Giter VIP home page Giter VIP logo

unanswerable_qa's Introduction

Code for "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval" (ACL 2021, Long)

This is the repository for baseline models and annotated data for this paper:
Akari Asai and Eunsol Choi. Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval. In: Proceedings of ACL. 2021

In the paper, we carefully analyze unanswerable questions in information-seeking QA dataset (i.e., Natural Questions and TyDi QA) and attempt to identify the remaining headrooms. We conduct both a range of controlled experiments and insensitive human annotations on around 800 examples across across 6 languages.

Annotated data

In human_annotated_data, we provide human annotated data from TyDi QA and Natural Questions.

Dataset language # of annotated questions file name
Natural Questions English 450 NQ.tsv
TyDi QA Bengali 50 TyDi-Bn.tsv
TyDi QA Japanese 100 TyDi-Ja.tsv
TyDi QA Korean 100 TyDi-Bn.tsv
TyDi QA Russian 50 TyDi-Ru.tsv
TyDi QA Telugu 50 TyDi-Te.tsv

Baselines

In this work, we conduct several baseline experiments to identify the remaining headrooms in information-seeking QA. This repository include baselines for question only baseline. See the training and evaluation details in README.md. We thank the authors of Riki Net, Retro-reader, and ETC for providing their models' predictions that are used to analyze those state-of-the-art models behaviors.

Citation and Contact

If you find this codebase is useful or use in your work, please cite our paper.

@inproceedings{
asai2020learning,
title={Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval},
author={Akari Asai and Eunsol Choi},
booktitle={ACL-IJCNLP},
year={2021}
}

Please contact Akari Asai (@AkariAsai, akari[at]cs.washington.edu) for questions and suggestions.

unanswerable_qa's People

Contributors

akariasai avatar eunsol avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.