CANDiS: Coupled & Attention-Driven Neural Distant Supervision [article]

Tushar Nagarajan, Sharmistha, Partha Talukdar
<span title="2017-10-26">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Distant Supervision for Relation Extraction uses heuristically aligned text data with an existing knowledge base as training data. The unsupervised nature of this technique allows it to scale to web-scale relation extraction tasks, at the expense of noise in the training data. Previous work has explored relationships among instances of the same entity-pair to reduce this noise, but relationships among instances across entity-pairs have not been fully exploited. We explore the use of
more &raquo; ... ce couplings based on verb-phrase and entity type similarities. We propose a novel technique, CANDiS, which casts distant supervision using inter-instance coupling into an end-to-end neural network model. CANDiS incorporates an attention module at the instance-level to model the multi-instance nature of this problem. CANDiS outperforms existing state-of-the-art techniques on a standard benchmark dataset.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="">arXiv:1710.09942v1</a> <a target="_blank" rel="external noopener" href="">fatcat:pf4jzgxelrbmhoc4g3ozh4ynbm</a> </span>
<a target="_blank" rel="noopener" href="" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="" title=" access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> </button> </a>