activity
20182022
most citedPyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings

89 citations · 287 across the 19 of their papers we have counts for

collaborators

41 papers

cs.CL20221 cited

Contrastive Representation Learning for Conversational Question Answering over Knowledge Graphs

Endri Kacupaj, Kuldeep Singh, Maria Maleshkova +1

This paper addresses the task of conversational question answering (ConvQA) over knowledge graphs (KGs). The majority of existing ConvQA methods rely on full supervision signals wi…

cs.CL20221 cited

DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation

Md Rashad Al Hasan Rony, Ricardo Usbeck, Jens Lehmann

Task-oriented dialogue generation is challenging since the underlying knowledge is often dynamic and effectively incorporating knowledge into the learning process is hard. It is pa…

cs.CL20221 cited

RoMe: A Robust Metric for Evaluating Natural Language Generation

Md Rashad Al Hasan Rony, Liubov Kovriguina, Debanjan Chaudhuri +2

Evaluating Natural Language Generation (NLG) systems is a challenging task. Firstly, the metric should ensure that the generated hypothesis reflects the reference's semantics. Seco…

cs.AI202248 cited

Time-aware Graph Neural Networks for Entity Alignment between Temporal Knowledge Graphs

Chengjin Xu, Fenglong Su, Jens Lehmann

Entity alignment aims to identify equivalent entity pairs between different knowledge graphs (KGs). Recently, the availability of temporal KGs (TKGs) that contain time information…

cs.AI202223 cited

Geometric Algebra based Embeddings for Static and Temporal Knowledge Graph Completion

Chengjin Xu, Mojtaba Nayyeri, Yung-Yu Chen +1

Recent years, Knowledge Graph Embeddings (KGEs) have shown promising performance on link prediction tasks by mapping the entities and relations from a Knowledge Graph (KG) into a g…

cs.LG2021

Improving Inductive Link Prediction Using Hyper-Relational Facts

Mehdi Ali, Max Berrendorf, Mikhail Galkin +4

For many years, link prediction on knowledge graphs (KGs) has been a purely transductive task, not allowing for reasoning on unseen entities. Recently, increasing efforts are put i…