Large Language Models are Complex Table Parsers

• URL: http://arxiv.org/abs/2312.11521v1
• Date: Wed, 13 Dec 2023 01:34:42 GMT
• Title: Large Language Models are Complex Table Parsers
• Authors: Bowen Zhao, Changkai Ji, Yuejie Zhang, Wen He, Yingwen Wang, Qing Wang, Rui Feng, Xiaobo Zhang
• Abstract summary: We propose to incorporate GPT-3.5 to address the challenges posed by Complex Table QA. Specifically, we encode each cell's hierarchical structure, position information and content as datasets. By enhancing the prompt template with an explanatory description of the meaning of each task, we effectively improve the hierarchical awareness structure capability.
• Score: 26.66460264175336
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data [61.936320820180875]
  Large language models (LLMs) have become increasingly pivotal across various domains. BabelBench is an innovative benchmark framework that evaluates the proficiency of LLMs in managing multimodal multistructured data with code execution. Our experimental findings on BabelBench indicate that even cutting-edge models like ChatGPT 4 exhibit substantial room for improvement.
  arXiv  Detail & Related papers  (2024-10-01T15:11:24Z)
• Knowledge in Triples for LLMs: Enhancing Table QA Accuracy with Semantic Extraction [1.0968343822308813]
  This paper proposes a novel approach that extracts triples straightforward from tabular data and integrates it with a retrieval-augmented generation (RAG) model to enhance the accuracy, coherence, and contextual richness of responses generated by a fine-tuned GPT-3.5-turbo-0125 model. Our approach significantly outperforms existing baselines on the FeTaQA dataset, particularly excelling in Sacre-BLEU and ROUGE metrics.
  arXiv  Detail & Related papers  (2024-09-21T16:46:15Z)
• DocTabQA: Answering Questions from Long Documents Using Tables [16.3130447078524]
  We study a new problem setting of question answering (QA), referred to as DocTabQA. Within this setting, given a long document, the goal is to respond to questions by organizing the answers into structured tables derived directly from the document's content. We introduce the QTabA dataset, encompassing 300 financial documents, accompanied by manually annotated 1.5k question-table pairs. We present a two-stage framework, called DocTabTalk, which initially retrieves relevant sentences from extensive documents and subsequently generates hierarchical tables based on these identified sentences.
  arXiv  Detail & Related papers  (2024-08-21T10:01:12Z)
• SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding [55.48936731641802]
  We present the SRFUND, a hierarchically structured multi-task form understanding benchmark. SRFUND provides refined annotations on top of the original FUNSD and XFUND datasets. The dataset includes eight languages including English, Chinese, Japanese, German, French, Spanish, Italian, and Portuguese.
  arXiv  Detail & Related papers  (2024-06-13T02:35:55Z)
• TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools [51.576974932743596]
  Large Language Models (LLMs) often do not perform well on queries that require the aggregation of information across texts. TACT contains challenging instructions that demand stitching information scattered across one or more texts. We construct this dataset by leveraging an existing dataset of texts and their associated tables. We demonstrate that all contemporary LLMs perform poorly on this dataset, achieving an accuracy below 38%.
  arXiv  Detail & Related papers  (2024-06-05T20:32:56Z)
• Beyond Extraction: Contextualising Tabular Data for Efficient Summarisation by Language Models [0.0]
  The conventional use of the Retrieval-Augmented Generation architecture has proven effective for retrieving information from diverse documents. This research introduces an innovative approach to enhance the accuracy of complex table queries in RAG-based systems.
  arXiv  Detail & Related papers  (2024-01-04T16:16:14Z)
• Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework [5.351873055148804]
  Self-training framework generates diverse synthetic data with complex logic. We optimize the procedure using a "Table-Text Manipulator" to handle joint table-text reasoning scenarios. UCTRST achieves above 90% of the supervised model performance on different tasks and domains.
  arXiv  Detail & Related papers  (2022-12-20T09:15:03Z)
• Towards Complex Document Understanding By Discrete Reasoning [77.91722463958743]
  Document Visual Question Answering (VQA) aims to understand visually-rich documents to answer questions in natural language. We introduce a new Document VQA dataset, named TAT-DQA, which consists of 3,067 document pages and 16,558 question-answer pairs. We develop a novel model named MHST that takes into account the information in multi-modalities, including text, layout and visual image, to intelligently address different types of questions.
  arXiv  Detail & Related papers  (2022-07-25T01:43:19Z)
• TAGPRIME: A Unified Framework for Relational Structure Extraction [71.88926365652034]
  TAGPRIME is a sequence tagging model that appends priming words about the information of the given condition to the input text. With the self-attention mechanism in pre-trained language models, the priming words make the output contextualized representations contain more information about the given condition. Extensive experiments and analyses on three different tasks that cover ten datasets across five different languages demonstrate the generality and effectiveness of TAGPRIME.
  arXiv  Detail & Related papers  (2022-05-25T08:57:46Z)
• Topic Transferable Table Question Answering [33.54533181098762]
  Weakly-supervised table question-answering(TableQA) models have achieved state-of-art performance by using pre-trained BERT transformer to jointly encoding a question and a table to produce structured query for the question. In practical settings TableQA systems are deployed over table corpora having topic and word distributions quite distinct from BERT's pretraining corpus. We propose T3QA (Topic Transferable Table Question Answering) as a pragmatic adaptation framework for TableQA.
  arXiv  Detail & Related papers  (2021-09-15T15:34:39Z)
• Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models [56.268862325167575]
  This paper presents an empirical study of conversational question reformulation (CQR) with sequence-to-sequence architectures and pretrained language models (PLMs) We leverage PLMs to address the strong token-to-token independence assumption made in the common objective, maximum likelihood estimation, for the CQR task. We evaluate fine-tuned PLMs on the recently-introduced CANARD dataset as an in-domain task and validate the models using data from the TREC 2019 CAsT Track as an out-domain task.
  arXiv  Detail & Related papers  (2020-04-04T11:07:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.