Post-Consumption Susceptibility of Online Reviewers to Random Weather-Related Events

Brandes, Leif; Dover, Yaniv

doi:10.2139/ssrn.3228036

Cited by 2 publications

(2 citation statements)

References 94 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research about patterns and expert crafted rules was popular in the past (Hearst, 1992;Kukich, 1992;Ravichandran and Hovy, 2002) and is still found useful nowadays; for enhancing embeddings (Schwartz, 2017), filtering noise in crawled data (Grundkiewicz and Junczys-Dowmunt, 2014;Koehn et al, 2019), as a component within large pipelines (Ein-Dor et al, 2019) or by itself in textrich domains (Padillo et al, 2019). Using domain expertise to categorize and understand a new domain is often the first practical step to apply in other fields too, which may devise rules for that purpose (Brandes and Dover, 2018;Choshen-Hillel et al, 2019;Li et al, 2019;Nguyen et al, 2010).…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains

Shnarch

Choshen

Moshkowich

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

Approaching new data can be quite deterrent; you do not know how your categories of interest are realized in it, commonly, there is no labeled data at hand, and the performance of domain adaptation methods is unsatisfactory.Aiming to assist domain experts in their first steps into a new task over a new corpus, we present an unsupervised approach to reveal complex rules which cluster the unexplored corpus by its prominent categories (or facets).These rules are human-readable, thus providing an important ingredient which has become in short supply lately -explainability. Each rule provides an explanation for the commonality of all the texts it clusters together.We present an extensive evaluation of the usefulness of these rules in identifying target categories, as well as a user study which assesses their interpretability.

show abstract