Fine-grained entity type classification with adaptive context

Diversified Semantic Attention Model for Fine-Grained Entity Typing

“…After that, Sanjeev et al [27] introduced an encoder-decoder neural model to infer entity types, which can be trained end-to-end. Different from previous methods that obtained the entity context information through a fixed window, Liu et al [28] introduced a novel entity typing method with sliding window context and dynamic global information. Despite of achieving promising results, these neural-based methods are still limited by ignoring type hierarchy in inferring process.…”

Advances in intelligence and internet of things for human-centric computing

“…The existing methodologies typically have acquired entity context information through a fixed window, which may lead to ambiguous because there is not enough external information to classify the entity. To solve the drawbacks of this method, Liu et al (2017a) proposed a detailed entity type classification method for unstructured text based on global information and sliding window context. By combining this information with other functions, this paper based on a bidirectional, short-term memory (LSTM) network to perform classification operations.…”