Quasar: Datasets for Question Answering by Search and Reading

Abstract

We present two new large-scale datasets aimed at evaluating systems designed to comprehend a natural language query and extract its answer from a large corpus of text. The Quasar-S dataset consists of 37000 cloze-style (fill-in-the-gap) queries constructed from definitions of software entity tags on the popular website Stack Overflow. The posts and comments on the website serve as the background corpus for answering the cloze questions. The Quasar-T dataset consists of 43000 open-domain trivia questions and their answers obtained from various internet sources. ClueWeb09 serves as the background corpus for extracting these answers. We pose these datasets as a challenge for two related subtasks of factoid Question Answering: (1) searching for relevant pieces of text that include the correct answer to a query, and (2) reading the retrieved text to answer the query. We also describe a retrieval system for extracting relevant sentences and documents from the corpus given a query, and include these in the release for researchers wishing to only focus on (2). We evaluate several baselines on both datasets, ranging from simple heuristics to powerful neural models, and show that these lag behind human performance by 16.4% and 32.1% for Quasar-S and -T respectively. The datasets are available at https://github.com/bdhingra/quasar .

Cited by in corpus (27)

• R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
• Open-Retrieval Conversational Question Answering
• What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams
• Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
• Universal Text Representation from BERT: An Empirical Study
• Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models
• PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
• Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model
• Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering
• Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network
• Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering
• Knowledge-Aided Open-Domain Question Answering
• Controlling Risk of Web Question Answering
• HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering
• Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension
• A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction
• Keyword-based Query Comprehending via Multiple Optimized-Demand Augmentation
• Tackling Graphical NLP problems with Graph Recurrent Networks
• A Multi-Resolution Word Embedding for Document Retrieval from Large Unstructured Knowledge Bases
• MRNN: A Multi-Resolution Neural Network with Duplex Attention for Document Retrieval in the Context of Question Answering
• Weakly-Supervised Open-Retrieval Conversational Question Answering
• Cross-language Sentence Selection via Data Augmentation and Rationale Training
• IIRC: A Dataset of Incomplete Information Reading Comprehension Questions
• Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study
• Knowledge Efficient Deep Learning for Natural Language Processing
• How to Pre-Train Your Model? Comparison of Different Pre-Training Models for Biomedical Question Answering
• A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering