Papers › TempoQR: Temporal Question Reasoning over Knowledge Graphs

TempoQR: Temporal Question Reasoning over Knowledge Graphs

10 Dec 2021arXiv:2112.05785archive 2025-07-28

Costas Mavromatis, Prasanna Lakkur Subramanyam, Vassilis N. Ioannidis, Soji Adeshina, Phillip R. Howard, Tetiana Grinberg, Nagib Hakim, George Karypis

Knowledge Graph Question Answering (KGQA) involves retrieving facts from a Knowledge Graph (KG) using natural language queries. A KG is a curated set of facts consisting of entities linked by relations. Certain facts include also temporal information forming a Temporal KG (TKG). Although many natural questions involve explicit or implicit time constraints, question answering (QA) over TKGs has been a relatively unexplored area. Existing solutions are mainly designed for simple temporal questions that can be answered directly by a single TKG fact. This paper puts forth a comprehensive embedding-based framework for answering complex questions over TKGs. Our method termed temporal question reasoning (TempoQR) exploits TKG embeddings to ground the question to the specific entities and time scope it refers to. It does so by augmenting the question embeddings with context, entity and time-aware information by employing three specialized modules. The first computes a textual representation of a given question, the second combines it with the entity embeddings for entities involved in the question, and the third generates question-specific time embeddings. Finally, a transformer-based encoder learns to fuse the generated temporal information with the question representation, which is used for answer predictions. Extensive experiments show that TempoQR improves accuracy by 25--45 percentage points on complex temporal questions over state-of-the-art approaches and it generalizes better to unseen question types.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

cmavro/tempoqr officialmentioned in papermentioned on GitHubpytorch report
czy1999/MultiTQ mentioned on GitHubpytorch report
czy1999/SubGTR mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Entity EmbeddingsGraph Question AnsweringKnowledge GraphsNatural Language QueriesNatural QuestionsQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering Complex-CronQuestions TempoQR Hits@1 79.2 #2 of 4 Archive leaderboard report
Question Answering Complex-CronQuestions EntityQR Hits@1 42.5 #3 of 4 Archive leaderboard report
Question Answering CronQuestions TempoQR-Hard Hits@1 91.8 #9 of 29 Archive leaderboard report
Question Answering CronQuestions TempoQR-Soft Hits@1 79.9 #14 of 29 Archive leaderboard report
Question Answering CronQuestions EntityQR Hits@1 74.5 #17 of 29 Archive leaderboard report
Question Answering CronQuestions BERT Hits@1 24.3 #24 of 29 Archive leaderboard report
Question Answering TIQ TempoQR P@1 1.1 #8 of 9 Archive leaderboard report
Question Answering TimeQuestions TempoQR P@1 43.8 #12 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections