Show simple item record

dc.creatorLi, Bangzheng
dc.creatorYin, Wenpeng
dc.creatorChen, Muhao
dc.identifier.citationBangzheng Li, Wenpeng Yin, Muhao Chen; Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference. Transactions of the Association for Computational Linguistics 2022; 10 607–622. doi:
dc.description.abstractThe 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 challenge 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 directly 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 developed 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 language inference (NLI) problem, making use of (i) the indirect supervision from NLI to infer 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 performance 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.
dc.format.extent16 pages
dc.relation.ispartofFaculty/ Researcher Works
dc.relation.haspartTransactions of the Association for Computational Linguistics, Vol. 10
dc.relation.isreferencedbyMIT Press
dc.rightsAttribution CC BY
dc.titleUltra-fine Entity Typing with Indirect Supervision from Natural Language Inference
dc.type.genreJournal article
dc.description.departmentComputer and Information Sciences
dc.ada.noteFor Americans with Disabilities Act (ADA) accommodation, including help with reading this content, please contact
dc.description.schoolcollegeTemple University. College of Science and Technology
dc.temple.creatorYin, Wenpeng

Files in this item


This item appears in the following Collection(s)

Show simple item record

Attribution CC BY
Except where otherwise noted, this item's license is described as Attribution CC BY