arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.06167cs.CLcs.AI
收藏

基于自然语言推理间接监督的超精细实体分类

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

University of Southern California(南加利福尼亚大学);Temple University(天普大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Bangzheng Li, Wenpeng Yin, Muhao Chen

摘要:

超精细实体分类(UFET)的任务旨在预测不同的和自由形式的单词或短语,描述句子中提到的适当类型的实体。这一任务的一个关键挑战在于大量的类型和每种类型的注释数据的稀缺性。现有的系统将任务制定为多路分类问题,并直接或远程地训练训练监督分类器。这导致两个问题:(i)分类器不捕获类型语义,因为类型通常被转换成索引;(ii)以这种方式开发的系统限于在预定义的类型集合内进行预测,并且通常不能推广到在训练中很少看到或看不到的类型。这项工作提出了LITE,一种新的方法,制定实体类型作为一个自然语言推理(NLI)的问题,利用(i)间接监督NLI推断类型信息有意义地表示为文本假设和缓解数据稀缺问题,以及(ii)学习排名的目标,以避免预先定义的类型集。实验表明,在有限的训练数据下,LITE在UFET任务上获得了最先进的性能。此外,LITE展示了其强大的通用性,不仅在其他细粒度实体类型基准上产生最佳结果,更重要的是,预训练的LITE系统在包含未知类型的新数据上运行良好。

英文摘要:

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 challenge for this task lies in the large amount 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 since 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑