Table Retrieval May Not Necessitate Table-specific Model Design

05/19/2022
by   Zhiruo Wang, et al.
0

Tables are an important form of structured data for both human and machine readers alike, providing answers to questions that cannot, or cannot easily, be found in texts. Recent work has designed special models and training paradigms for table-related tasks such as table-based question answering and table retrieval. Though effective, they add complexity in both modeling and data acquisition compared to generic text solutions and obscure which elements are truly beneficial. In this work, we focus on the task of table retrieval, and ask: "is table-specific model design necessary for table retrieval, or can a simpler text-based model be effectively used to achieve a similar result?" First, we perform an analysis on a table-based portion of the Natural Questions dataset (NQ-table), and find that structure plays a negligible role in more than 70 Passage Retriever (DPR) based on text and a specialized Dense Table Retriever (DTR) that uses table-specific model designs. We find that DPR performs well without any table-specific design and training, and even achieves superior results compared to DTR when fine-tuned on properly linearized tables. 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. However, none of these yielded significant improvements, suggesting that table-specific model design may not be necessary for table retrieval.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/26/2021

Representations for Question Answering from Documents with Tables and Text

Tables in Web documents are pervasive and can be directly used to answer...
research
09/06/2021

Text-to-Table: A New Way of Information Extraction

We study a new problem setting of information extraction (IE), referred ...
research
05/31/2019

Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval

Tables contain valuable knowledge in a structured form. We employ neural...
research
08/09/2021

Multi-modal Retrieval of Tables and Texts Using Tri-encoder Models

Open-domain extractive question answering works well on textual data by ...
research
05/06/2021

TABBIE: Pretrained Representations of Tabular Data

Existing work on tabular representation learning jointly models tables a...
research
03/27/2023

TabIQA: Table Questions Answering on Business Document Images

Table answering questions from business documents has many challenges th...
research
01/31/2023

Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning

Table-based reasoning has shown remarkable progress in combining deep mo...

Please sign up or login with your details

Forgot password? Click here to reset