Structural Deep Encoding for Table Question Answering

• URL: http://arxiv.org/abs/2503.01457v1
• Date: Mon, 03 Mar 2025 12:16:43 GMT
• Title: Structural Deep Encoding for Table Question Answering
• Authors: Raphaël Mouravieff, Benjamin Piwowarski, Sylvain Lamprier,
• Abstract summary: Transformers-based architectures often flatten the table structure.<n>This can lead to the loss of essential inter-dependencies between rows, columns, and cells.<n>We introduce a set of novel sparse attention mask designs for tabular data, that not only enhance computational efficiency but also preserve structural integrity.
• Score: 19.58143979341734
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although Transformers-based architectures excel at processing textual information, their naive adaptation for tabular data often involves flattening the table structure. This simplification can lead to the loss of essential inter-dependencies between rows, columns, and cells, while also posing scalability challenges for large tables. To address these issues, prior works have explored special tokens, structured embeddings, and sparse attention patterns. In this paper, we conduct a comprehensive analysis of tabular encoding techniques, which highlights the crucial role of attention sparsity in preserving structural information of tables. We also introduce a set of novel sparse attention mask designs for tabular data, that not only enhance computational efficiency but also preserve structural integrity, leading to better overall performance.

Related papers

• TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models [57.005158277893194]
  TableLoRA is a module designed to improve LLMs' understanding of table structure during PEFT. It incorporates special tokens for serializing tables with special token encoder and uses 2D LoRA to encode low-rank information on cell positions.
  arXiv  Detail & Related papers  (2025-03-06T12:50:14Z)
• Theme-Explanation Structure for Table Summarization using Large Language Models: A Case Study on Korean Tabular Data [1.0621665950143144]
  This paper proposes the Theme-Explanation Structure-based Table Summarization pipeline (Tabular-TX)<n>It generates summary sentences following a structured format, where the Theme Part appears as an adverbial phrase, and the Explanation Part follows as a predictive clause.<n> Experimental results demonstrate that Tabular-TX significantly outperforms conventional fine-tuning-based methods.
  arXiv  Detail & Related papers  (2025-01-17T08:42:49Z)
• Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding [42.841205217768106]
  "Tree-of-Table" is a novel approach designed to enhance LLMs' reasoning capabilities over large and complex tables. We show that Tree-of-Table sets a new benchmark with superior performance, showcasing remarkable efficiency and generalization capabilities in large-scale table reasoning.
  arXiv  Detail & Related papers  (2024-11-13T11:02:04Z)
• TableRAG: Million-Token Table Understanding with Language Models [53.039560091592215]
  TableRAG is a Retrieval-Augmented Generation (RAG) framework specifically designed for LM-based table understanding.<n>TableRAG leverages query expansion combined with schema and cell retrieval to pinpoint crucial information before providing it to the LMs.<n>Our results demonstrate that TableRAG achieves the highest retrieval quality, leading to the new state-of-the-art performance on large-scale table understanding.
  arXiv  Detail & Related papers  (2024-10-07T04:15:02Z)
• 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)
• UniTabNet: Bridging Vision and Language Models for Enhanced Table Structure Recognition [55.153629718464565]
  We introduce UniTabNet, a novel framework for table structure parsing based on the image-to-text model. UniTabNet employs a divide-and-conquer'' strategy, utilizing an image-to-text model to decouple table cells and integrating both physical and logical decoders to reconstruct the complete table structure.
  arXiv  Detail & Related papers  (2024-09-20T01:26:32Z)
• PixT3: Pixel-based Table-To-Text Generation [66.96636025277536]
  We present PixT3, a multimodal table-to-text model that overcomes the challenges of linearization and input size limitations. Experiments on the ToTTo and Logic2Text benchmarks show that PixT3 is competitive and superior to generators that operate solely on text.
  arXiv  Detail & Related papers  (2023-11-16T11:32:47Z)
• Multi-Layer Attention-Based Explainability via Transformers for Tabular Data [11.866061471514582]
  We propose a graph-oriented attention-based explainability method for tabular data. We take into account the attention matrices of all heads and layers as a whole. To assess the quality of multi-layer attention-based explanations, we compare them with popular attention-, gradient-, and perturbation-based explanability methods.
  arXiv  Detail & Related papers  (2023-02-28T03:28:18Z)
• Efficient Information Sharing in ICT Supply Chain Social Network via Table Structure Recognition [12.79419287446918]
  Table Structure Recognition (TSR) aims to represent tables with complex structures in a machine-interpretable format. We implement our proposed method based on Faster-RCNN and achieve 94.79% on mean Average Precision (AP)
  arXiv  Detail & Related papers  (2022-11-03T20:03:07Z)
• Table Retrieval May Not Necessitate Table-specific Model Design [83.27735758203089]
  We focus on the task of table retrieval, and ask: "is table-specific model design necessary for table retrieval?" Based on an analysis on a table-based portion of the Natural Questions dataset (NQ-table), we find that structure plays a negligible role in more than 70% of the cases. We then experiment with three modules to explicitly encode table structures, namely auxiliary row/column embeddings, hard attention masks, and soft relation-based attention biases. None of these yielded significant improvements, suggesting that table-specific model design may not be necessary for table retrieval.
  arXiv  Detail & Related papers  (2022-05-19T20:35:23Z)
• TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition [76.06530816349763]
  We propose an end-to-end trainable table graph reconstruction network (TGRNet) for table structure recognition. Specifically, the proposed method has two main branches, a cell detection branch and a cell logical location branch, to jointly predict the spatial location and the logical location of different cells.
  arXiv  Detail & Related papers  (2021-06-20T01:57:05Z)
• TUTA: Tree-based Transformers for Generally Structured Table Pre-training [47.181660558590515]
  Recent attempts on table understanding mainly focus on relational tables, yet overlook to other common table structures. We propose TUTA, a unified pre-training architecture for understanding generally structured tables. TUTA is highly effective, achieving state-of-the-art on five widely-studied datasets.
  arXiv  Detail & Related papers  (2020-10-21T13:22:31Z)
• Identifying Table Structure in Documents using Conditional Generative Adversarial Networks [0.0]
  In many industries and in academic research, information is primarily transmitted in the form of unstructured documents. We propose a top-down approach, first using a conditional generative adversarial network to map a table image into a standardised skeleton' table form. We then deriving latent table structure using xy-cut projection and Genetic Algorithm optimisation.
  arXiv  Detail & Related papers  (2020-01-13T20:42:40Z)

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.