Exploiting Unlabeled Data for Neural Grammatical Error Detection
| Autor: | Yang Liu, Zhuo-Ran Liu |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Artificial neural network
business.industry Computer science 010401 analytical chemistry Pattern recognition 02 engineering and technology Machine learning computer.software_genre 01 natural sciences Grammatical error 0104 chemical sciences Computer Science Applications Theoretical Computer Science Support vector machine ComputingMethodologies_PATTERNRECOGNITION Computational Theory and Mathematics Binary classification Hardware and Architecture 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business computer Software Word (computer architecture) |
| Zdroj: | Journal of Computer Science and Technology. 32:758-767 |
| ISSN: | 1860-4749 1000-9000 |
| DOI: | 10.1007/s11390-017-1757-4 |
| Popis: | Identifying and correcting grammatical errors in the text written by non-native writers have received increasing attention in recent years. Although a number of annotated corpora have been established to facilitate data-driven grammatical error detection and correction approaches, they are still limited in terms of quantity and coverage because human annotation is labor-intensive, time-consuming, and expensive. In this work, we propose to utilize unlabeled data to train neural network based grammatical error detection models. The basic idea is to cast error detection as a binary classification problem and derive positive and negative training examples from unlabeled data. We introduce an attention-based neural network to capture long-distance dependencies that influence the word being detected. Experiments show that the proposed approach significantly outperforms SVM and convolutional networks with fixed-size context window. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink