Neural-based Character-Level Text Error Correction (TEC) Algorithm
A Neural-based Character-Level Text Error Correction (TEC) Algorithm is a neural TEC algorithm that is a character-level TEC algorithm.
- Context:
- It can be implemented by a Neural-based Character-Level TEC System.
- Example(s):
- Counter-Example(s):
- See: Character-level Text Generation Algorithm.
References
2017
- (Schmaltz et al., 2017) ⇒ Allen Schmaltz, Yoon Kim, Alexander Rush, and Stuart Shieber. (2017). “Adapting Sequence Models for Sentence Correction.” In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.
- QUOTE: ... In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via convolutions, and that modeling the output data as a series of diffs improves effectiveness over standard approaches. ...
2016
- (Xie et al., 2016) ⇒ Ziang Xie, Anand Avati, Naveen Arivazhagan, Dan Jurafsky, and Andrew Y. Ng. (2016). “Neural Language Correction with Character-Based Attention.” In: CoRR, abs/1603.09727.
- QUOTE: Natural language correction has the potential to help language learners improve their writing skills. While approaches with separate classifiers for different error types have high precision, they do not flexibly handle errors such as redundancy or non-idiomatic phrasing. On the other hand, word and phrase-based machine translation methods are not designed to cope with orthographic errors, and have recently been outpaced by neural models. Motivated by these issues, we present a neural network-based approach to language correction. The core component of our method is an encoder-decoder recurrent neural network with an attention mechanism. ...
... Given an input sentence [math]\displaystyle{ x }[/math] that we wish to map to an output sentence [math]\displaystyle{ y }[/math], we seek to model [math]\displaystyle{ P(y \mid x) }[/math]. Our model consists of an encoder and a decoder (Sutskever et al., 2014; Cho et al., 2014). The encoder maps the input sentence to a higher-level representation with a pyramidal bidirectional RNN architecture similar to that of Chan et al. (2015). The decoder is also a recurrent neural network that uses a content-based attention mechanism (Bahdanau et al., 2014) to attend to the encoded representation and generate the output sentence one character at a time.
- QUOTE: Natural language correction has the potential to help language learners improve their writing skills. While approaches with separate classifiers for different error types have high precision, they do not flexibly handle errors such as redundancy or non-idiomatic phrasing. On the other hand, word and phrase-based machine translation methods are not designed to cope with orthographic errors, and have recently been outpaced by neural models. Motivated by these issues, we present a neural network-based approach to language correction. The core component of our method is an encoder-decoder recurrent neural network with an attention mechanism. ...