A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2012.04334v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
From Bag of Sentences to Document: Distantly Supervised Relation Extraction via Machine Reading Comprehension
[article]
<span title="2020-12-09">2020</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2020-12-08">2020</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.04334v1">arXiv:2012.04334v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2agksbzugfag5l24n7fy5o4z54">fatcat:2agksbzugfag5l24n7fy5o4z54</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.04334v1">arXiv:2012.04334v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2agksbzugfag5l24n7fy5o4z54">fatcat:2agksbzugfag5l24n7fy5o4z54</a> </span>
Distant supervision (DS) is a promising approach for relation extraction but often suffers from the noisy label problem. Traditional DS methods usually represent an entity pair as a bag of sentences and denoise labels using multi-instance learning techniques. The bag-based paradigm, however, fails to leverage the inter-sentence-level and the entity-level evidence for relation extraction, and their denoising algorithms are often specialized and complicated. In this paper, we propose a new DS
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.04334v2">arXiv:2012.04334v2</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4ab72nh2vfdrtddlrg5qienc2u">fatcat:4ab72nh2vfdrtddlrg5qienc2u</a>
</span>
more »
... digm–document-based distant supervision, which models relation extraction as a document-based machine reading comprehension (MRC) task. By re-organizing all sentences about an entity as a document and extracting relations via querying the document with relation-specific questions, the document-based DS paradigm can simultaneously encode and exploit all sentence-level, inter-sentence-level, and entity-level evidence. Furthermore, we design a new loss function–DSLoss (distant supervision loss), which can effectively train MRC models using only ⟨document, question, answer⟩ tuples, therefore noisy label problem can be inherently resolved. Experiments show that our method achieves new state-of-the-art DS performance.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201211011155/https://arxiv.org/pdf/2012.04334v2.pdf" 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="https://blobs.fatcat.wiki/thumbnail/pdf/4a/79/4a790c258879945f65610231accfaa77ec809916.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.04334v2" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>