Proceedings of the 40th Annual Meeting on Association for Computational Linguistics

217 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.

Generate Natural Language Explanations for Recommendation (2021, methodology): “•We adopt three o ine metrics – BLEU score, ROUGE score and feature coverage – to evaluate the quality of the generated explanations. e rst two metrics are classical measures for neural machine translation and text summarization.”
Semi-supervised learning by disagreement (2010, unknown): “Even a weak conditional independence [2] is difficult to be met in practice.”
Unsupervised biomedical named entity recognition: Experiments with clinical and biological texts (2013, methodology): “With sequence labeling models like Hidden Markov Models (HMMs) and Conditional Random Fields (CRFs), the two tasks could be jointly handled taking advantage of the Markov property which models transitions between labels [15,16].”