PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text

Abstract

We consider open-domain queston answering (QA) where answers are drawn from either a corpus, a knowledge base (KB), or a combination of both of these. We focus on a setting in which a corpus is supplemented with a large but incomplete KB, and on questions that require non-trivial (e.g., ``multi-hop'') reasoning. We describe PullNet, an integrated framework for (1) learning what to retrieve (from the KB and/or corpus) and (2) reasoning with this heterogeneous information to find the best answer. PullNet uses an {iterative} process to construct a question-specific subgraph that contains information relevant to the question. In each iteration, a graph convolutional network (graph CNN) is used to identify subgraph nodes that should be expanded using retrieval (or ``pull'') operations on the corpus and/or KB. After the subgraph is complete, a similar graph CNN is used to extract the answer from the subgraph. This retrieve-and-reason process allows us to answer multi-hop questions using large KBs and corpora. PullNet is weakly supervised, requiring question-answer pairs but not gold inference paths. Experimentally PullNet improves over the prior state-of-the art, and in the setting where a corpus is used with incomplete KB these improvements are often dramatic. PullNet is also often superior to prior systems in a KB-only setting or a text-only setting.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• End-To-End Memory Networks
• QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Variational Reasoning for Question Answering with Knowledge Graph
• Quasar: Datasets for Question Answering by Search and Reading
• Modeling Relational Data with Graph Convolutional Networks
• Phase Conductor on Multi-layered Attentions for Machine Comprehension
• Question Answering from Unstructured Text by Retrieval and Comprehension

Cited by in corpus (11)

• Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
• Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
• Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphs
• Faithful Embeddings for Knowledge Base Queries
• Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval
• Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base
• Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona
• Recent Advances in Automated Question Answering In Biomedical Domain
• On-The-Fly Information Retrieval Augmentation for Language Models
• Knowledge Efficient Deep Learning for Natural Language Processing
• SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning