arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.05277cs.CL
收藏

瑞典语开放域会话语言模型的构建

Building a Swedish Open-Domain Conversational Language Model

Chalmers University of Technology(查尔姆斯理工大学);Recorded Future;Royal Institute of Technology(皇家理工学院);Schibsted Media Group(施布斯特传媒集团)

Tobias Norlund, Agnes Stenbom

摘要:

我们目前正在进行的评估工作,据我们所知,第一个大型的生成语言模型训练,在瑞典语交谈,使用数据从在线讨论论坛闪回。我们进行了一项人类评估试点研究,表明该模型通常能够以类似人类和信息丰富的方式对各种主题的对话做出回应。虽然来自在线论坛的数据可以用于构建会话系统,但我们反思了不谨慎的应用程序可能产生的负面后果,以及采取积极措施防范这些后果的必要性。

英文摘要:

We present on-going work of evaluating the, to our knowledge, first large generative language model trained to converse in Swedish, using data from the online discussion forum Flashback. We conduct a human evaluation pilot study that indicates the model is often able to respond to conversations in both a human-like and informative manner, on a diverse set of topics. While data from online forums can be useful to build conversational systems, we reflect on the negative consequences that incautious application might have, and the need for taking active measures to safeguard against them.

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。

↑