Bootstrapped Learning of Semantic Classes from Positive and Negative Examples

By Winston Lin, Roman Yangarber, Ralph Grishman. 2003

89 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.

Cross-Task Generalization via Natural Language Crowdsourcing Instructions (2021, neutral): “Best results correspond to FULL INSTRUCTION - NEG EXAMPLES, indicating all instruction elements are helpful except the NEGATIVE EXAMPLES, which remains a hurdle for NLP models as also discussed in previous work (Xuan et al., 2020; Lin et al., 2003).”
Natural Instructions: Benchmarking Generalization to New Tasks from Natural Language Instructions (2021, background): “However, for humans, negative instructions (describing undesirable behaviors ; (Lin et al., 2003; Jindal and Roth, 2011)) are effective means to communicate a given task’s scope.”
Improved Pattern Learning for Bootstrapped Entity Extraction (2014, methodology): “(2002) and Lin et al. (2003) used a combination of accuracy and confidence of a pattern”
Name Tagging with Word Clusters and Discriminative Training (2004, result): “The work presented here extends a substantial body of previous work (Blum and Mitchell, 1998; Riloff and Jones, 1999; Lin et al., 2003; Boschee et al, 2002; Collins and Singer, 1999; Yarowsky, 1995) that all focuses on reducing annotation requirements through a combination of (a) seed examples, (b) ”