Neural Sequence Segmentation as Determining the Leftmost Segments
This work addresses text segmentation for natural language processing tasks, offering a novel approach that improves accuracy in modeling long-term dependencies, though it is incremental in its method.
The paper tackles the problem of text segmentation by proposing a segment-level framework that incrementally identifies the leftmost segments, addressing limitations in capturing long-term dependencies. It achieves new state-of-the-art results on syntactic chunking and Chinese POS tagging across three datasets, with significant performance improvements over previous baselines.
Prior methods to text segmentation are mostly at token level. Despite the adequacy, this nature limits their full potential to capture the long-term dependencies among segments. In this work, we propose a novel framework that incrementally segments natural language sentences at segment level. For every step in segmentation, it recognizes the leftmost segment of the remaining sequence. Implementations involve LSTM-minus technique to construct the phrase representations and recurrent neural networks (RNN) to model the iterations of determining the leftmost segments. We have conducted extensive experiments on syntactic chunking and Chinese part-of-speech (POS) tagging across 3 datasets, demonstrating that our methods have significantly outperformed previous all baselines and achieved new state-of-the-art results. Moreover, qualitative analysis and the study on segmenting long-length sentences verify its effectiveness in modeling long-term dependencies.