Character-to-Word Attention for Word Segmentation: Research Process
نویسندگان
چکیده
منابع مشابه
Word-Context Character Embeddings for Chinese Word Segmentation
Neural parsers have benefited from automatically labeled data via dependencycontext word embeddings. We investigate training character embeddings on a word-based context in a similar way, showing that the simple method significantly improves state-of-the-art neural word segmentation models, beating tritraining baselines for leveraging autosegmented data.
متن کاملWhich Is Essential for Chinese Word Segmentation: Character versus Word
This paper proposes an empirical comparison between word-based method and character-based method for Chinese word segmentation. In three Chinese word segmentation Bakeoffs, character-based method quickly rose as a mainstream technique in this field. We disclose the linguistic background and statistical feature behind this observation. Also, an empirical study between wordbased method and charac...
متن کاملLearning Character Representations for Chinese Word Segmentation
We propose a simple yet effective semi-supervised method for improving Chinese Word Segmentation. Our method is based on learning generalizable vector and cluster representations of variable-length character sequences from large unlabeled data, which is then incorporated into a sequence labeling model with the passive-aggressive algorithm as features. We achieve state-of-the-art results on the ...
متن کاملChinese Word Segmentation as Character Tagging
In this paper we report results of a supervised machine-learning approach to Chinese word segmentation. A maximum entropy tagger is trained on manually annotated data to automatically assign to Chinese characters, or hanzi, tags that indicate the position of a hanzi within a word. The tagged output is then converted into segmented text for evaluation. Preliminary results show that this approach...
متن کاملA Character-Based Joint Model for Chinese Word Segmentation
The character-based tagging approach is a dominant technique for Chinese word segmentation, and both discriminative and generative models can be adopted in that framework. However, generative and discriminative character-based approaches are significantly different and complement each other. A simple joint model combining the character-based generative model and the discriminative one is thus p...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Natural Language Processing
سال: 2021
ISSN: 1340-7619,2185-8314
DOI: 10.5715/jnlp.28.688