Summary of Piece Of Table: a Divide-and-conquer Approach For Selecting Subtables in Table Question Answering, by Wonjin Lee et al.
Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answering
by Wonjin Lee, Kyumin Kim, Sungjae Lee, Jihun Lee, Kwang In Kim
First submitted to arxiv on: 10 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel framework called PieTa for question answering (QA) in tables. Traditional language models are not well-suited for tabular data due to structural differences and limitations in understanding context across large tables. PieTa addresses these challenges through an iterative process of dividing tables into smaller windows, selecting relevant cells using language models, and merging them into a subtable. This multi-resolution approach captures dependencies across multiple rows and columns while avoiding the limitations caused by long context inputs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary PieTa is a new framework for question answering in tables that helps machines understand complex data structures better. The problem is that language models were designed to work with text, not tables. PieTa uses an iterative process to break down big tables into smaller parts, select important cells using language models, and combine them into a smaller table. This way, it can capture relationships between different rows and columns in the table. |
Keywords
» Artificial intelligence » Question answering
