Linguistic Individuality Transformation for Spoken Language

Linguistic Individuality Transformation for Spoken Language
复制标题

口语的语言个性转化

DOI:
10.1007/978-3-319-19291-8_13
复制
发表时间:
2015
影响因子:
2.3
通讯作者:
Satoshi Nakamura
Satoshi Nakamura
中科院分区:
心理学4区
文献类型:
--
作者:
M. Mizukami;Graham Neubig;S. Sakti;T. Toda;Satoshi Nakamura

文献摘要

参考文献

被引文献

相似文献

在文本和语音中,有各种表达作者或说话者个性的特征。在本文中,我们通过提出一种使用受统计机器翻译(SMT)启发的技术来转换个性的方法,朝着创建考虑这种个性的对话系统迈出了一步。然而,找到具有相同语义内容但不同个性的平行语料库是很困难的,这妨碍了标准SMT技术的使用。因此,在本文中,我们重点关注通过将少量富有个性的数据与大量背景文本相结合,使用来自释义文献和语言模型(LM)的技术来创建翻译模型(TM)的方法。我们对三种类型的 TM 构建技术的有效性进行了自动和手动评估,发现所提出的系统使用专注于有限功能词集的方法是最有效的,并且可以将个性转变到既引人注目又可识别的程度。
In text and speech, there are various features that express the individuality of the writer or speaker. In this paper, we take a step towards the creation of dialogue systems that consider this individuality by proposing a method for transforming individuality using a technique inspired by statistical machine translation (SMT). However, finding a parallel corpus with identical semantic content but different individuality is difficult, precluding the use of standard SMT techniques. Thus, in this paper, we focus on methods for creating a translation model (TM) using techniques from the paraphrasing literature and a language model (LM) by combining small amounts of individuality-rich data with larger amounts of background text. We perform an automatic and manual evaluation comparing the effectiveness of three types of TM construction techniques and find that the proposed system using a method focusing on a limited set of function words is most effective and can transform individuality to a degree that is both noticeable and identifiable.
一种用于说话风格转变的单调统计机器翻译方法
DOI: 10.1016/j.csl.2012.02.003
发表时间: 2012
影响因子: 4.3
作者:
G. Neubig;Y. Akita;S. Mori;and T. Kawahara
通讯作者: and T. Kawahara
现代日语“角色语言”(Yakuwarigo):日本文学和流行文化中的虚构口语
DOI: --
发表时间: 2011
影响因子: 0.8
作者:
Kinsui;Satosi;Teshigawara;Mihoko
通讯作者: Mihoko