Spontaneous spoken dialogue is often disfluent, containing pauses,
hesitations, self-corrections and false starts. Processing such phenomena is
essential in understanding a speaker's intended meaning and controlling the
flow of the conversation. Furthermore, this processing needs to be word-by-word
incremental to allow further downstream processing to begin as early as
possible in order to handle real spontaneous human conversational behaviour.
In addition, from a developer's point of view, it is highly desirable to be
able to develop systems which can be trained from `clean' examples while also
able to generalise to the very diverse disfluent variations on the same data --
thereby enhancing both data-efficiency and robustness. In this paper, we
present a multi-task LSTM-based model for incremental detection of disfluency
structure, which can be hooked up to any component for incremental
interpretation (e.g. an incremental semantic parser), or else simply used to
`clean up' the current utterance as it is being produced.
We train the system on the Switchboard Dialogue Acts (SWDA) corpus and
present its accuracy on this dataset. Our model outperforms prior neural
network-based incremental approaches by about 10 percentage points on SWDA
while employing a simpler architecture. To test the model's generalisation
potential, we evaluate the same model on the bAbI+ dataset, without any
additional training. bAbI+ is a dataset of synthesised goal-oriented dialogues
where we control the distribution of disfluencies and their types. This shows
that our approach has good generalisation potential, and sheds more light on
which types of disfluency might be amenable to domain-general processing.

本文提出一种多任务基于 LSTM 的模型，用于增量检测口吃结构，可以连接到任何组件以进行增量解释，或者在产生当前话语时用于 “清理” 当前话语。我们在 Switchboard 对话行为语料库上训练了该系统，并展示了其在该数据集上的准确性。我们的模型在 SWDA 上比以前的神经网络基于增量的方法表现优异，同时采用较简单的架构。为了测试模型的泛化潜力，我们在没有任何附加训练的情况下，在 bAbI + 数据集上评估了相同的模型。这表明我们的方法具有很好的泛化潜力，并更加详细地阐明了哪些类型的口吃可能适合于领域通用处理。