Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference

Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference Bangzheng Li⋄†∗, Wenpeng Yin‡, and Muhao Chen⋄ ⋄University of Southern California, USA †University of Illinois at Urbana-Champaign, USA ‡Temple University, USA vincentleebang@gmail.com; wenpeng.yin@temple.edu; muhaoche@usc.edu Abstract The task of ultra-fine entity typing (UFET) seeks to predict diverse and free-form words or phrases that describe the appropriate types of entities mentioned in sentences. A key chal- lenge for this task lies in the large number of types and the scarcity of annotated data per type. Existing systems formulate the task as a multi-way classification problem and train di- rectly or distantly supervised classifiers. This causes two issues: (i) the classifiers do not capture the type semantics because types are often converted into indices; (ii) systems de- veloped in this way are limited to predicting within a pre-defined type set, and often fall short of generalizing to types that are rarely seen or unseen in training. This work presents LITE , a new approach that formulates entity typing as a natural lan- guage inference (NLI) problem, making use of (i) the indirect supervision from NLI to in- fer type information meaningfully represented as textual hypotheses and alleviate the data scarcity issue, as well as (ii) a learning-to-rank objective to avoid the pre-defining of a type set. Experiments show that, with limited training data, LITE obtains state-of-the-art perfor- mance on the UFET task. In addition, LITE demonstrates its strong generalizability by not only yielding best results on other fine-grained entity typing benchmarks, more importantly, a pre-trained LITE system works well on new data containing unseen types.1 1 Introduction Entity typing, inferring the semantic types of the entity mentions in text, is a fundamental and ∗ This work was done when the first author was visiting the University of Southern California. 1Our models and implementation are available at https:// github.com/luka-group/lite. long-lasting research problem in natural language understanding, which aims at inferring the seman- tic types of the entities mentioned in text. The resulted type information can help with grounding human language components to real-world con- cepts (Chandu et al., 2021), and provide valuable prior knowledge for natural language understand- ing tasks such as entity linking (Ling et al., 2015; Onoe and Durrett, 2020), question answering (Yavuz et al., 2016), and information extraction (Koch et al., 2014). Prior studies have mainly formulated the task as a multi-way classification problems (Wang et al., 2021; Zhang et al., 2019; Chen et al., 2020a; Hu et al., 2020). However, earlier efforts for entity typing are far from enough for representing real-world sce- narios, where types of entities can be extremely diverse. Accordingly, the community has recently paid much attention to more fine-grained model- ing of types for entities. One representative work is the Ultra-fine Entity Typing (UFET) bench- mark created by Choi et al. (2018). The task seeks to search for the most appropriate types for an entity among over ten thousand free-form type candidates. The drastic increase of types forces us to question whether the multi-way classification framework …

Content truncated to 500 words