Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models

Daniel Watson, Nasser Zalmout, Nizar Habash

Research output: Contribution to conferencePaper

Abstract

Text normalization is an important enabling technology for several NLP tasks. Recently, neural-network-based approaches have outperformed well-established models in this task. However, in languages other than English, there has been little exploration in this direction. Both the scarcity of annotated data and the complexity of the language increase the difficulty of the problem. To address these challenges, we use a sequence-to-sequence model with character-based attention, which in addition to its self-learned character embeddings, uses word embeddings pre-trained with an approach that also models subword information. This provides the neural model with access to more linguistic information especially suitable for text normalization, without large parallel corpora. We show that providing the model with word-level features bridges the gap for the neural network approach to achieve a state-of-the-art F1 score on a standard Arabic language correction shared task dataset.
Original languageEnglish (US)
Number of pages7
DOIs
StatePublished - Jun 29 2019

Fingerprint Dive into the research topics of 'Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models'. Together they form a unique fingerprint.

  • Cite this