This repository contains data and code for the paper below:
Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information
Sudha Rao ([email protected]) and Hal Daumé III ([email protected])
Proceedings of The 2018 Association of Computational Lingusitics (ACL 2018)
-
Download the clarification questions dataset from google drive here: https://go.umd.edu/clarification_questions_dataset
-
cp clarification_questions_dataset/data ranking_clarification_questions/data
-
Download word embeddings trained on stackexchange datadump here: https://go.umd.edu/stackexchange_embeddings
-
cp stackexchange_embeddings/embeddings ranking_clarification_questions/embeddings
The above dataset contains clarification questions for these three sites of stackexchange:
- askubuntu.com
- unix.stackexchange.com
- superuser.com
To run models on a combination of the three sites above, check ranking_clarification_questions/src/models/README
To generate clarification questions for a different site of stackexchange, check ranking_clarification_questions/src/data_generation/README
To retrain word embeddings on a newer version of stackexchange datadump, check ranking_clarification_questions/src/embedding_generation/README
Please contact Sudha Rao ([email protected]) if you have any questions or any feedback.
存储库信息 此存储库包含以下论文的数据和代码: 学会提出好问题:使用完美信息的神经期望值对澄清问题进行排名 Sudha Rao ([email protected]) 和 Hal Daumé III ([email protected]) 2018 年计算语言学协会论文集 (ACL 2018) 下载数据
- 从谷歌云端硬盘下载澄清问题数据集:https://go.umd.edu/clarification_questions_dataset
- CP clarification_questions_dataset/data ranking_clarification_questions/data
- 在此处下载在 stackexchange datadump 上训练的词嵌入:https://go.umd.edu/stackexchange_embeddings
- cp stackexchange_embeddings/embeddings ranking_clarification_questions/embeddings 上面的数据集包含了 stackexchange 的这三个站点的澄清问题:
- askubuntu.com
- unix.stackexchange.com
- superuser.com 根据上述数据运行模型 要在上述三个站点的组合上运行模型,请查看 ranking_clarification_questions/src/models/README 为其他站点生成数据 要为 stackexchange 的不同站点生成澄清问题,请查看 ranking_clarification_questions/src/data_generation/README 重新训练 stackexchange 词嵌入 要在较新版本的 stackexchange 数据转储上重新训练单词嵌入,请查看 ranking_clarification_questions/src/embedding_generation/README 联系方式 如果您有任何问题或任何反馈,请联系 Sudha Rao ([email protected])。