Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases
arXiv:1903.02188
Abstract
When answering natural language questions over knowledge bases (KBs), different question components and KB aspects play different roles. However, most existing embedding-based methods for knowledge base question answering (KBQA) ignore the subtle inter-relationships between the question and the KB (e.g., entity types, relation paths and context). In this work, we propose to directly model the two-way flow of interactions between the questions and the KB via a novel Bidirectional Attentive Memory Network, called BAMnet. Requiring no external resources and only very few hand-crafted features, on the WebQuestions benchmark, our method significantly outperforms existing information-retrieval based methods, and remains competitive with (hand-crafted) semantic parsing based methods. Also, since we use attention mechanisms, our method offers better interpretability compared to other baselines.
11 pages. Accepted as NAACL 2019 Long Paper. Final Version
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Large-scale Simple Question Answering with Memory Networks
- Dynamic Coattention Networks For Question Answering
- Machine Comprehension Using Match-LSTM and Answer Pointer
- Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
- Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
- Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
- S-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking
Cited by in corpus (5)
- Question Answering over Knowledge Base using Language Model Embeddings
- Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model
- Attention-based Aspect Reasoning for Knowledge Base Question Answering on Clinical Notes
- Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
- CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering