Using Corpus Statistics on Entities to Improve Semi-supervised Relation Extraction from the Web

55 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Natural Language Processing (Almost) from Scratch (2011, methodology): “Previous semi-supervised approaches for NLP can be roughly categorized as follows: • Ad-hoc approaches such as (Rosenfeld and Feldman, 2007) for relation extraction.”
A unified architecture for natural language processing: deep neural networks with multitask learning (2008, methodology): “We chose linear models for POS and NER.”
Multi-Hop Paragraph Retrieval for Open-Domain Question Answering (2019, background): “• Relation extraction (Rosenfeld and Feldman, 2007), another task in IE, which is concerned with finding and classifying semantic relations among the text entities (e.”
Confidence Driven Unsupervised Semantic Parsing (2011, background): “…as syntactic parsing (Reichart and Rappoport, 2007a; Yates et al., 2006), machine translation (Uefﬁng and Ney, 2007), speech (Koo et al., 2001), relation extraction (Rosenfeld and Feldman, 2007), IE (Culotta and McCallum, 2004), QA (Chu-Carroll et al., 2003) and dialog systems (Lin and Weng, 2008).”
Coupled semi-supervised learning for information extraction (2010, background): “Type checking relation arguments using available entity recognizers can help avoid incorrect labels [17, 20].”
Multimodal Learning for Web Information Extraction (2017, unknown): “Type checking [6, 19, 22] by specifying types (e.”