Joint Learning of Representations for Web-tables, Entities and Types using Graph Convolutional Network

Abstract

Existing approaches for table annotation with entities and types either capture the structure of table using graphical models, or learn embeddings of table entries without accounting for the complete syntactic structure. We propose TabGCN, which uses Graph Convolutional Networks to capture the complete structure of tables, knowledge graph and the training annotations, and jointly learns embeddings for table elements as well as the entities and types. To account for knowledge incompleteness, TabGCN's embeddings can be used to discover new entities and types. Using experiments on 5 benchmark datasets, we show that TabGCN significantly outperforms multiple state-of-the-art baselines for table annotation, while showing promising performance on downstream table-related applications.

Is My Model Using the Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning

“…Additionally, probes defined on one tabular dataset (INFOTABS in our case) can be easily ported to other tabular datasets such as WikiTableQA (Pasupat and Liang, 2015), TabFact (Chen et al, 2020b), HybridQA (Chen et al, 2020c;Zayats et al, 2021;Oguz et al, 2020), OpenTableQA (Chen et al, 2021), ToTTo (Parikh et al, 2020), Turing Tables (Yoran et al, 2021, and Logic-Table (Chen et al, 2020a). Moreover, such probes can be used to better understand the behavior of various tabular reasoning models (e.g., Müller et al, 2021;Herzig et al, 2020;Yin et al, 2020;Iida et al, 2021;Pramanick and Bhattacharya, 2021;Glass et al, 2021;and others).…”

Column-Type Prediction for Web Tables Powered by Knowledge Base and Text

“…The tabular data-prediction task aims to match table elements with semantic types, including cell-entity and column-type predictions. Recent methods mainly focus on columntype prediction [7][8][9][11][12][13], except that PGM [10], TabGCN [14], and Meimei [15] simultaneously finish these two tasks. However, TabGCN requires a complex algorithm to transform data into graphs and is sensitive to dirty data.…”

“…Representation learning. Nowadays, the representation learning approaches can be divided into three categories: discrete methods [16,17], distributed methods [18,19], and deep learning methods [7,8,11,12,14]. The discrete representation methods use discrete vectors for representation, which cannot express the semantic information of words and will encounter the problem of sparse data and loss of information.…”

Right for the Right Reason: Evidence Extraction for Trustworthy Tabular Reasoning

“…Tabular Reasoning Many recent studies investigate various NLP tasks on semi-structured tabular data, including tabular NLI and fact verification (Chen et al, 2020b;, various question answering and semantic parsing tasks (Zhang and Balog, 2020;Pasupat and Liang, 2015;Krishnamurthy et al, 2017;Abbas et al, 2016;Sun et al, 2016;Chen et al, 2020c;Lin et al, 2020;Zayats et al, 2021;Oguz et al, 2020;Chen et al, 2021, inter alia), and table-to-text generation (e.g., Parikh et al, 2020;Nan et al, 2021;Yoran et al, 2021;Chen et al, 2020a). Several strategies for representing Wikipedia relational tables are proposed, such as Ta-ble2vec (Deng et al, 2019), TAPAS (Herzig et al, 2020), TaBERT (Yin et al, 2020), TabStruc (Zhang et al, 2020a), TABBIE (Iida et al, 2021), TabGCN (Pramanick and Bhattacharya, 2021) and RCI (Glass et al, 2021). Yu et al (2018; and Neeraja et al (2021) study pre-training for improving tabular inference.…”