An Interpretable Reasoning Network for Multi-Relation Question Answering
arXiv:1801.04726
Abstract
Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base. In this paper, we present a novel model called Interpretable Reasoning Network that employs an interpretable, hop-by-hop reasoning process for question answering. The model dynamically decides which part of an input question should be analyzed at each hop; predicts a relation that corresponds to the current parsed results; utilizes the predicted relation to update the question representation and the state of the reasoning process; and then drives the next-hop reasoning. Experiments show that our model yields state-of-the-art results on two datasets. More interestingly, the model can offer traceable and observable intermediate predictions for reasoning analysis and failure diagnosis, thereby allowing manual manipulation in predicting the final answer.
COLING 2018, 13pages
References in corpus (5)
- Sequence to Sequence Learning with Neural Networks
- Large-scale Simple Question Answering with Memory Networks
- Question Answering with Subgraph Embeddings
- Open Question Answering with Weakly Supervised Embedding Models
- Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering
Cited by in corpus (9)
- Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering
- Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networks
- NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation
- Graph-based Multi-hop Reasoning for Long Text Generation
- Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
- Question-Aware Memory Network for Multi-hop Question Answering in Human-Robot Interaction
- Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases
- Complex Knowledge Base Question Answering: A Survey
- JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs