Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?
This addresses the challenge of flexible dependency modeling in unsupervised POS tagging for natural language processing, though it shows mixed trends in real languages and incremental improvements.
The paper tackles the problem of unsupervised part-of-speech tagging by proposing a Masked Part-of-Speech Model (MPoSM) to handle long-term and bidirectional dependencies like subject-verb agreement, achieving competitive results on English and 10 diverse languages, with MPoSM performing better overall in synthetic experiments on tag agreement.
Previous Part-Of-Speech (POS) induction models usually assume certain independence assumptions (e.g., Markov, unidirectional, local dependency) that do not hold in real languages. For example, the subject-verb agreement can be both long-term and bidirectional. To facilitate flexible dependency modeling, we propose a Masked Part-of-Speech Model (MPoSM), inspired by the recent success of Masked Language Models (MLM). MPoSM can model arbitrary tag dependency and perform POS induction through the objective of masked POS reconstruction. We achieve competitive results on both the English Penn WSJ dataset as well as the universal treebank containing 10 diverse languages. Though modeling the long-term dependency should ideally help this task, our ablation study shows mixed trends in different languages. To better understand this phenomenon, we design a novel synthetic experiment that can specifically diagnose the model's ability to learn tag agreement. Surprisingly, we find that even strong baselines fail to solve this problem consistently in a very simplified setting: the agreement between adjacent words. Nonetheless, MPoSM achieves overall better performance. Lastly, we conduct a detailed error analysis to shed light on other remaining challenges. Our code is available at https://github.com/owenzx/MPoSM