Question Answering Over Temporal Knowledge Graphs

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pages 6663–6676 August 1–6, 2021. ©2021 Association for Computational Linguistics 6663 Question Answering Over Temporal Knowledge Graphs Apoorv Saxena Indian Institute of Science Bangalore apoorvsaxena@iisc.ac.in Soumen Chakrabarti Indian Institute of Technology Bombay soumen@cse.iitb.ac.in Partha Talukdar Google Research India partha@google.com Abstract Temporal Knowledge Graphs (Temporal KGs) extend regular Knowledge Graphs by provid- ing temporal scopes (e.g., start and end times) on each edge in the KG. While Question An- swering over KG (KGQA) has received some attention from the research community, QA over Temporal KGs (Temporal KGQA) is a relatively unexplored area. Lack of broad- coverage datasets has been another factor lim- iting progress in this area. We address this challenge by presenting CRONQUESTIONS, the largest known Temporal KGQA dataset, clearly stratified into buckets of structural com- plexity. CRONQUESTIONS expands the only known previous dataset by a factor of 340×. We find that various state-of-the-art KGQA methods fall far short of the desired perfor- mance on this new dataset. In response, we also propose CRONKGQA, a transformer- based solution that exploits recent advances in Temporal KG embeddings, and achieves per- formance superior to all baselines, with an in- crease of 120% in accuracy over the next best performing method. Through extensive experi- ments, we give detailed insights into the work- ings of CRONKGQA, as well as situations where significant further improvements appear possible. In addition to the dataset, we have re- leased our code as well. 1 Introduction Temporal Knowledge Graphs (Temporal KGs) are multi-relational graph where each edge is associ- ated with a time duration. This is in contrast to a regular KG where no time annotation is present. For example, a regular KG may contain a fact such as (Barack Obama, held position, President of USA), while a temporal KG would contain the start and end time as well — (Barack Obama, held position, President of USA, 2008, 2016). Edges may be associated with a set of non-contiguous time intervals as well. These temporal scopes on facts can be either automatically estimated (Taluk- dar et al., 2012) or user contributed. Several such Temporal KGs have been proposed in the literature, where the focus is on KG completion (Dasgupta et al. 2018; Garc´ıa-Dur´an et al. 2018; Leetaru and Schrodt 2013; Lacroix et al. 2020; Jain et al. 2020). The task of Knowledge Graph Question Answer- ing (KGQA) is to answer natural language ques- tions using a KG as the knowledge base. This is in contrast to reading comprehension-based ques- tion answering, where typically the question is ac- companied by a context (e.g., text passage) and the answer is either one of multiple choices (Ra- jpurkar et al., 2016) or a piece of text from the context (Yang et al., 2018). In KGQA, the an- swer is usually an entity (node) in the KG, and the reasoning required to answer questions is either single-fact based (Bordes et al., 2015), …

Content truncated to 500 words