Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification

Abstract

Text classification must sometimes be applied in a low-resource language with no labeled training data. However, training data may be available in a related language. We investigate whether character-level knowledge transfer from a related language helps text classification. We present a cross-lingual document classification framework (CACO) that exploits cross-lingual subword similarity by jointly training a character-based embedder and a word-based classifier. The embedder derives vector representations for input words from their written forms, and the classifier makes predictions based on the word vectors. We use a joint character representation for both the source language and the target language, which allows the embedder to generalize knowledge about source language words to target language words with similar forms. We propose a multi-task objective that can further improve the model if additional cross-lingual or monolingual resources are available. Experiments confirm that character-level knowledge transfer is more data-efficient than word-level transfer between related languages.

arXiv commentAAAI 2020

References in corpus (10)

• Natural Language Processing (almost) from Scratch
• Exploiting Similarities among Languages for Machine Translation
• A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
• Massively Multilingual Word Embeddings
• Character-based Neural Machine Translation
• Low-Resource Named Entity Recognition with Cross-Lingual, Character-Level Neural Conditional Random Fields
• Cross-lingual, Character-Level Neural Morphological Tagging
• A Resource-Free Evaluation Metric for Cross-Lingual Word Embeddings Based on Graph Modularity
• Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization
• Interactive Refinement of Cross-Lingual Word Embeddings