tag-based-multi-span-extraction - GitLite

KO | EN

gitlite — search

#javascript #python #react #ai #typescript #android #rust #docker #macos #windows #awesome #awesome-list #pytorch #openai

tag-based-multi-span-extraction

(★ 158)

The official implementation of EMNLP 2020, "A Simple and Effective Model for Answering Multi-span Questions".

파일 탐색기

최종 버전 다운로드 (.zip)

- analysis_by_number_of_spans.ipynb
- analysis_num_tokens_and_occurrences.ipynb
- analysis_num_tokens_and_occurrences.py
- - model.jsonnet
- drop_dataset_dev.json
- drop_dataset_dev_standardized.json
- drop_dataset_train.json
- drop_dataset_train_standardized.json
- license.txt
- drop_predictions.jsonl
- quoref_predictions.jsonl
- quoref-dev-v0.1.json
- quoref-train-v0.1.json
- quoref_dataset_dev.json
- quoref_dataset_train.json
- README.txt
- - __init__.py
- - __init__.py
  - multi_head_model.py
- - __init__.py
- - __init__.py
- __init__.py
- dropify_quoref.py
- generate_submission_predictions.py
- standardize_drop.py
.gitignore
README.md
requirements.txt

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/eladsegal/tag-based-multi-span-extraction

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd tag-based-multi-span-extraction

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

python -m allennlp.tools.drop_eval --gold_path drop_data/drop_dataset_dev.json \

파이썬 스크립트(또는 모듈)를 실행합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# A Simple and Effective Model for Answering Multi-span Questions

This repository contains the official implementation of the following paper:  
Elad Segal, Avia Efrat, Mor Shoham, Amir Globerson, Jonathan Berant. ["A Simple and Effective Model for Answering Multi-span Questions"](http://arxiv.org/abs/1909.13375). _In EMNLP, 2020_.

### Citation
```
@inproceedings{Segal2020TASE,
  title={A Simple and Effective Model for Answering Multi-span Questions},
  author={Segal, Elad and Efrat, Avia and Shoham, Mor and Globerson, Amir and Berant, Jonathan},
  booktitle={EMNLP},
  year={2020},
}
```

## [DROP Explorer](https://github.com/eladsegal/DROP-explorer)
Use [DROP Explorer](https://github.com/eladsegal/DROP-explorer) to better understand DROP, Quoref and the models' predictions.

## Usage
The commands listed in this section need to be run from the root directory of the repository.

First, install prerequisites with  
```pip install -r requirements.txt```

### Commands
* Train a model:  
```
allennlp train configs/[config file] -s [training_directory] --include-package src
```

* Output predictions by a model:  
```
allennlp predict model.tar.gz drop_data/drop_dataset_dev.json --predictor machine-comprehension \
--cuda-device 0 --output-file predictions.jsonl --use-dataset-reader --include-package src \
-o "{'validation_dataset_reader.pickle.action': 'None'}"
```

* Evaluate a model (unofficial evaluation code, faster):  
```
allennlp evaluate model.tar.gz drop_data/drop_dataset_dev.json --cuda-device 0 --output-file eval.json \
--include-package src -o "{'validation_dataset_reader.pickle.action': 'None'}"
```

* Evaluate a model (official evaluation code, slower):

1. 
    ```
    python tools/generate_submission_predictions.py --archive_file model.tar.gz \
    --input_file drop_data/drop_dataset_dev.json --cuda-device 0 --output_file predictions.json \
    --include-package src
  ```
  2. 
    ```
    python -m allennlp.tools.drop_eval --gold_path drop_data/drop_dataset_dev.json \
    --prediction_path predictions.json --output_path metrics.json
    ```
  
### Trained Models
- [RoBERTa TASE_IO + SSE](https://drive.google.com/file/d/1k8MFEmmGeUXlBmghAKN8Xl_a6mbFUHdn/view) - Trained on DROP ([config](https://github.com/eladsegal/tag-based-multi-span-extraction/blob/master/configs/drop/roberta/drop_roberta_large_TASE_IO_SSE.jsonnet))
- [RoBERTa TASE_IO](https://drive.google.com/file/d/1VneI-thp4dfTOcqRPv1-Gzq1jmwsvq_i/view) - Trained on DROP ([config](https://github.com/eladsegal/tag-based-multi-span-extraction/blob/master/configs/drop/roberta/drop_roberta_large_TASE_IO.jsonnet))