paper-with-me

홈 › Papers

Measure More, Question More: Experimental Studies on Transformer-based Language Models and Complement Coercion

2022-12-20 · Yuling Gu

Transformer-based language models have shown strong performance on an array of natural language understanding tasks. However, the question of how these models react to implicit meaning has been largely unexplored. We investigate this using the complement coercion phenomenon, which involves sentences like "The student finished the book about sailing" where the action "reading" is implicit. We compare LMs' surprisal estimates at various critical sentence regions in sentences with and without implicit meaning. Effects associated with recovering implicit meaning were found at a critical region other than where sentences minimally differ. We then use follow-up experiments to factor out potential confounds, revealing different perspectives that offer a richer and more accurate picture.

📄 PDF Abstract BibTeX arXiv:2212.10536

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language UnderstandingSentence

Similar Papers 제목 키워드 기반

On Measures of Biases and Harms in NLP

2021-08-07 · Sunipa Dev, Emily Sheng, Jieyu Zhao, Aubrie Amstutz 외

Recent studies show that Natural Language Processing (NLP) technologies propagate societal biases about demographic groups associated with attributes such as gender, race, and nationality. To create interventions and mit…

Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifiers

2021-09-10 · Findings (EMNLP) 2021 11 · Shane Storks, Joyce Chai

As large-scale, pre-trained language models achieve human-level and superhuman accuracy on existing language understanding tasks, statistical bias in benchmark data and probing studies have recently called into question …

text-classificationText Classification

Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness

2023-01-21 · Shuaichen Chang, Jun Wang, Mingwen Dong, Lin Pan 외

Neural text-to-SQL models have achieved remarkable performance in translating natural language questions into SQL queries. However, recent studies reveal that text-to-SQL models are vulnerable to task-specific perturbati…

DiagnosticNatural QuestionsText to SQLText-To-SQL

Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Knowledge-based visual question answering (KVQA) task aims to answer questions that require additional external knowledge as well as an understanding of images and questions. Recent studies on KVQA inject an external kno…

Question AnsweringSemantic SimilaritySemantic Textual SimilarityVisual Question Answering+1

Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base

2022-07-27 · Jinyeong Chae, Jihie Kim

Knowledge-based visual question answering (KVQA) task aims to answer questions that require additional external knowledge as well as an understanding of images and questions. Recent studies on KVQA inject an external kno…

Question AnsweringSemantic SimilaritySemantic Textual SimilarityVisual Question Answering+1