Measuring Context-Word Biases in Lexical Semantic Datasets
State-of-the-art pretrained contextualized models (PCM) eg. BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that performance in these tasks reflect how well a model represents the coupled word and context semantics. We question this assumption by presenting the first quantitative analysis on the context-word interaction being tested in major contextual lexical semantic tasks. To achieve this, we run probing baselines on masked input, and propose measures to calculate and visualize the degree of context or word biases in existing datasets. The analysis was performed on both models and humans. Our findings demonstrate that models are usually not being tested for word-in-context semantics in the same way as humans are in these tasks, which helps us better understand the model-human gap. Specifically, to PCMs, most existing datasets fall into the extreme ends (the retrieval-based tasks exhibit strong target word bias while WiC-style tasks and WSD show strong context bias); In comparison, humans are less biased and achieve much better performance when both word and context are available than with masked input. We recommend our framework for understanding and controlling these biases for model interpretation and future task design.
Code (0)
등록된 구현이 없습니다.
Tasks
RetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Measuring Word-Context Biases in Lexical Semantic Datasets
State-of-the-art contextualized models eg. BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that performance in these tasks reflect how well a model represents…
RetrievalContext vs Target Word: Quantifying Biases When Applying Models to Lexical Semantic Datasets
State-of-the-art contextualized models such as BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that performance in these tasks reflect how well a model repres…
Entity LinkingModels can use keywords to answer questions that human cannot
Recent studies raised that reading comprehension (RC) models learn to exploit biases and annotation artifacts in current Machine Reading Comprehension (MRC) datasets to achieve impressive performance. This hinders the co…
Machine Reading ComprehensionReading ComprehensionDiBiMT: A Novel Benchmark for Measuring Word Sense Disambiguation Biases in Machine Translation
Lexical ambiguity poses one of the greatest challenges in the field of Machine Translation. Over the last few decades, multiple efforts have been undertaken to investigate incorrect translations caused by the polysemous …
Machine TranslationTranslationWord Sense DisambiguationMeasuring Inductive Biases of In-Context Learning with Underspecified Demonstrations
In-context learning (ICL) is an important paradigm for adapting large language models (LLMs) to new tasks, but the generalization behavior of ICL remains poorly understood. We investigate the inductive biases of ICL from…
In-Context LearningInductive Bias