NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA
Dec 10, 2023
Speakers
Hyeong Kyu Choi
Speaker · 0 followers
Seunghun Lee
Speaker · 0 followers
Jaewon Chu
Speaker · 0 followers
Hyunwoo J. Kim
Speaker · 0 followers
About
Multi-hop Knowledge Graph Question Answering (KGQA) is a task that involves retrieving nodes from a knowledge graph (KG) to answer natural language questions. Recent GNN-based approaches formulate this task as a KG path searching problem, where messages are sequentially propagated from the seed node towards the answer nodes. However, these messages are past-oriented, and they do not consider the full KG context. To make matters worse, KG nodes often represent pronoun entities and are sometimes encrypted, being uninformative in selecting between paths. To address these problems, we propose Neural Tree Search (NuTrea), a tree search-based GNN model that incorporates the broader KG context. Our model adopts a message-passing scheme that probes the unreached subtree regions to boost the past-oriented embeddings. In addition, we introduce the Relation Frequency-Inverse Entity Frequency (RF-IEF) node embedding that considers the global KG context to better characterize ambiguous KG nodes. The general effectiveness of our approach is demonstrated through experiments on three major multi-hop KGQA benchmark datasets, and our extensive analyses further validate its expressiveness and robustness. Overall, NuTrea provides a powerful means to query the KG with complex natural language questions. Code will be released.Multi-hop Knowledge Graph Question Answering (KGQA) is a task that involves retrieving nodes from a knowledge graph (KG) to answer natural language questions. Recent GNN-based approaches formulate this task as a KG path searching problem, where messages are sequentially propagated from the seed node towards the answer nodes. However, these messages are past-oriented, and they do not consider the full KG context. To make matters worse, KG nodes often represent pronoun entities and are sometimes e…
Organizer
NeurIPS 2023
Account · 645 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Tailoring Self-Attention for Graph via Rooted Subtrees
Watch later
Siyuan Huang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions
Watch later
Yingtai Xiao, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Leveraging Early-Stage Robustness in Diffusion Models for Efficient and High-Quality Image Synthesis
Watch later
Yulhwa Kim, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
AmadeusGPT: a natural language interface for interactive animal behavioral analysis
Watch later
Shaokai Ye, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Online Inventory Problems: Beyond the i.i.d. Setting with Online Convex Optimization
Watch later
Massil Hihat, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%