{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mt4crossoie-multi-stage-tuning-for-cross","title":"MT4CrossOIE: Multi-stage Tuning for Cross-lingual Open Information Extraction","arxiv_id":"2308.06552","date":"2023-08-12","proceeding":null,"authors":["Tongliang Li","Zixiang Wang","Linzheng Chai","Jian Yang","Jiaqi Bai","Yuwei Yin","Jiaheng Liu","Hongcheng Guo","Liqun Yang","Hebboul Zine el-abidine","Zhoujun Li"],"abstract":"Cross-lingual open information extraction aims to extract structured information from raw text across multiple languages. Previous work uses a shared cross-lingual pre-trained model to handle the different languages but underuses the potential of the language-specific representation. In this paper, we propose an effective multi-stage tuning framework called MT4CrossIE, designed for enhancing cross-lingual open information extraction by injecting language-specific knowledge into the shared model. Specifically, the cross-lingual pre-trained model is first tuned in a shared semantic space (e.g., embedding matrix) in the fixed encoder and then other components are optimized in the second stage. After enough training, we freeze the pre-trained model and tune the multiple extra low-rank language-specific modules using mixture-of-LoRAs for model-based cross-lingual transfer. In addition, we leverage two-stage prompting to encourage the large language model (LLM) to annotate the multi-lingual raw data for data-based cross-lingual transfer. The model is trained with multi-lingual objectives on our proposed dataset OpenIE4++ by combing the model-based and data-based transfer techniques. Experimental results on various benchmarks emphasize the importance of aggregating multiple plug-in-and-play language-specific modules and demonstrate the effectiveness of MT4CrossIE in cross-lingual OIE\\footnote{\\url{https://github.com/CSJianYang/Multilingual-Multimodal-NLP}}.","url_abs":"https://arxiv.org/abs/2308.06552v2","url_pdf":"https://arxiv.org/pdf/2308.06552v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mt4crossoie-multi-stage-tuning-for-cross","repo_url":"https://github.com/csjianyang/multilingual-multimodal-nlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"mt4crossoie-multi-stage-tuning-for-cross","repo_url":"https://github.com/CSJianYang/Multilingual-Multimodal-NLP/tree/main/MT4CrossOIE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"open-information-extraction","task_name":"Open Information Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.06552","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}