English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Question Answering over Knowledge Graph (KGQA) aims to seek answer entitiesfor the natural language question from a large-scale Knowledge Graph~(KG). Tobetter perform reasoning on KG, recent work typically adopts a pre-trainedlanguage model~(PLM) to model the question, and a graph neural network~(GNN)based module to perform multi-hop reasoning on the KG. Despite theeffectiveness, due to the divergence in model architecture, the PLM and GNN arenot closely integrated, limiting the knowledge sharing and fine-grained featureinteractions. To solve it, we aim to simplify the above two-module approach,and develop a more capable PLM that can directly support subgraph reasoning forKGQA, namely ReasoningLM. In our approach, we propose a subgraph-awareself-attention mechanism to imitate the GNN for performing structuredreasoning, and also adopt an adaptation tuning strategy to adapt the modelparameters with 20,000 subgraphs with synthesized questions. After adaptation,the PLM can be parameter-efficient fine-tuned on downstream tasks. Experimentsshow that ReasoningLM surpasses state-of-the-art models by a large margin, evenwith fewer updated parameters and less training data. Our codes and data arepublicly available at~\url{https://github.com/RUCAIBox/ReasoningLM}.

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