← Search

Sarthak Dash

2 accepted papers

2022

Permutation Invariant Strategy Using Transformer Encoders for Table Understanding

NAACL 2022findings

Representing text in tables is essential for many business intelligence tasks such as semantic retrieval, data exploration and visualization, and question answering. Existing methods that leverage pretrained Transformer encoders range from a simple construction of pseudo-sentences by concatenating t…

2021

Open Knowledge Graphs Canonicalization using Variational Autoencoders

EMNLP 2021main

Noun phrases and Relation phrases in open knowledge graphs are not canonicalized, leading to an explosion of redundant and ambiguous subject-relation-object triples. Existing approaches to solve this problem take a two-step approach. First, they generate embedding representations for both noun and r…