Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Question Calibration and Multi-Hop Modeling for Temporal Question Answering

Chao Xue, Di Liang, Pengfei Wang, Jing Zhang

TL;DR

A novel Question Calibration and Multi-Hop Modeling (QC-MHM) network that calibrate the question representation by fusing the question and the time-constrained concepts in KG, and construct the GNN layer to complete multi-hop message passing.

Abstract

Many models that leverage knowledge graphs (KGs) have recently demonstrated remarkable success in question answering (QA) tasks. In the real world, many facts contained in KGs are time-constrained thus temporal KGQA has received increasing attention. Despite the fruitful efforts of previous models in temporal KGQA, they still have several limitations. (I) They adopt pre-trained language models (PLMs) to obtain question representations, while PLMs tend to focus on entity information and ignore entity transfer caused by temporal constraints, and finally fail to learn specific temporal representations of entities. (II) They neither emphasize the graph structure between entities nor explicitly model the multi-hop relationship in the graph, which will make it difficult to solve complex multi-hop question answering. To alleviate this problem, we propose a novel Question Calibration and Multi-Hop Modeling (QC-MHM) approach. Specifically, We first calibrate the question representation by fusing the question and the time-constrained concepts in KG. Then, we construct the GNN layer to complete multi-hop message passing. Finally, the question representation is combined with the embedding output by the GNN to generate the final prediction. Empirical results verify that the proposed model achieves better performance than the state-of-the-art models in the benchmark dataset. Notably, the Hits@1 and Hits@10 results of QC-MHM on the CronQuestions dataset's complex questions are absolutely improved by 5.1% and 1.2% compared to the best-performing baseline. Moreover, QC-MHM can generate interpretable and trustworthy predictions.

Question Calibration and Multi-Hop Modeling for Temporal Question Answering

TL;DR

A novel Question Calibration and Multi-Hop Modeling (QC-MHM) network that calibrate the question representation by fusing the question and the time-constrained concepts in KG, and construct the GNN layer to complete multi-hop message passing.

Abstract

Many models that leverage knowledge graphs (KGs) have recently demonstrated remarkable success in question answering (QA) tasks. In the real world, many facts contained in KGs are time-constrained thus temporal KGQA has received increasing attention. Despite the fruitful efforts of previous models in temporal KGQA, they still have several limitations. (I) They adopt pre-trained language models (PLMs) to obtain question representations, while PLMs tend to focus on entity information and ignore entity transfer caused by temporal constraints, and finally fail to learn specific temporal representations of entities. (II) They neither emphasize the graph structure between entities nor explicitly model the multi-hop relationship in the graph, which will make it difficult to solve complex multi-hop question answering. To alleviate this problem, we propose a novel Question Calibration and Multi-Hop Modeling (QC-MHM) approach. Specifically, We first calibrate the question representation by fusing the question and the time-constrained concepts in KG. Then, we construct the GNN layer to complete multi-hop message passing. Finally, the question representation is combined with the embedding output by the GNN to generate the final prediction. Empirical results verify that the proposed model achieves better performance than the state-of-the-art models in the benchmark dataset. Notably, the Hits@1 and Hits@10 results of QC-MHM on the CronQuestions dataset's complex questions are absolutely improved by 5.1% and 1.2% compared to the best-performing baseline. Moreover, QC-MHM can generate interpretable and trustworthy predictions.
Paper Structure (17 sections, 18 equations, 4 figures, 4 tables)

This paper contains 17 sections, 18 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Definition
  4. Proposed Methods
  5. Time-Sensitive KG Embedding
  6. Question Calibration and Multi-Hop Modeling
  7. Answer Prediction
  8. Datasets and Baselines
  9. Datasets
  10. Baselines
  11. Results
  12. Model Performance
  13. Ablation Study
  14. Interpretability of Multi-Hop Modeling
  15. Interpretability of Question Calibration
  16. ...and 2 more sections

Figures (4)

  • Figure 1: Examples of complex queries in both Google Search and ChatGPT yield incorrect results.
  • Figure 2: Visualization of a case study of the interpretability of our model. For brevity, we only show the key entities.
  • Figure 3: Visualization of the question and SPO vectors using the adaptive fusion technique.
  • Figure 4: Visualization of the SPO gradients. The left if percentage of gradients, and the right is details of the SPOs.