Collective Learning From Diverse Datasets for Entity Typing in the Wild
This addresses the problem of entity typing without domain-specific knowledge for NLP applications, representing a novel but incremental extension of existing methods.
The paper tackles entity typing in the wild, where models must assign labels without prior knowledge of domain or label sets, by proposing a Collective Learning Framework that learns from diverse datasets to predict fine-grained labels across domains, achieving strong performance on seven real-world datasets.
Entity typing (ET) is the problem of assigning labels to given entity mentions in a sentence. Existing works for ET require knowledge about the domain and target label set for a given test instance. ET in the absence of such knowledge is a novel problem that we address as ET in the wild. We hypothesize that the solution to this problem is to build supervised models that generalize better on the ET task as a whole, rather than a specific dataset. In this direction, we propose a Collective Learning Framework (CLF), which enables learning from diverse datasets in a unified way. The CLF first creates a unified hierarchical label set (UHLS) and a label mapping by aggregating label information from all available datasets. Then it builds a single neural network classifier using UHLS, label mapping, and a partial loss function. The single classifier predicts the finest possible label across all available domains even though these labels may not be present in any domain-specific dataset. We also propose a set of evaluation schemes and metrics to evaluate the performance of models in this novel problem. Extensive experimentation on seven diverse real-world datasets demonstrates the efficacy of our CLF.