Skip to content
Code for the TriviaQA reading comprehension dataset
Python
Branch: master
Clone or download
Latest commit 34a26ae Aug 23, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
evaluation Update readme May 11, 2017
samples minor bug fixes May 4, 2017
utils minor bug fixes May 4, 2017
.gitignore Initial commit Apr 25, 2017
LICENSE add license Aug 22, 2019
README.md remove links Nov 8, 2018
requirements.txt Add requirements; update readme May 11, 2017

README.md

TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

  • This repo contains code for the paper Mandar Joshi, Eunsol Choi, Daniel Weld, Luke Zettlemoyer.

TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension In Association for Computational Linguistics (ACL) 2017, Vancouver, Canada.

Requirements

General

  • Python 3. You should be able to run the evaluation scripts using Python 2.7 if you take care of unicode in utils.utils.py.
  • BiDAF requires Python 3 -- check the original repository for more details.

Python Packages

  • tensorflow (only if you want to run BiDAF, verified on r0.11)
  • nltk
  • tqdm

Evaluation

The dataset file parameter refers to files in the qa directory of the data (e.g., wikipedia-dev.json). For file format, check out the sample directory in the repo.

python3 -m evaluation.triviaqa_evaluation --dataset_file samples/triviaqa_sample.json --prediction_file samples/sample_predictions.json

Miscellaneous

  • If you have a SQuAD model and want to run on TriviaQA, please refer to utils.convert_to_squad_format.py
You can’t perform that action at this time.