University of Washington TAC-KBP 2016 System Description
نویسندگان
چکیده
This document describes the University of Washington’s event extraction system used in the Event Argument Extraction and Linking and Event Nugget Detection tasks of the 2016 TAC KBP competition. This system was composed of three components: Evento, a CRFbased extractor, NomEvent, which makes use a lexicon to build features to identify nominal triggers, and NewsSpike, which uses an unsupervised training process to produce a highprecision extractor (Zhang et al., 2015). These three methods combine to form a complementary system which performs better than any single individual component.
منابع مشابه
University of Washington System for 2015 KBP Cold Start Slot Filling
The University of Washington participated in Cold Start Slot Filling for TAC-KBP 2015 with a system that combines three methods: 1) its 2013 OPENIE-KBP system (Soderland et al., 2013); 2) a novel Implicit Relation Information Extractor (IMPLIE); and 3) MULTIR extractor (Hoffmann et al., 2011), trained on a combination of distant supervision and crowdsourced training instances. These three metho...
متن کاملContext-Based Entity Linking - University of Amsterdam at TAC 2012
This paper describes our approach to the 2012 Text Analysis Conference (TAC) Knowledge Base Population (KBP) entity linking track. For this task, we turn to a state-of-the-art system for entity linking in microblog posts. Compared to the little context microblog posts provide, the documents in the TAC KBP track provide context of greater length and of a less noisy nature. In this paper, we adap...
متن کاملECNU: Brief System Description of Submission to Knowledge Base Population at TAC 2011
This paper briefly reports our submissions to the three tasks in TAC KBP 2011, i.e., Slot Filling (SF for short), Entity Linking (EL for short) and Cross-lingual Entity Linking (CEL for short).
متن کاملSaarland University Spoken Language Systems at the Slot Filling Task of TAC KBP 2010
For the slot filling task of TAC KBP 2010 we developed as a system a simple pipeline architecture whose main components are a two-stage retrieval module and a relation extraction module. We use word-cluster features in the system as a method of achieving generalization by exploiting raw text. In the relation extraction module we use distant supervision in order to extract training examples from...
متن کاملSaarland University Spoken Language Systems Group at TAC KBP 2011
In this paper we describe our participation in the Knowledge Base Population (KBP) track at TAC 2011. The architecture of our slot filling system is the same as last year. We mainly focus on developing a new system for the cross-language entity linking task. We compare the performance of monolingual retrieval and cross-lingual retrieval for entity linking. For NIL entity clustering, we group re...
متن کامل