IndexFziQ/MSMARCO-MRC-Analysis
Analysis on the MS-MARCO leaderboard regarding the machine reading comprehension task.
This project offers a breakdown of how well different AI models perform on the MS MARCO benchmark for machine reading comprehension. It takes in various AI model results and details about the MS MARCO dataset, then outputs a comparison of model accuracy in generating human-like answers to real-world questions. Anyone involved in developing or evaluating natural language processing (NLP) systems for question answering would find this useful.
No commits in the last 6 months.
Use this if you need to understand the historical performance of various AI models on a large-scale, real-world question-answering benchmark.
Not ideal if you are looking for an actively maintained and updated leaderboard, as the MS MARCO Q&A missions have been retired.
Stars
21
Forks
4
Language
—
License
MIT
Category
Last pushed
Dec 14, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/IndexFziQ/MSMARCO-MRC-Analysis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ymcui/cmrc2018
A Span-Extraction Dataset for Chinese Machine Reading Comprehension (CMRC 2018)
princeton-nlp/DensePhrases
[ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval...
thunlp/MultiRD
Code and data of the AAAI-20 paper "Multi-channel Reverse Dictionary Model"
IndexFziQ/KMRC-Papers
A list of recent papers regarding knowledge-based machine reading comprehension.
danqi/rc-cnn-dailymail
CNN/Daily Mail Reading Comprehension Task