ReQA: An Evaluation for End-to-End Answer Retrieval Models

@inproceedings{Ahmad2019ReQAAE,
  title={ReQA: An Evaluation for End-to-End Answer Retrieval Models},
  author={Amin Ahmad and Noah Constant and Yinfei Yang and Daniel Matthew Cer},
  booktitle={MRQA@EMNLP},
  year={2019}
}
  • Amin Ahmad, Noah Constant, +1 author Daniel Matthew Cer
  • Published in MRQA@EMNLP 2019
  • Computer Science
  • Popular QA benchmarks like SQuAD have driven progress on the task of identifying answer spans within a specific passage, with models now surpassing human performance. [...] Key Method We establish baselines using both neural encoding models as well as classical information retrieval techniques. We release our evaluation code to encourage further work on this challenging task.Expand Abstract
    18 Citations
    MultiReQA: A Cross-Domain Evaluation for Retrieval Question Answering Models
    • 4
    • PDF
    A Technical Question Answering System with Transfer Learning
    • 1
    Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation
    Crossing Variational Autoencoders for Answer Retrieval
    • 3
    • PDF
    Embedding-based Zero-shot Retrieval through Query Generation
    Pre-training Tasks for Embedding-based Large-scale Retrieval
    • 31
    • Highly Influenced
    • PDF
    Talk to Papers: Bringing Neural Question Answering to Academic Search
    • 3
    • Highly Influenced
    • PDF
    SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval

    References

    SHOWING 1-10 OF 39 REFERENCES
    Adaptive Document Retrieval for Deep Question Answering
    • 27
    • PDF
    End-to-End Open-Domain Question Answering with BERTserini
    • 115
    • Highly Influential
    • PDF
    Reading Wikipedia to Answer Open-Domain Questions
    • 724
    • PDF
    Modeling of the Question Answering Task in the YodaQA System
    • 56
    • PDF
    SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
    • 197
    • PDF
    Text Embeddings for Retrieval From a Large Knowledge Base
    • 4
    • Highly Influential
    • PDF
    WikiQA: A Challenge Dataset for Open-Domain Question Answering
    • 470
    • PDF
    Building a question answering test collection
    • 315
    • PDF
    Latent Retrieval for Weakly Supervised Open Domain Question Answering
    • 99
    • PDF