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 2306.01944cs.HCcs.AIcs.CL
收藏

EdGCon:基于词汇属性的象似性评分自动分配器,用于辅助技术手势的生成

EdGCon: Auto-assigner of Iconicity Ratings Grounded by Lexical Properties to Aid in Generation of Technical Gestures

Arizona State University(亚利桑那州立大学)

Sameena Hossain, Payal Kamboj, Aranyak Maity, Tamiko Azuma, Ayan Banerjee, Sandeep K. S. Gupta

AI总结:

本文提出 EdGCon,利用 ASL-LEX 的位置、手形和运动属性及词义相关性,为 ASL 技术手势自动分配象似性评分,在 61 个手势测试中准确率达 80.76%。

摘要:

在形式上具有相似性且在意义上相关的手势,应当更容易被学习者识别并纳入其已有的词汇库。在这方面,为了更容易被聋人和听障群体接受为标准,美国手语(ASL)中的技术手势最好能与其词汇邻近项在形式上具有相似性。我们利用一个 ASL 词汇数据库 ASL-LEX 来识别一组技术手势中的词汇关系。我们对 ASL-LEX 中 3 种独特的次词汇属性——位置、手形和运动——使用自动识别。EdGCon 根据新手势与现有一组技术手势在词汇属性上的相似性,以及新技术词与现有一组技术词在意义上的相关性,分配一个象似性评分。我们从不同互联网网站收集了 30 个临时众包技术手势,并使用来自 DeafTEC 技术语料库的 31 个手势对其进行测试。我们发现,EdGCon 能够在 80.76% 的情况下正确自动分配象似性评分。

英文摘要:

Gestures that share similarities in their forms and are related in their meanings, should be easier for learners to recognize and incorporate into their existing lexicon. In that regard, to be more readily accepted as standard by the Deaf and Hard of Hearing community, technical gestures in American Sign Language (ASL) will optimally share similar in forms with their lexical neighbors. We utilize a lexical database of ASL, ASL-LEX, to identify lexical relations within a set of technical gestures. We use automated identification for 3 unique sub-lexical properties in ASL- location, handshape and movement. EdGCon assigned an iconicity rating based on the lexical property similarities of the new gesture with an existing set of technical gestures and the relatedness of the meaning of the new technical word to that of the existing set of technical words. We collected 30 ad hoc crowdsourced technical gestures from different internet websites and tested them against 31 gestures from the DeafTEC technical corpus. We found that EdGCon was able to correctly auto-assign the iconicity ratings 80.76% of the time.

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。

↑