University of Washington System for 2015 KBP Cold Start Slot Filling
نویسندگان
چکیده
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 methods are complementary with little overlap in the resulting extractions. In particular, IMPLIE finds extractions that are beyond the scope of OPENIE-KBP.
منابع مشابه
New York University 2014 Knowledge Base Population Systems
New York University (NYU) participated in three tracks of the 2014 TAC-KBP evaluation: English Slot Filling, Cold Start and Entity Discovery and Linking. While this year is the first time and second time we participated in entity discovery and linking (EDL) and cold start respectively, we have been working on the slot filling task for several years. With additional development time this year, o...
متن کاملGhent University-IBCN Participation in TAC-KBP 2014 Slot Filling and Cold Start Tasks
This paper presents the system of the UGENT IBCN team for the TAC KBP 2014 slot filling and cold start (slot filling variant) tasks. This was the team’s first participation in both tasks. The slot filling system uses distant supervision to generate training data combined with a noise reduction step, and two different types of classifiers. We show that the noise reduction step significantly impr...
متن کاملOff to a Cold Start: New York University's 2013 Knowledge Base Population Systems
New York University submitted two runs this year: a KBP Slot Filling run and a Cold Start run. The Slot Filling run used the same system as last year (Min et al. 2012), with only the minimal changes needed to address the revised specifications. These included changes in the provenance information and collapsing employee_of and member_of slots. We included the confidence estimation step (Li and ...
متن کاملIntelius-NYU TAC-KBP2012 Cold Start System
This paper describes the Intelius-NYU 2012 system for the KBP Cold Start task. The Cold Start task can be decomposed into two subtasks: slot filling and entity linking. For slot filling, we focus on the adaptation of the NYU 2011 regular slot filling system to the Cold Start task. For entity linking, we apply Intelius‘s commercial conflation engine to link person and organization entities with ...
متن کاملLinguistic Resources for 2013 Knowledge Base Population Evaluations
Knowledge Base Population (KBP) is an evaluation track of the Text Analysis Conference (TAC), a workshop series organized by the National Institute of Standards and Technology (NIST). In 2013, the KBP evaluations included five tasks targeting information extraction and question answering technologies: Entity Linking, Slot Filling, Temporal Slot Filling, Sentiment Slot Filling, and Cold Start. T...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2015