Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrieval
This work improves entity linking in NLP for tasks like information extraction, though it is incremental as it builds on existing graph-based methods.
The paper tackles the problem of zero-shot entity retrieval by addressing the limitations of coarse-grained sentence embeddings from pre-trained language models, proposing a graph-enhanced framework that captures fine-grained information through a hierarchical graph attention network, achieving state-of-the-art performance on popular benchmarks.
Zero-shot entity retrieval, aiming to link mentions to candidate entities under the zero-shot setting, is vital for many tasks in Natural Language Processing. Most existing methods represent mentions/entities via the sentence embeddings of corresponding context from the Pre-trained Language Model. However, we argue that such coarse-grained sentence embeddings can not fully model the mentions/entities, especially when the attention scores towards mentions/entities are relatively low. In this work, we propose GER, a \textbf{G}raph enhanced \textbf{E}ntity \textbf{R}etrieval framework, to capture more fine-grained information as complementary to sentence embeddings. We extract the knowledge units from the corresponding context and then construct a mention/entity centralized graph. Hence, we can learn the fine-grained information about mention/entity by aggregating information from these knowledge units. To avoid the graph information bottleneck for the central mention/entity node, we construct a hierarchical graph and design a novel Hierarchical Graph Attention Network~(HGAN). Experimental results on popular benchmarks demonstrate that our proposed GER framework performs better than previous state-of-the-art models. The code has been available at https://github.com/wutaiqiang/GER-WSDM2023.