تقرير
Large Language Models are Complex Table Parsers
| العنوان: | Large Language Models are Complex Table Parsers |
|---|---|
| المؤلفون: | Zhao, Bowen, Ji, Changkai, Zhang, Yuejie, He, Wen, Wang, Yingwen, Wang, Qing, Feng, Rui, Zhang, Xiaobo |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence |
| الوصف: | With the Generative Pre-trained Transformer 3.5 (GPT-3.5) exhibiting remarkable reasoning and comprehension abilities in Natural Language Processing (NLP), most Question Answering (QA) research has primarily centered around general QA tasks based on GPT, neglecting the specific challenges posed by Complex Table QA. In this paper, we propose to incorporate GPT-3.5 to address such challenges, in which complex tables are reconstructed into tuples and specific prompt designs are employed for dialogues. Specifically, we encode each cell's hierarchical structure, position information, and content as a tuple. By enhancing the prompt template with an explanatory description of the meaning of each tuple and the logical reasoning process of the task, we effectively improve the hierarchical structure awareness capability of GPT-3.5 to better parse the complex tables. Extensive experiments and results on Complex Table QA datasets, i.e., the open-domain dataset HiTAB and the aviation domain dataset AIT-QA show that our approach significantly outperforms previous work on both datasets, leading to state-of-the-art (SOTA) performance. Comment: EMNLP 2023 Main |
| نوع الوثيقة: | Working Paper |
| الوصول الحر: | http://arxiv.org/abs/2312.11521Test |
| رقم الانضمام: | edsarx.2312.11521 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |