{"id":18950141,"url":"https://github.com/salesforce/fewxc","last_synced_at":"2025-07-30T23:37:50.959Z","repository":{"id":231085085,"uuid":"617694361","full_name":"salesforce/FewXC","owner":"salesforce","description":"Official code and data release for Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning, accepted by findings of EACL 2024.","archived":false,"fork":false,"pushed_at":"2025-05-29T13:03:32.000Z","size":46,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-06-01T23:24:22.020Z","etag":null,"topics":["cross-lingual","nlp","task-oriented-dialogue"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2304.01295","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/salesforce.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-03-22T23:07:45.000Z","updated_at":"2025-05-29T13:03:35.000Z","dependencies_parsed_at":"2025-05-29T12:45:51.041Z","dependency_job_id":null,"html_url":"https://github.com/salesforce/FewXC","commit_stats":null,"previous_names":["salesforce/fewxc"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/salesforce/FewXC","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2FFewXC","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2FFewXC/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2FFewXC/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2FFewXC/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/salesforce","download_url":"https://codeload.github.com/salesforce/FewXC/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2FFewXC/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267960975,"owners_count":24172513,"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","status":"online","status_checked_at":"2025-07-30T02:00:09.044Z","response_time":70,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["cross-lingual","nlp","task-oriented-dialogue"],"created_at":"2024-11-08T13:21:12.354Z","updated_at":"2025-07-30T23:37:50.931Z","avatar_url":"https://github.com/salesforce.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# FewXC (Few-shot Cross-lingual Conversational Research)\nOfficial code and data release for [Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning](https://arxiv.org/abs/2304.01295), accepted by findings of EACL 2024.\n\n## XSGD Data\nhttps://console.cloud.google.com/storage/browser/multilingual-sgd-data-research\n\n## MASSIVE Data\nPlease refer to https://github.com/alexa/massive for data and pre-processing pipeline.\n\n## Backbone Model\nXLM-RoBERTa series, https://huggingface.co/docs/transformers/model_doc/xlm-roberta\n\n## Examples\n```python\n# NLI style intent classificaiton with MASSIVE dataset\nCUDA_VISIBLE_DEVICES=0  python xlmr_massive_finetuning_nli.py \\\n--training_strategy 5 \\\n--learning_rate 1e-5 \\\n--training_data /export/home/xclm/1.1/parsed_data.train \\\n--intent_schema /export/home/xclm/1.1/parsed_data.intents \\\n--slot_schema /export/home/xclm/1.1/parsed_data.slots \\\n--dev_data /export/home/xclm/1.1/parsed_data.dev \\\n--prefix # turn on prefix tuning\n\n# Regular intent classfication with MASSIVE dataset\nCUDA_VISIBLE_DEVICES=0  python xlmr_massive_finetuning_vanilla.py \\\n--training_strategy 5 \\\n--learning_rate 1e-5 \\\n--training_data /export/home/xclm/1.1/parsed_data.train \\\n--intent_schema /export/home/xclm/1.1/parsed_data.intents \\\n--slot_schema /export/home/xclm/1.1/parsed_data.slots \\\n--dev_data /export/home/xclm/1.1/parsed_data.dev \\\n--prefix \\\n--task intent,slot\n```\n\n## Citation\n```\n@inproceedings{\nanonymous2024efficiently,\ntitle={Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning},\nauthor={Lifu Tu, Jin Qu, Semih Yavuz, Shafiq Joty, Wenhao Liu, Caiming Xiong, Yingbo Zhou},\nbooktitle={18th Conference of the European Chapter of the Association for Computational Linguistics},\nyear={2024},\nurl={https://openreview.net/forum?id=Lb4qW0NiIb}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsalesforce%2Ffewxc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsalesforce%2Ffewxc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsalesforce%2Ffewxc/lists"}