Search Results for author:
Found 9 papers, 3 papers with code
Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data
Question answering over mixed sources, like text and tables, has been advanced by verbalizing all contents and encoding it with a language model.
RAG-based Question Answering over Heterogeneous Data and Text
This article presents the QUASAR system for question answering over unstructured text, structured tables, and knowledge graphs, with unified treatment of all sources.
Ranked #2 on
Question Answering
on TimeQuestions
Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision
Long-form question answering (LFQA) aims at generating in-depth answers to end-user questions, providing relevant information beyond the direct answer.
Faithful Temporal Question Answering over Heterogeneous Sources
The method has three stages: (i) understanding the question and its temporal conditions, (ii) retrieving evidence from all sources, and (iii) faithfully answering the question.
Ranked #1 on
Question Answering
on TIQ
CompMix: A Benchmark for Heterogeneous Question Answering
Fact-centric question answering (QA) often requires access to multiple, heterogeneous, information sources.
Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural Networks
In conversational question answering, users express their information needs through a series of utterances with incomplete context.
Ranked #2 on
Question Answering
on TIQ
Conversational Question Answering on Heterogeneous Sources
Conversational question answering (ConvQA) tackles sequential information needs where contexts in follow-up questions are left implicit.
Ranked #15 on
Question Answering
on TimeQuestions
Beyond NED: Fast and Effective Search Space Reduction for Complex Question Answering over Knowledge Bases
Answering complex questions over knowledge bases (KB-QA) faces huge input data with billions of facts, involving millions of entities and thousands of predicates.
Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion
Fact-centric information needs are rarely one-shot; users typically ask follow-up questions to explore a topic.
