Looking at the Overlooked: An Analysis on the Word-Overlap Bias in Natural Language Inference
It has been shown that NLI models are usually biased with respect to the word-overlap between premise and hypothesis; they take this feature as a primary cue for predicting the entailment label. In this paper, we focus on an overlooked aspect of the overlap bias in NLI models: the reverse word-overlap bias. Our experimental results demonstrate that current NLI models are highly biased towards the non-entailment label on instances with low overlap, and the existing debiasing methods, which are reportedly successful on existing challenge datasets, are generally ineffective in addressing this category of bias. We investigate the reasons for the emergence of the overlap bias and the role of minority examples in its mitigation. For the former, we find that the word-overlap bias does not stem from pre-training, and for the latter, we observe that in contrast to the accepted assumption, eliminating minority examples does not affect the generalizability of debiasing methods with respect to the overlap bias.
Code (1)
Tasks
Natural Language InferenceSimilar Papers 제목 키워드 기반
Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classification
Few-Shot Event Classification (FSEC) aims at developing a model for event prediction, which can generalize to new event types with a limited number of annotated data. Existing FSEC studies have achieved high accuracy on …
Mitigating Non-Target Speaker Bias in Guided Speaker Embedding
Obtaining high-quality speaker embeddings in multi-speaker conditions is crucial for many applications. A recently proposed guided speaker embedding framework, which utilizes speech activities of target and non-target sp…
Speaker VerificationTransformer Language Models Handle Word Frequency in Prediction Head
Prediction head is a crucial component of Transformer language models. Despite its direct impact on prediction, this component has often been overlooked in analyzing Transformers. In this study, we investigate the inner …
PredictionText GenerationStrategies in subword tokenization: humans vs. algorithms
The output of subword tokenization can be very different depending on what algorithm is used. It is typically judged as more or less plausible, depending on how much it corresponds to human intuition. A subword vocabular…
SegmentationWordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings
Intersectional bias is a bias caused by an overlap of multiple social factors like gender, sexuality, race, disability, religion, etc. A recent study has shown that word embedding models can be laden with biases against …
Word Embeddings