“…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.…”