arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.08155cs.CL
收藏

用于复杂电话通话中下一动作预测的图集成语言Transformer

Graph Integrated Language Transformers for Next Action Prediction in Complex Phone Calls

Infinitus Systems, Inc.(无限系统公司)

Amin Hosseiny Marani, Ulie Schnaithmann, Youngseo Son, Akil Iyer, Manas Paldhe, Arushi Raghuvanshi

AI总结:

针对现有对话式AI预测下一动作依赖多组件流水线、复杂度高且易出错的问题,提出图集成语言Transformer模型,无需外部依赖即可理解话语与动作的关联,在真实通话场景中性能优于现有生产级系统。

摘要:

当前的对话式AI系统采用不同的机器学习流水线,以及外部知识源和业务逻辑来预测下一动作。维护对话管理器流水线中的各类组件会增加扩展和更新的复杂度,延长处理时间,还会在流水线中产生累加噪声,进而导致下一动作预测错误。本文研究将图结构集成到语言Transformer中,以在不依赖外部源或组件的情况下,更好地理解人类话语、先前动作与下一动作之间的关系。针对真实通话的实验分析表明,在真实场景下与人类用户进行交互式通话时,所提出的Graph Integrated Language Transformer模型相比其他生产级对话式AI系统能实现更优性能。

英文摘要:

Current Conversational AI systems employ different machine learning pipelines, as well as external knowledge sources and business logic to predict the next action. Maintaining various components in dialogue managers' pipeline adds complexity in expansion and updates, increases processing time, and causes additive noise through the pipeline that can lead to incorrect next action prediction. This paper investigates graph integration into language transformers to improve understanding the relationships between humans' utterances, previous, and next actions without the dependency on external sources or components. Experimental analyses on real calls indicate that the proposed Graph Integrated Language Transformer models can achieve higher performance compared to other production level conversational AI systems in driving interactive calls with human users in real-world settings.

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。

↑