Ашық домен Сұрақ-Жауап
Related Papers
Speech Grammars for Textual Entailment Patterns in Multimodal Question Answering
AbstractOver the last several years, speech-based question answering (QA) has become very popular in contrast to pure search engine based approaches on a desktop. Open-domain QA systems are now much …...
Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering
AbstractBERT model has been successfully applied to open-domain QA tasks. However, previous work trains BERT by viewing passages corresponding to the same question as independent training instances, which may cause …...
Explaining Answers with Entailment Trees
AbstractOur goal, in the context of open-domain textual question-answering (QA), is to explain answers by showing the line of reasoning from what is known to the answer, rather than simply …...
UnitedQA: A Hybrid Approach for Open Domain Question Answering
AbstractTo date, most of recent work under the retrieval-reader framework for open-domain QA focuses on either extractive or generative reader exclusively. In this paper, we study a hybrid approach for …...
CycleKQR: Unsupervised Bidirectional Keyword-Question Rewriting
AbstractUsers expect their queries to be answered by search systems, regardless of the query’s surface form, which include keyword queries and natural questions. Natural Language Understanding (NLU) components of Search …...
Retrieval-guided Counterfactual Generation for QA
AbstractDeep NLP models have been shown to be brittle to input perturbations. Recent work has shown that data augmentation using counterfactuals — i.e. minimally perturbed inputs — can help ameliorate …...
Evaluating Open-Domain Question Answering in the Era of Large Language Models
AbstractLexical matching remains the de facto evaluation method for open-domain question answering (QA). Unfortunately, lexical matching fails completely when a plausible candidate answer does not appear in the list of …...