UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Collective cross-document relation extraction without labelled data

Yao, L; Riedel, S; McCallum, A; (2010) Collective cross-document relation extraction without labelled data. In: (pp. pp. 1013-1023).

Full text not available from this repository.


We present a novel approach to relation extraction that integrates information across documents, performs global inference and requires no labelled text. In particular, we tackle relation extraction and entity identification jointly. We use distant supervision to train a factor graph model for relation extraction based on an existing knowledge base (Freebase, derived in parts from Wikipedia). For inference we run an efficient Gibbs sampler that leads to linear time joint inference. We evaluate our approach both for an in-domain (Wikipedia) and a more realistic out-of-domain (New York Times Corpus) setting. For the in-domain setting, our joint model leads to 4% higher precision than an isolated local approach, but has no advantage over a pipeline. For the out-of-domain data, we benefit strongly from joint modelling, and observe improvements in precision of 13% over the pipeline, and 15% over the isolated baseline. © 2010 Association for Computational Linguistics.

Type: Proceedings paper
Title: Collective cross-document relation extraction without labelled data
ISBN: 1932432868
UCL classification: UCL > School of BEAMS
UCL > School of BEAMS > Faculty of Engineering Science
URI: http://discovery.ucl.ac.uk/id/eprint/1367735
Downloads since deposit
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item