5 papers
The ReQAP System for Question Answering over Personal Information
Philipp Christmann, Gerhard Weikum
Personal information is abundant on users' devices, from structured data in calendar, shopping records or fitness tools, to unstructured contents in mail and social media posts. Th…
Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data
Philipp Christmann, Gerhard Weikum
Question answering over mixed sources, like text and tables, has been advanced by verbalizing all contents and encoding it with a language model. A prominent case of such heterogen…
Preference-based Learning with Retrieval Augmented Generation for Conversational Question Answering
Magdalena Kaiser, Gerhard Weikum
Conversational Question Answering (ConvQA) involves multiple subtasks, i) to understand incomplete questions in their context, ii) to retrieve relevant information, and iii) to gen…
Large Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questions
Aidan Hogan, Xin Luna Dong, Denny VrandeÄiÄ +1
Much has been discussed about how Large Language Models, Knowledge Graphs and Search Engines can be combined in a synergistic manner. A dimension largely absent from current academ…
RAG-based Question Answering over Heterogeneous Data and Text
Philipp Christmann, Gerhard Weikum
This article presents the QUASAR system for question answering over unstructured text, structured tables, and knowledge graphs, with unified treatment of all sources. The system ad…