Evita: A Robust Event Recognizer For QA Systems

By Roser Saurí, Robert Knippen, Marc Verhagen, James Pustejovsky. 2005

184 citations recorded by the source corpus.

We present Evita, an application for recognizing events in natural language texts. Although developed as part of a suite of tools aimed at providing question answering systems with information about both temporal and intensional relations among events, it can be used independently as an event extraction tool. It is unique in that it is not limited to any pre-established list of relation types (events), nor is it restricted to a specific domain. Evita performs the identification and tagging of event expressions based on fairly simple strategies, informed by both linguistic-and statistically-based data. It achieves a performance ratio of 80.12% F-measure.

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

1. Dan Roth
2. Subhro Roy
3. Kang Liu
4. Tim Vieira
5. Jian Liu
6. Yubo Chen
7. James Pustejovsky
8. Marc Verhagen

In Natural Language Processing

1. Subhro Roy
2. Dan Roth
3. Tim Vieira
4. Kang Liu
5. Yubo Chen
6. James Pustejovsky
7. Inderjeet Mani
8. Jian Liu

Citations in the corpus

• Reasoning about Quantities in Natural Language (2015, background): “There has also been some work on quantities in specific domains, such as the temporal domain, the most significant being the TimeML project (Pustejovsky et al., 2003; Saur et al., 2005; PrattHartmann, 2005; Do et al., 2012).”
• Exploiting the Ground-Truth: An Adversarial Imitation Based Knowledge Distillation Approach for Event Detection (2019, background): “…be beneficial for a big variety of real-world applications including Information Retrieval (IR) (Allan 2002; Campos et al. 2014), Question Answering (QA) (Saur´ı et al. 2005; Kuchmann-Beauger, Aufaure, and Thollot 2015), Automatic Text Summarization (Ge et al. 2016; Marujo et al. 2017) and others.”
• Machine Learning of Temporal Relations (2006, background): “(4) Max <EVENT eventID=“e1” class=“occurrence” tense=“past” aspect=“none”> entered</EVENT> the room.”