Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss

Abstract

The task of Fine-grained Entity Type Classification (FETC) consists of assigning types from a hierarchy to entity mentions in text. Existing methods rely on distant supervision and are thus susceptible to noisy labels that can be out-of-context or overly-specific for the training sentence. Previous methods that attempt to address these issues do so with heuristics or with the help of hand-crafted features. Instead, we propose an end-to-end solution with a neural network model that uses a variant of crossentropy loss function to handle out-of-context labels, and hierarchical loss normalization to cope with overly-specific ones. Also, previous work solve FETC a multi-label classification followed by ad-hoc post-processing. In contrast, our solution is more elegant: we use public word embeddings to train a single-label that jointly learns representations for entity mentions and their context. We show experimentally that our approach is robust against noise and consistently outperforms the state-of-theart on established benchmarks for the task.

Diversified Semantic Attention Model for Fine-Grained Entity Typing

“…Ren et al [10] designed a novel partial-label loss to further reduce the label noise. Moreover, Xu et al [22] introduced a method of normalization of hierarchical loss to reduce specific types of noise. A recent study [23] introduced a penalty term in the optimization process to effectively diminish the side effect of the label noise and confirmation bias.…”

Description-Based Zero-shot Fine-Grained Entity Typing

“…Existing work on FGET focuses on performing context-sensitive typing (Gillick et al, 2014;Corro et al, 2015), learning from noisy training data (Abhishek et al, 2017;Ren et al, 2016;Xu and Barbosa, 2018), and exploiting the type hierarchies to improve the learning and inference (Yogatama et al, 2015;Murty et al, 2018). More recent studies support even finer granularity (Choi et al, 2018;Murty et al, 2018).…”

Fine-Grained Entity Typing in Hyperbolic Space

“…Shimaoka et al (2017) encode the hierarchy through a sparse matrix. Xu and Barbosa (2018) model the relations through a hierarchy-aware loss function. Ma et al (2016) and Abhishek et al (2017) learn embeddings for labels and feature representations into a joint space in order to facilitate information sharing among them.…”