QUEST is a method that can answer complex questions directly from textual sources on-the-fly, by computing similarity joins over partial results from different documents. It is completely unsupervised, avoiding training-data bottlenecks and being able to cope with rapidly evolving adhoc topics and formulation style in user questions. QUEST builds a noisy quasi KG with node and edge weights, consisting of dynamically retrieved entity names and relational phrases. It augments this graph with types and semantic alignments, and computes the best answers by an algorithm for Group Steiner Trees.
Our code and data are available here.
To cite QUEST:
-
Xiaolu Lu, Soumajit Pramanik, Rishiraj Saha Roy, Abdalghani Abujabal, Yafang Wang and Gerhard Weikum, "Answering Complex Questions by Joining Multi-Document Evidence with Quasi Knowledge Graphs", In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval 2019 (SIGIR '19), Paris, France, 21 - 25 July 2019, pages 105 - 114.
For feedback and clarifications, please contact: