but that is outside the scope of the current work. models.”
Improving Coreference Resolution by Learning Entity-Level Distributed Representations (2016, methodology): “Learning-to-search style algorithms have been employed to train coreference resolvers on trajectories of decisions similar to those that would be seen at test-time by Daumé et al. (2005), Ma et al. (2014), and Clark and Manning (2015).”
Coreference Resolution with World Knowledge (2011, unknown): “World knowledge is extracted primarily from three data sources, online encyclo-pedia (e.g., Ponzetto and Strube (2006), Uryupina et al. (2011)), unannotated data (e.g., Daum´e III and Marcu (2005), Ng (2007)), and coreference-annotated data (e.g., Bengtson and Roth (2008)).”
Coreference Semantics from Web Features (2012, methodology): “There is also work on end-to-end coreference resolution that uses large noun-similarity lists (Daum´e III and Marcu, 2005) or structured knowledge bases such as Wikipedia (Yang and Su, 2007; Haghighi and Klein, 2009; Kobdani et al., 2011) and YAGO (Rahman and Ng, 2011).”