activity
20162021
most citedEvaluating the Impact of Knowledge Graph Context on Entity Disambiguation Models

32 citations · 33 across the 5 of their papers we have counts for

collaborators

13 papers

cs.CL20211 cited

KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction

Abhishek Nadgeri, Anson Bastos, Kuldeep Singh +4

We present a novel method for relation extraction (RE) from a single sentence, mapping the sentence and two given entities to a canonical fact in a knowledge graph (KG). Especially…

cs.CL2021

Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks

Endri Kacupaj, Joan Plepi, Kuldeep Singh +3

This paper addresses the task of (complex) conversational question answering over a knowledge graph. For this task, we propose LASAGNE (muLti-task semAntic parSing with trAnsformer…

cs.CL2021

ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation

Endri Kacupaj, Barshana Banerjee, Kuldeep Singh +1

This paper presents ParaQA, a question answering (QA) dataset with multiple paraphrased responses for single-turn conversation over knowledge graphs (KG). The dataset was created u…

cs.CL2021

Context Transformer with Stacked Pointer Networks for Conversational Question Answering over Knowledge Graphs

Joan Plepi, Endri Kacupaj, Kuldeep Singh +2

Neural semantic parsing approaches have been widely used for Question Answering (QA) systems over knowledge graphs. Such methods provide the flexibility to handle QA datasets with…

cs.CL2021

Better Call the Plumber: Orchestrating Dynamic Information Extraction Pipelines

Mohamad Yaser Jaradeh, Kuldeep Singh, Markus Stocker +2

In the last decade, a large number of Knowledge Graph (KG) information extraction approaches were proposed. Albeit effective, these efforts are disjoint, and their collective stren…

cs.CL2021

CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata

Manoj Prabhakar Kannan Ravi, Kuldeep Singh, Isaiah Onando Mulang' +3

In this paper, we propose CHOLAN, a modular approach to target end-to-end entity linking (EL) over knowledge bases. CHOLAN consists of a pipeline of two transformer-based models in…