AwesomeMRC

*working in progress

This repo is our research summary and playground for MRC. More features are coming.

Summary

Looking for a comprehensive and comparative review of MRC? check out our new survey paper: Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond (preprint, 2020).

In this work, MRC model is regarded as a two-stage Encoder-Decoder architecture. Our empirical analysis is shared in this repo.

Encoder:

1) Language Units

[Subword-augmented Embedding for Cloze Reading Comprehension (COLING 2018)](https://www.aclweb.org/anthology/C18-1153/)

Effective Subword Segmentation for Text Comprehension (TASLP)

2) Linguistic Knowledge

[Semantics-aware BERT for language understanding (AAAI 2020)](https://arxiv.org/abs/1909.02209)

SG-Net: Syntax-Guided Machine Reading Comprehension (AAAI 2020)
LIMIT-BERT: Linguistic Informed Multi-Task BERT (preprint)

3) Commonsense Injection

[Multi-choice Dialogue-Based Reading Comprehension with Knowledge and Key Turns (preprint)](https://arxiv.org/abs/2004.13988)

4) Contextualized language models (CLMs) for MRC:

Decoder:

The implementation is based on Transformers v2.3.0.

As part of the techniques in our Retro-Reader paper:

Retrospective Reader for Machine Reading Comprehension (preprint)

Answer Verification

1) Multitask-style verification

We evaluate different loss functions

cross-entropy (

run_squad_av.py

binary cross-entropy (

run_squad_av_bce.py

mse regression (

run_squad_avreg.py

2) External verification

Train an external verifier (

run_cls.py

Matching Network

Cross Attention (

run_squad_seq_trm.py

Matching Attention (

run_squad_seq_sc.py

Related Work:

Modeling Multi-turn Conversation with Deep Utterance Aggregation (COLING 2018)

DCMN+: Dual Co-Matching Network for Multi-choice Reading Comprehension (AAAI 2020)

Answer Dependency

Model answer dependency (start + seq -> end) (

run_squad_dep.py

Example: Retrospective Reader

1) train a sketchy reader (

sh_albert_cls.sh

2) train an intensive reader (

sh_albert_av.sh

3) rear verification: merge the prediction for final answer (

run_verifier.py

SQuAD 2.0 Dev Results:  

{
"exact": 87.75372694348522, 
"f1": 90.91630165754992, 
"total": 11873, 
"HasAns_exact": 83.1140350877193, 
"HasAns_f1": 89.4482539777485, 
"HasAns_total": 5928, 
"NoAns_exact": 92.38015138772077, 
"NoAns_f1": 92.38015138772077, 
"NoAns_total": 5945
}

Question Classification

One-shot Learning for Question-Answering in Gaokao History Challenge (COLING 2018)

Citation

@article{zhang2020retrospective,
  title={Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond},
  author={Zhang, Zhuosheng and Zhao, Hai and Wang, Rui},
  journal={arXiv preprint arXiv:2005.06249},
  year={2020}
}

@article{zhang2020retrospective,
  title={Retrospective reader for machine reading comprehension},
  author={Zhang, Zhuosheng and Yang, Junjie and Zhao, Hai},
  journal={arXiv preprint arXiv:2001.09694},
  year={2020}
}

Related Records (best)

CMRC 2017: The best single model (2017).

SQuAD 2.0: The best among all submissions (both single and ensemble settings); The first to surpass human benchmark on both EM and F1 scores with a single model (2019).

SNLI: The best among all submissions (2019-2020).

RACE: The best among all submissions (2019).

GLUE: The 3rd best among all submissions (early 2019).

Contact

Feel free to email zhangzs [at] sjtu.edu.cn if you have any questions.