activity
20192021
most citedType Prediction Systems

1 citations · 1 across the 1 of their papers we have counts for

collaborators

5 papers

cs.CL20211 cited

Type Prediction Systems

Sarthak Dash, Nandana Mihindukulasooriya, Alfio Gliozzo +1

Inferring semantic types for entity mentions within text documents is an important asset for many downstream NLP tasks, such as Semantic Role Labelling, Entity Disambiguation, Know…

cs.CL2020

Open Knowledge Graphs Canonicalization using Variational Autoencoders

Sarthak Dash, Gaetano Rossiello, Nandana Mihindukulasooriya +2

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 appro…

cs.CL2019

Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation

Sarthak Dash, Michael R. Glass, Alfio Gliozzo +1

In this paper, we propose a fully automated system to extend knowledge graphs using external information from web-scale corpora. The designed system leverages a deep learning based…

cs.AI2019

Hypernym Detection Using Strict Partial Order Networks

Sarthak Dash, Md Faisal Mahbub Chowdhury, Alfio Gliozzo +2

This paper introduces Strict Partial Order Networks (SPON), a novel neural network architecture designed to enforce asymmetry and transitive properties as soft constraints. We appl…

cs.LG2019

Distributional Negative Sampling for Knowledge Base Completion

Sarthak Dash, Alfio Gliozzo

State-of-the-art approaches for Knowledge Base Completion (KBC) exploit deep neural networks trained with both false and true assertions: positive assertions are explicitly taken f…