Logographic Information Aids Learning Better Representations for Natural Language Inference

TL;DR

This paper investigates how incorporating logographic visual features into language models enhances semantic understanding in natural language inference, especially for languages with logographic scripts like Chinese and Vietnamese.

Contribution

It introduces a multi-modal approach combining contextual and glyph information, demonstrating improved representations for logographic languages in NLI tasks.

Findings

Multi-modal embeddings outperform traditional models in logographic languages.

Glyph information significantly benefits low-frequency words.

Results are consistent across six diverse languages.

Abstract

Statistical language models conventionally implement representation learning based on the contextual distribution of words or other formal units, whereas any information related to the logographic features of written text are often ignored, assuming they should be retrieved relying on the cooccurence statistics. On the other hand, as language models become larger and require more data to learn reliable representations, such assumptions may start to fall back, especially under conditions of data sparsity. Many languages, including Chinese and Vietnamese, use logographic writing systems where surface forms are represented as a visual organization of smaller graphemic units, which often contain many semantic cues. In this paper, we present a novel study which explores the benefits of providing language models with logographic information in learning better semantic representations. We test our hypothesis in the natural language inference (NLI) task by evaluating the benefit of computing multi-modal representations that combine contextual information with glyph information. Our evaluation results in six languages with different typology and writing systems suggest significant benefits of using multi-modal embeddings in languages with logograhic systems, especially for words with less occurence statistics.