English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Distant supervision (DS) is a promising approach for relation extraction butoften suffers from the noisy label problem. Traditional DS methods usuallyrepresent an entity pair as a bag of sentences and denoise labels usingmulti-instance learning techniques. The bag-based paradigm, however, fails toleverage the inter-sentence-level and the entity-level evidence for relationextraction, and their denoising algorithms are often specialized andcomplicated. In this paper, we propose a new DS paradigm--document-baseddistant supervision, which models relation extraction as a document-basedmachine reading comprehension (MRC) task. By re-organizing all sentences aboutan entity as a document and extracting relations via querying the document withrelation-specific questions, the document-based DS paradigm can simultaneouslyencode and exploit all sentence-level, inter-sentence-level, and entity-levelevidence. Furthermore, we design a new loss function--DSLoss (distantsupervision loss), which can effectively train MRC models using only$\langle$document, question, answer$\rangle$ tuples, therefore noisy labelproblem can be inherently resolved. Experiments show that our method achievesnew state-of-the-art DS performance.

From Bag of Sentences to Document: Distantly Supervised Relation Extraction via Machine Reading Comprehension