Joint Transition-based Dependency Parsing and Disfluency Detection for Automatic Speech Recognition Texts
Joint Transition-based Dependency Parsing and Disfluency Detection for Automatic Speech Recognition Texts
复制标题
DOI：
10.18653/v1/d16-1109
复制
发表时间：
2016-11
期刊：
影响因子：
--
通讯作者：
Masashi Yoshikawa;Hiroyuki Shindo;Yuji Matsumoto
中科院分区：
文献类型：
--
作者：
Masashi Yoshikawa;Hiroyuki Shindo;Yuji Matsumoto
联合依存句法分析和歧义检测是语音语言处理中的一项重要任务。最近的方法表现出高性能的这项任务，虽然大多数作者不切实际的假设，输入文本是由人类注释者转录。在实际应用中，输入文本通常是自动语音识别（ASR）系统的输出，这意味着文本不仅包含不连续噪声，而且还包含来自ASR系统的识别错误。在这项工作中，我们提出了一种分析方法，处理discriminency和ASR错误使用的增量移位减少算法与几个新的功能，适合ASR输出文本。由于黄金依赖信息通常只标注在转录文本上，我们还引入了一种基于注释的方法，用于将黄金依赖注释转移到ASR输出文本中，以构建我们的解析器的训练数据。我们进行了一个实验上的Switchboard语料库，并表明，我们的方法优于传统的方法在依赖分析和不一致性检测。
Joint dependency parsing with disfluency detection is an important task in speech language processing. Recent methods show high performance for this task, although most authors make the unrealistic assumption that input texts are transcribed by human annotators. In real-world applications, the input text is typically the output of an automatic speech recognition (ASR) system, which implies that the text contains not only disfluency noises but also recognition errors from the ASR system. In this work, we propose a parsing method that handles both disfluency and ASR errors us-ing an incremental shift-reduce algorithm with several novel features suited to ASR output texts. Because the gold dependency information is usually annotated only on transcribed texts, we also introduce an alignment-based method for transferring the gold dependency annotation to the ASR output texts to construct training data for our parser. We conducted an experiment on the Switchboard corpus and show that our method outperforms conventional methods in terms of dependency parsing and disfluency detection.