Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels
In this study, we investigated the effectiveness of augmented data for encoder-decoder-based neural normalization models. Attention based encoder-decoder models are greatly effective in generating many natural languages. {\%} such as machine translation or machine summarization. In general, we have to prepare for a large amount of training data to train an encoder-decoder model. Unlike machine translation, there are few training data for text-normalization tasks. In this paper, we propose two methods for generating augmented data. The experimental results with Japanese dialect normalization indicate that our methods are effective for an encoder-decoder model and achieve higher BLEU score than that of baselines. We also investigated the oracle performance and revealed that there is sufficient room for improving an encoder-decoder model.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationDecoderMachine TranslationText NormalizationText SummarizationTranslationSimilar Papers 제목 키워드 기반
Morphological Analysis for Japanese Noisy Text based on Character-level and Word-level Normalization
N-Gramas de Caractere como T\'ecnica de Normaliza\cc\~ao Morfol\'ogica para L\'\ingua Portuguesa: Um Estudo em Categoriza\cc\~ao de Textos (Character N-grams as a Morphological Normalization Technique for Portuguese Language: A Study in Text Categorization)
Applying the Transformer to Character-level Transduction
The transformer has been shown to outperform recurrent neural network-based sequence-to-sequence models in various word-level NLP tasks. Yet for character-level transduction tasks, e.g. morphological inflection generatio…
Grapheme-to-Phoneme ConversionMorphological InflectionText NormalizationTransliterationJoint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Tagging
Semitic languages can be highly ambiguous, having several interpretations of the same surface forms, and morphologically rich, having many morphemes that realize several morphological features. This is further exacerbate…
LemmatizationMorphological TaggingAutomatically Extracting Variant-Normalization Pairs for Japanese Text Normalization
Social media texts, such as tweets from Twitter, contain many types of non-standard tokens, and the number of normalization approaches for handling such noisy text has been increasing. We present a method for automatical…
Machine TranslationMorphological AnalysisText Normalization