Complex Temporal Question Answering on Knowledge Graphs

1 code implementation • 18 Sep 2021 • Zhen Jia, Soumajit Pramanik, Rishiraj Saha Roy, Gerhard Weikum

This work presents EXAQT, the first end-to-end system for answering complex temporal questions that have multiple entities and predicates, and associated temporal conditions.

16k Entity Embeddings +2

UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text

1 code implementation • 19 Aug 2021 • Soumajit Pramanik, Jesujoba Alabi, Rishiraj Saha Roy, Gerhard Weikum

Some of these systems incorporate textual sources as additional evidence for the answering process, but cannot compute answers that are present in text alone.

Knowledge Graphs Question Answering

ELIXIR: Learning from User Feedback on Explanations to Improve Recommender Models

1 code implementation • 15 Feb 2021 • Azin Ghazimatin, Soumajit Pramanik, Rishiraj Saha Roy, Gerhard Weikum

System-provided explanations for recommendations are an important component towards transparent and trustworthy AI.

Answering Complex Questions by Joining Multi-Document Evidence with Quasi Knowledge Graphs

no code implementations • 1 Aug 2019 • Xiaolu Lu, Soumajit Pramanik, Rishiraj Saha Roy, Abdalghani Abujabal, Yafang Wang, Gerhard Weikum

Direct answering of questions that involve multiple entities and relations is a challenge for text-based QA.

Knowledge Graphs