no code implementations • EMNLP 2017 • Abdalghani Abujabal, Rishiraj Saha Roy, Mohamed Yahya, Gerhard Weikum
We present QUINT, a live system for question answering over knowledge bases.
no code implementations • IJCNLP 2017 • David Ziegler, Abdalghani Abujabal, Rishiraj Saha Roy, Gerhard Weikum
This paper investigates the problem of answering compositional factoid questions over knowledge bases (KB) under efficiency constraints.
no code implementations • NAACL 2019 • Abdalghani Abujabal, Rishiraj Saha Roy, Mohamed Yahya, Gerhard Weikum
To bridge the gap between the capabilities of the state-of-the-art in factoid question answering (QA) and what users ask, we need large datasets of real user questions that capture the various question phenomena users are interested in, and the diverse ways in which these questions are formulated.
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.
1 code implementation • 8 Aug 2019 • Azin Ghazimatin, Rishiraj Saha Roy, Gerhard Weikum
We model the user's local neighborhood on the platform as an interaction graph, a form of heterogeneous information network constructed solely from information that is easily accessible to the concerned user.
no code implementations • 9 Aug 2019 • Zhen Jia, Abdalghani Abujabal, Rishiraj Saha Roy, Jannik Stroetgen, Gerhard Weikum
An important case, addressed here, is that of temporal questions, where cues for temporal relations need to be discovered and handled.
1 code implementation • 8 Oct 2019 • Philipp Christmann, Rishiraj Saha Roy, Abdalghani Abujabal, Jyotsna Singh, Gerhard Weikum
Fact-centric information needs are rarely one-shot; users typically ask follow-up questions to explore a topic.
1 code implementation • 7 Nov 2019 • Magdalena Kaiser, Rishiraj Saha Roy, Gerhard Weikum
Information needs around a topic cannot be satisfied in a single turn; users typically ask follow-up questions referring to the same theme and a system must be capable of understanding the conversational context of a request to retrieve correct answers.
1 code implementation • 19 Nov 2019 • Azin Ghazimatin, Oana Balalau, Rishiraj Saha Roy, Gerhard Weikum
Interpretable explanations for recommender systems and other machine learning models are crucial to gain user trust.
no code implementations • 4 Apr 2020 • Asia J. Biega, Jana Schmidt, Rishiraj Saha Roy
Translating verbose information needs into crisp search queries is a phenomenon that is ubiquitous but hardly understood.
no code implementations • 24 Apr 2020 • Rishiraj Saha Roy, Avishek Anand
The last few years have seen an explosion of research on the topic of automated question answering (QA), spanning the communities of information retrieval, natural language processing, and artificial intelligence.
1 code implementation • 27 Apr 2020 • Magdalena Kaiser, Rishiraj Saha Roy, Gerhard Weikum
In this work, we demonstrate CROWN (Conversational passage ranking by Reasoning Over Word Networks): an unsupervised yet effective system for conversational QA with passage responses, that supports several modes of context propagation over multiple turns.
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.
1 code implementation • 11 May 2021 • Magdalena Kaiser, Rishiraj Saha Roy, Gerhard Weikum
We present a reinforcement learning model, termed CONQUER, that can learn from a conversational stream of questions and reformulations.
1 code implementation • 11 May 2021 • Khanh Hiep Tran, Azin Ghazimatin, Rishiraj Saha Roy
Understanding why specific items are recommended to users can significantly increase their trust and satisfaction in the system.
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.
1 code implementation • 19 Aug 2021 • Philipp Christmann, Rishiraj Saha Roy, Gerhard Weikum
Answering complex questions over knowledge bases (KB-QA) faces huge input data with billions of facts, involving millions of entities and thousands of predicates.
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.
no code implementations • 25 Apr 2022 • Philipp Christmann, Rishiraj Saha Roy, Gerhard Weikum
Conversational question answering (ConvQA) tackles sequential information needs where contexts in follow-up questions are left implicit.
1 code implementation • 2 May 2023 • Philipp Christmann, Rishiraj Saha Roy, Gerhard Weikum
In conversational question answering, users express their information needs through a series of utterances with incomplete context.
no code implementations • 21 Jun 2023 • Philipp Christmann, Rishiraj Saha Roy, Gerhard Weikum
Fact-centric question answering (QA) often requires access to multiple, heterogeneous, information sources.
no code implementations • 20 Oct 2023 • Magdalena Kaiser, Rishiraj Saha Roy, Gerhard Weikum
This implies that training is limited to surface forms seen in the respective datasets, and evaluation is on a small set of held-out questions.