Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation
This addresses the readability and processing challenges of ASR-generated transcripts for applications like summarization and reading comprehension, representing a strong incremental advance in document segmentation.
The paper tackles the problem of automatically segmenting spoken document transcripts into paragraphs to improve readability and downstream NLP tasks, achieving state-of-the-art performance with F1 score improvements of 4.2 points on an English benchmark and 4.3-10.1 points on Chinese datasets while reducing inference time to less than 1/6 of the previous best.
Transcripts generated by automatic speech recognition (ASR) systems for spoken documents lack structural annotations such as paragraphs, significantly reducing their readability. Automatically predicting paragraph segmentation for spoken documents may both improve readability and downstream NLP performance such as summarization and machine reading comprehension. We propose a sequence model with self-adaptive sliding window for accurate and efficient paragraph segmentation. We also propose an approach to exploit phonetic information, which significantly improves robustness of spoken document segmentation to ASR errors. Evaluations are conducted on the English Wiki-727K document segmentation benchmark, a Chinese Wikipedia-based document segmentation dataset we created, and an in-house Chinese spoken document dataset. Our proposed model outperforms the state-of-the-art (SOTA) model based on the same BERT-Base, increasing segmentation F1 on the English benchmark by 4.2 points and on Chinese datasets by 4.3-10.1 points, while reducing inference time to less than 1/6 of inference time of the current SOTA.