Search Results for author:
Found 6 papers, 4 papers with code
Answer-level Calibration for Free-form Multiple Choice Question Answering
We present ALC (Answer-Level Calibration), where our main suggestion is to model context-independent biases in terms of the probability of a choice without the associated context and to subsequently remove it using an unsupervised estimate of similarity with the full context.
Interpreting Text Classifiers by Learning Context-sensitive Influence of Words
Many existing approaches for interpreting text classification models focus on providing importance scores for parts of the input text, such as words, but without a way to test or improve the interpretation method itself.
Reordering Examples Helps during Priming-based Few-Shot Learning
Finally, we analyze the learned prompts to reveal novel insights, including the idea that two training examples in the right order alone can provide competitive performance for sentiment classification and natural language inference.
NILE : Natural Language Inference with Faithful Natural Language Explanations
In this work, we focus on the task of natural language inference (NLI) and address the following question: can we build NLI systems which produce labels with high accuracy, while also generating faithful explanations of its decisions?
Improving Answer Selection and Answer Triggering using Hard Negatives
In this paper, we establish the effectiveness of using hard negatives, coupled with a siamese network and a suitable loss function, for the tasks of answer selection and answer triggering.
Zero-shot Word Sense Disambiguation using Sense Definition Embeddings
To overcome this challenge, we propose Extended WSD Incorporating Sense Embeddings (EWISE), a supervised model to perform WSD by predicting over a continuous sense embedding space as opposed to a discrete label space.
