End-to-End Open-Domain Question Answering with BERTserini

Abstract

We demonstrate an end-to-end question answering system that integrates BERT with the open-source Anserini information retrieval toolkit. In contrast to most question answering and reading comprehension models today, which operate over small amounts of input text, our system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles in an end-to-end fashion. We report large improvements over previous results on a standard benchmark test collection, showing that fine-tuning pretrained BERT with SQuAD is sufficient to achieve high accuracy in identifying answer spans.

arXiv commentPublished in the Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)

References in corpus (2)

• Passage Re-ranking with BERT
• R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering

Cited by in corpus (76)

• Multi-Stage Document Ranking with BERT
• Span-based Joint Entity and Relation Extraction with Transformer Pre-training
• Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering
• Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
• Simple Applications of BERT for Ad Hoc Document Retrieval
• Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering
• Critically Examining the "Neural Hype": Weak Baselines and the Additivity of Effectiveness Gains from Neural Ranking Models
• How Context Affects Language Models' Factual Predictions
• What does BERT know about books, movies and music? Probing BERT for Conversational Recommendation
• Efficient Document Re-Ranking for Transformers by Precomputing Term Representations
• Table Search Using a Deep Contextualized Language Model
• Distilling Knowledge from Reader to Retriever for Question Answering
• Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering
• Rapidly Deploying a Neural Search Engine for the COVID-19 Open Research Dataset: Preliminary Thoughts and Lessons Learned
• Embed2Detect: Temporally Clustered Embedded Words for Event Detection in Social Media
• Improving Question Answering with External Knowledge
• A Replication Study of Dense Passage Retriever
• Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model
• Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering
• Pretrained AI Models: Performativity, Mobility, and Change
• Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval
• Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index
• Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification
• A Study of BERT for Non-Factoid Question-Answering under Passage Length Constraints
• Comparing Approaches to Dravidian Language Identification
• You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
• Accelerating Real-Time Question Answering via Question Generation
• Multi-Hop Paragraph Retrieval for Open-Domain Question Answering
• CFO: A Framework for Building Production NLP Systems
• WLV-RIT at HASOC-Dravidian-CodeMix-FIRE2020: Offensive Language Identification in Code-switched YouTube Comments
• Zero-shot Neural Passage Retrieval via Domain-targeted Synthetic Question Generation
• Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directions
• TWEAC: Transformer with Extendable QA Agent Classifiers
• Beyond English-Only Reading Comprehension: Experiments in Zero-Shot Multilingual Transfer for Bulgarian
• Cross-Lingual Relevance Transfer for Document Retrieval
• A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering
• Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension
• Learning Dense Representations of Phrases at Scale
• SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval
• SQRQuerier: A Visual Querying Framework for Cross-national Survey Data Recycling
• EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System
• Delaying Interaction Layers in Transformer-based Encoders for Efficient Open Domain Question Answering
• Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension
• Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering
• Talk to Papers: Bringing Neural Question Answering to Academic Search
• Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answering
• Attacking Open-domain Question Answering by Injecting Misinformation
• Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction
• Answering Any-hop Open-domain Questions with Iterative Document Reranking
• An Experimental Evaluation of Transformer-based Language Models in the Biomedical Domain
• AnswerQuest: A System for Generating Question-Answer Items from Multi-Paragraph Documents
• Weakly-Supervised Open-Retrieval Conversational Question Answering
• An Effective Contextual Language Modeling Framework for Speech Summarization with Augmented Features
• Answering Open-Domain Questions of Varying Reasoning Steps from Text
• Contextualized Query Embeddings for Conversational Search
• AutoADR: Automatic Model Design for Ad Relevance
• Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs
• Technical Question Answering across Tasks and Domains
• GLOW : Global Weighted Self-Attention Network for Web Search
• Contextualized Sparse Representations for Real-Time Open-Domain Question Answering
• Tradeoffs in Sentence Selection Techniques for Open-Domain Question Answering
• Does Dialog Length matter for Next Response Selection task? An Empirical Study
• What makes us curious? analysis of a corpus of open-domain questions
• MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering
• SF-QA: Simple and Fair Evaluation Library for Open-domain Question Answering
• Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering
• Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance
• Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering
• Open-Domain Question-Answering for COVID-19 and Other Emergent Domains
• A question-answering system for aircraft pilots' documentation
• Zero-Shot Estimation of Base Models' Weights in Ensemble of Machine Reading Comprehension Systems for Robust Generalization
• Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints
• Predicting Clinical Trial Results by Implicit Evidence Integration
• Using the Hammer Only on Nails: A Hybrid Method for Evidence Retrieval for Question Answering
• Customizing Contextualized Language Models forLegal Document Reviews
• BERT for Target Apps Selection: Analyzing the Diversity and Performance of BERT in Unified Mobile Search