arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.06362cs.CL
收藏

来自大型语言模型的词定义

Word Definitions from Large Language Models

Department of Computer Science(计算机科学系);Earlham College(埃尔哈姆学院);Stony Brook University(石溪大学)

Bach Pham, JuiHsuan Wong, Samuel Kim, Yunting Yin, Steven Skiena

AI总结:

本研究比较了传统词典与ChatGPT生成的词定义,发现ChatGPT定义高度准确且在低频词上优于GloVE和FastText词嵌入。

摘要:

历史上,词典定义一直是词语含义的仲裁者,但这一首要地位受到了NLP近期进展的威胁,包括词嵌入和ChatGPT等生成式模型。我们提出了一项探索性研究,探讨经典词典的词定义与这些较新计算产物之间的一致性程度。具体而言,我们将三部已出版词典的定义与ChatGPT变体生成的定义进行了比较。我们表明:(i) 来自不同传统词典的定义在表面形式上比模型生成的定义表现出更高的相似性;(ii) ChatGPT生成的定义高度准确,与传统词典相当;(iii) 基于ChatGPT的嵌入定义即使在低频词上也能保持其准确性,远优于GloVE和FastText词嵌入。

英文摘要:

Dictionary definitions are historically the arbitrator of what words mean, but this primacy has come under threat by recent progress in NLP, including word embeddings and generative models like ChatGPT. We present an exploratory study of the degree of alignment between word definitions from classical dictionaries and these newer computational artifacts. Specifically, we compare definitions from three published dictionaries to those generated from variants of ChatGPT. We show that (i) definitions from different traditional dictionaries exhibit more surface form similarity than do model-generated definitions, (ii) that the ChatGPT definitions are highly accurate, comparable to traditional dictionaries, and (iii) ChatGPT-based embedding definitions retain their accuracy even on low frequency words, much better than GloVE and FastText word embeddings.

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。

↑