← Search

Weerayut Buaphet

2 accepted papers

2022

Mitigating Spurious Correlation in Natural Language Understanding with Counterfactual Inference

EMNLP 2022main

Despite their promising results on standard benchmarks, NLU models are still prone to make predictions based on shortcuts caused by unintended bias in the dataset. For example, an NLI model may use lexical overlap as a shortcut to make entailment predictions due to repetitive data generation pattern…

Cited by 13SourcePDFScholar
2022

Thai Nested Named Entity Recognition Corpus

ACL 2022findings

This paper presents the first Thai Nested Named Entity Recognition (N-NER) dataset. Thai N-NER consists of 264,798 mentions, 104 classes, and a maximum depth of 8 layers obtained from 4,894 documents in the domains of news articles and restaurant reviews. Our work, to the best of our knowledge, pres…