{"id":18950041,"url":"https://github.com/salesforce/query-focused-sum","last_synced_at":"2025-04-15T23:31:36.518Z","repository":{"id":45121109,"uuid":"436795008","full_name":"salesforce/query-focused-sum","owner":"salesforce","description":"Official code repository for \"Exploring Neural Models for Query-Focused Summarization\".","archived":false,"fork":false,"pushed_at":"2023-06-12T21:32:58.000Z","size":45,"stargazers_count":42,"open_issues_count":2,"forks_count":5,"subscribers_count":8,"default_branch":"master","last_synced_at":"2024-04-08T00:13:13.960Z","etag":null,"topics":["deep-learning","machine-learning","neural-network","nlp","question-answering","summarization"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2112.07637","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/salesforce.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":null,"governance":null}},"created_at":"2021-12-09T23:53:46.000Z","updated_at":"2024-04-03T06:30:48.000Z","dependencies_parsed_at":"2022-09-22T17:21:31.541Z","dependency_job_id":"937095dc-e7bc-4f7a-9a5c-ab1759c8ce2d","html_url":"https://github.com/salesforce/query-focused-sum","commit_stats":{"total_commits":20,"total_committers":5,"mean_commits":4.0,"dds":0.35,"last_synced_commit":"46cb3878ff9f55b963ad94728676189a6d421d60"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2Fquery-focused-sum","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2Fquery-focused-sum/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2Fquery-focused-sum/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2Fquery-focused-sum/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/salesforce","download_url":"https://codeload.github.com/salesforce/query-focused-sum/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223689737,"owners_count":17186489,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","machine-learning","neural-network","nlp","question-answering","summarization"],"created_at":"2024-11-08T13:20:26.390Z","updated_at":"2024-11-08T13:20:26.939Z","avatar_url":"https://github.com/salesforce.png","language":"Python","readme":"# Exploring Neural Models for Query-Focused Summarization\n\nThis is the official code repository for [Exploring Neural Models for Query-Focused Summarization](https://arxiv.org/abs/2112.07637)\nby [Jesse Vig*](https://twitter.com/jesse_vig), [Alexander R. Fabbri*](https://twitter.com/alexfabbri4),\n[Wojciech Kryściński*](https://twitter.com/iam_wkr), [Chien-Sheng Wu](https://twitter.com/jasonwu0731), and\n[Wenhao Liu](https://twitter.com/owenhaoliu) (*equal contribution). \n\nWe present code and instructions for reproducing the paper experiments and running the models against your own datasets.\n\n## Table of contents\n- [Introduction](#introduction)\n- [Two-stage models](#two-stage-models)\n- [Segment Encoder](#segment-encoder)\n- [Citation](#citation)\n- [License](#license)\n\n## Introduction\nQuery-focused summarization (QFS) aims to produce summaries that answer particular questions of interest, enabling greater user control and personalization.\nIn [our paper](https://arxiv.org/abs/2112.07637) we conduct a systematic exploration of neural approaches to QFS, considering two general classes of methods: two-stage extractive-abstractive solutions and end-to-end models.\nWithin those categories, we investigate existing methods and present two model extensions that achieve state-of-the-art performance on the QMSum dataset  by a margin of up to 3.38 ROUGE-1, 3.72 ROUGE-2, and 3.28 ROUGE-L.\n\n## Two-stage models\n\nTwo-step approaches consist of an *extractor* model, which extracts parts of the source document relevant to the input query, and an *abstractor* model,\nwhich synthesizes the extracted segments into a final summary.\n\nSee [extractors](extractors/README.md) directory for instructions and code for training and evaluating two-stage models.\n\n## Segment Encoder\n\nThe Segment Encoder is an end-to-end model that uses sparse local attention to achieve SOTA ROUGE scores on the QMSum dataset.\n\nTo [replicate](multiencoder/README.md#reproducing-qmsum-experiments) the QMSum experiments, or train and evaluate Segment Encoder\n[on your own dataset](multiencoder/README.md#running-on-your-own-datasets), see the \n [multiencoder](multiencoder/README.md) directory.\n\n## Citation\n\nWhen referencing this repository, please cite [this paper](https://arxiv.org/abs/2112.07637):\n\n```bibtex\n@misc{vig-etal-2021-exploring,\n      title={Exploring Neural Models for Query-Focused Summarization}, \n      author={Jesse Vig and Alexander R. Fabbri and Wojciech Kry{\\'s}ci{\\'n}ski and Chien-Sheng Wu and Wenhao Liu},\n      year={2021},\n      eprint={2112.07637},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2112.07637}\n}\n```\n\n## License\n\nThis repository is released under the [BSD-3 License](LICENSE.txt).\n\n\n\n\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsalesforce%2Fquery-focused-sum","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsalesforce%2Fquery-focused-sum","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsalesforce%2Fquery-focused-sum/lists"}