Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

answer entity prediction

Answer entity prediction is the task in natural language processing and question answering of identifying the specific entity or entities within a structured knowledge graph that correctly answers a natural language question. To accomplish this, computational systems analyze the semantic intent of an input query, identify key topic entities, and perform structured or multi-hop reasoning over the graph relations and candidate nodes. The process typically involves scoring and ranking nodes within relevant subgraphs to determine the most probable factual target, often combining pre-trained language models for query comprehension with graph neural networks or attention mechanisms to navigate complex relational data.

1 item

ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph

ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph

Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, Yaliang Li, Ji-Rong Wen

OrganizationsAlibaba GroupRenmin University of ChinaSchool of Information

Why you should read this

Proposes a unified pre-trained language model that performs structural subgraph reasoning directly via a specialized self-attention mechanism, outperforming traditional two-module graph neural network approaches for knowledge graph question answering while updating fewer parameters.

Question Answering over Knowledge Graph (KGQA) aims to seek answer entities for the natural language question from a large-scale Knowledge Graph (KG). To better perform reasoning on KG, recent work typically adopts a pre-trained language model (PLM) to model the question, and a graph neural network (GNN) based module to perform multi-hop reasoning on the KG. Despite the effectiveness, due to the divergence in model architecture, the PLM and GNN are not closely integrated, limiting the knowledge sharing and fine-grained feature interactions. To solve it, we aim to simplify the above two-module approach, and develop a more capable PLM that can directly support subgraph reasoning for KGQA, namely ReasoningLM. In our approach, we propose a subgraph-aware self-attention mechanism to imitate the GNN for performing structured reasoning, and also adopt an adaptation tuning strategy to adapt the model parameters with 20,000 subgraphs with synthesized questions. After adaptation, the PLM can be parameter-efficient fine-tuned on downstream tasks. Experiments show that ReasoningLM surpasses state-of-the-art models by a large margin, even with fewer updated parameters and less training data. Our codes and data are publicly available at https://github.com/RUCAIBox/ReasoningLM.

Added

2026-10-03