SQuAD 2.0
Related Papers
Learning to Ask Unanswerable Questions for Machine Reading Comprehension
AbstractMachine reading comprehension with unanswerable questions is a challenging task. In this work, we propose a data augmentation technique by automatically generating relevant unanswerable questions according to an answerable question …...
pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference
AbstractReasoning about implied relationships (e.g. paraphrastic, common sense, encyclopedic) between pairs of words is crucial for many cross-sentence inference problems. This paper proposes new methods for learning and using embeddings …...
Relation Module for Non-Answerable Predictions on Reading Comprehension
AbstractMachine reading comprehension (MRC) has attracted significant amounts of research attention recently, due to an increase of challenging reading comprehension datasets. In this paper, we aim to improve a MRC …...
Fluent Response Generation for Conversational Question Answering
AbstractQuestion answering (QA) is an important aspect of open-domain conversational agents, garnering specific research focus in the conversational QA (ConvQA) subtask. One notable limitation of recent ConvQA efforts is the …...
SpanBERT: Improving Pre-training by Representing and Predicting Spans
AbstractWe present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. Our approach extends BERT by (1) masking contiguous random spans, rather than random …...
Training Question Answering Models From Synthetic Data
AbstractQuestion and answer generation is a data augmentation method that aims to improve question answering (QA) models given the limited amount of human labeled data. However, a considerable gap remains …...
Undersensitivity in Neural Reading Comprehension
AbstractCurrent reading comprehension methods generalise well to in-distribution test sets, yet perform poorly on adversarially selected data. Prior work on adversarial inputs typically studies model oversensitivity: semantically invariant text perturbations …...
Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher
AbstractWith the ever growing scale of neural models, knowledge distillation (KD) attracts more attention as a prominent tool for neural model compression. However, there are counter intuitive observations in the …...
Synthetic Data Generation for Multilingual Domain-Adaptable Question Answering Systems
AbstractDeep learning models have significantly advanced the state of the art of question answering systems. However, the majority of datasets available for training such models have been annotated by humans, …...
The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models
AbstractPretrained language models have achieved super-human performances on many Machine Reading Comprehension (MRC) benchmarks. Nevertheless, their relative inability to defend against adversarial attacks has spurred skepticism about their natural language …...