Forecasting Question Answering over Temporal Knowledge Graphs

@article{Ding2022ForecastingQA,
  title={Forecasting Question Answering over Temporal Knowledge Graphs},
  author={Zifeng Ding and Ruoxia Qi and Zongyue Li and Bailan He and Jingpei Wu and Yunpu Ma and Zhao Meng and Zhen Han and Volker Tresp},
  journal={ArXiv},
  year={2022},
  volume={abs/2208.06501}
}
Question answering over temporal knowledge graphs (TKGQA) has recently found increasing interest. TKGQA requires temporal reasoning techniques to extract the rele- vant information from temporal knowledge bases. The only existing TKGQA dataset, i.e., C RON Q UESTIONS , consists of temporal questions based on the facts from a fixed time period, where a temporal knowledge graph (TKG) span- ning the same period can be fully used for answer infer-ence, allowing the TKGQA models to use even the fu… 

Figures and Tables from this paper

Few-Shot Inductive Learning on Temporal Knowledge Graphs using Concept-Aware Information

This work proposes a few-shot out-of-graph (OOG) link prediction task for TKGs, where the missing entities from the links concerning unseen entities are predicted by employing a meta-learning framework and utilizing the meta-information provided by only few edges associated with each unseen entity.

A Simple But Powerful Graph Encoder for Temporal Knowledge Graph Completion

This paper proposes a simple but powerful graph encoder for TKGC, namely, TARGCN, which is parameter-efficient, and it exten- 016 sively utilizes the information from the whole 017 temporal context.

References

SHOWING 1-10 OF 38 REFERENCES

TempoQR: Temporal Question Reasoning over Knowledge Graphs

A comprehensive embedding-based framework for answering complex questions over TKGs by exploiting TKG embeddings to ground the question to the specific entities and time scope it refers to and improves accuracy by 25--45 percentage points on complex temporal questions over state-of-the-art approaches.

Improving Time Sensitivity for Question Answering over Temporal Knowledge Graphs

A time-sensitive question answering (TSQA) framework that significantly outperforms the previous state of the art on a new benchmark for question answering over temporal KGs, especially achieving a 32% error reduction on complex questions that require multiple steps of reasoning over facts in the temporal KG.

Complex Temporal Question Answering on Knowledge Graphs

Results show that EXAQT outperforms three state-of-the-art systems for answering complex questions over KGs, thereby justifying specialized treatment of temporal QA.

Question Answering Over Temporal Knowledge Graphs

This work proposes CRONKGQA, a transformer-based solution that exploits recent advances in Temporal KG embeddings, and achieves performance superior to all baselines, with an increase of 120% in accuracy over the next best performing method.

Learning to Walk across Time for Interpretable Temporal Knowledge Graph Completion

T-GAP is proposed, a novel model for TKG completion that maximally utilizes both temporal information and graph structure in its encoder and decoder, and enjoys transparent interpretability, and follows human intuition in its reasoning process.

Variational Reasoning for Question Answering with Knowledge Graph

This work proposes a novel and unified deep learning architecture, and an end-to-end variational learning algorithm which can handle noise in questions, and learn multi-hop reasoning simultaneously.

Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks

A new representation learning model for temporal knowledge graphs, namely CyGNet, based on a novel time-aware copy-generation mechanism that is not only able to predict future facts from the whole entity vocabulary, but also capable of identifying facts with repetition and accordingly predicting such future facts with reference to the known facts in the past.

TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs

This work addresses the task of link forecasting on temporal knowledge graphs and introduces TLogic, an explainable framework that is based on temporal logical rules extracted via temporal random walks, and works well in the inductive setting where already learned rules are transferred to related datasets with a common vocabulary.

ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data

This work aims to formulate a task, construct a dataset, and provide benchmarks for developing methods for event forecasting with large volumes of unstructured text data, and introduces ForecastQA, a question-answering dataset consisting of 10,392 event forecasting questions, which have been collected and verified via crowdsourcing efforts.

The Web as a Knowledge-Base for Answering Complex Questions

This paper proposes to decompose complex questions into a sequence of simple questions, and compute the final answer from the sequence of answers, and empirically demonstrates that question decomposition improves performance from 20.8 precision@1 to 27.5 precision @1 on this new dataset.