口语语句无监督成分句法分析的级联与直接方法
Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences
AI总结：
本文首次研究口语语句的无监督成分句法分析，比较级联ASR与直接训练两种方法，发现级联方法更优，且准确分割足以解析口语，直接方法能无偏学习头部方向性。
摘要：
以往关于无监督句法分析的研究仅限于书面形式。本文首次研究了在给定无标签口语语句和无配对文本数据的情况下，对口语进行无监督成分句法分析。目标是确定口语语句的层次句法结构，以成分句法树的形式呈现，其中每个节点是对应于一个成分的音频片段。我们比较了两种方法：（1）将无监督自动语音识别（ASR）模型与无监督句法分析器级联，以获得ASR转录文本上的句法树；（2）直接在连续的词级语音表示上训练无监督句法分析器。这首先通过将话语分割成词级片段序列，并在片段内聚合自监督语音表示以获得片段嵌入来实现。我们发现，在无配对文本上单独训练句法分析器并直接应用于ASR转录文本进行推理，在无监督句法分析上取得了更好的结果。此外，我们的结果表明，仅凭准确的分割可能就足以准确解析口语语句。最后，我们展示了直接方法可以在没有任何显式归纳偏置的情况下，对头前置语言和头后置语言都正确学习头部方向性。
英文摘要：
Past work on unsupervised parsing is constrained to written form. In this paper, we present the first study on unsupervised spoken constituency parsing given unlabeled spoken sentences and unpaired textual data. The goal is to determine the spoken sentences' hierarchical syntactic structure in the form of constituency parse trees, such that each node is a span of audio that corresponds to a constituent. We compare two approaches: (1) cascading an unsupervised automatic speech recognition (ASR) model and an unsupervised parser to obtain parse trees on ASR transcripts, and (2) direct training an unsupervised parser on continuous word-level speech representations. This is done by first splitting utterances into sequences of word-level segments, and aggregating self-supervised speech representations within segments to obtain segment embeddings. We find that separately training a parser on the unpaired text and directly applying it on ASR transcripts for inference produces better results for unsupervised parsing. Additionally, our results suggest that accurate segmentation alone may be sufficient to parse spoken sentences accurately. Finally, we show the direct approach may learn head-directionality correctly for both head-initial and head-final languages without any explicit inductive bias.
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。
