no code implementations • 28 Feb 2023 • Simon Gottschalk, Endri Kacupaj, Sara Abdollahi, Diego Alves, Gabriel Amaral, Elisavet Koutsiana, Tin Kuculo, Daniela Major, Caio Mello, Gullal S. Cheema, Abdul Sittar, Swati, Golsa Tahmasebzadeh, Gaurish Thakkar
Accessing and understanding contemporary and historical events of global impact such as the US elections and the Olympic Games is a major prerequisite for cross-lingual event analytics that investigate event causes, perception and consequences across country borders.
1 code implementation • 9 Oct 2022 • Endri Kacupaj, Kuldeep Singh, Maria Maleshkova, Jens Lehmann
The majority of existing ConvQA methods rely on full supervision signals with a strict assumption of the availability of gold logical forms of queries to extract answers from the KG.
no code implementations • 13 Aug 2022 • Endri Kacupaj, Kuldeep Singh, Maria Maleshkova, Jens Lehmann
We introduce a new dataset for conversational question answering over Knowledge Graphs (KGs) with verbalized answers.
3 code implementations • 24 Jun 2021 • Endri Kacupaj, Shyamnath Premnadh, Kuldeep Singh, Jens Lehmann, Maria Maleshkova
The VOGUE framework attempts to generate a verbalized answer using a hybrid approach through a multi-task learning paradigm.
1 code implementation • 30 Apr 2021 • Golsa Tahmasebzadeh, Endri Kacupaj, Eric Müller-Budack, Sherzod Hakimov, Jens Lehmann, Ralph Ewerth
The first module is a state-of-the-art model for geolocation estimation of images.
1 code implementation • EACL 2021 • Endri Kacupaj, Joan Plepi, Kuldeep Singh, Harsh Thakkar, Jens Lehmann, Maria Maleshkova
For this task, we propose LASAGNE (muLti-task semAntic parSing with trAnsformer and Graph atteNtion nEtworks).
1 code implementation • 22 Mar 2021 • Aynur Guluzade, Endri Kacupaj, Maria Maleshkova
We evaluate DARLING through link prediction for treatments and medicines, on a medical KG constructed from EMR data, and illustrate its superior performance compared to existing KG embedding models.
1 code implementation • 13 Mar 2021 • Endri Kacupaj, Barshana Banerjee, Kuldeep Singh, Jens Lehmann
This paper presents ParaQA, a question answering (QA) dataset with multiple paraphrased responses for single-turn conversation over knowledge graphs (KG).
1 code implementation • 13 Mar 2021 • Joan Plepi, Endri Kacupaj, Kuldeep Singh, Harsh Thakkar, Jens Lehmann
In this work, we propose a novel framework named CARTON, which performs multi-task semantic parsing for handling the problem of conversational question answering over a large-scale knowledge graph.
1 code implementation • 14 Aug 2020 • Jason Armitage, Endri Kacupaj, Golsa Tahmasebzadeh, Swati, Maria Maleshkova, Ralph Ewerth, Jens Lehmann
We demonstrate the value of the resource in developing novel applications in the digital humanities with a motivating use case and specify a benchmark set of tasks to retrieve modalities and locate entities in the dataset.