Incorporating Sememes into Chinese Definition Modeling

TL;DR

This paper introduces novel models that incorporate sememes into Chinese definition modeling, significantly improving the quality of generated definitions by leveraging an attention mechanism and a new corpus.

Contribution

The paper presents two innovative models, AAM and SAAM, that effectively integrate sememes into Chinese definition generation, advancing the state-of-the-art performance.

Findings

AAM outperforms previous models with +6.0 BLEU score.

SAAM reduces path length by replacing recurrent connections with self-attention.

Incorporating sememes improves definition generation quality.

Abstract

Chinese definition modeling is a challenging task that generates a dictionary definition in Chinese for a given Chinese word. To accomplish this task, we construct the Chinese Definition Modeling Corpus (CDM), which contains triples of word, sememes and the corresponding definition. We present two novel models to improve Chinese definition modeling: the Adaptive-Attention model (AAM) and the Self- and Adaptive-Attention Model (SAAM). AAM successfully incorporates sememes for generating the definition with an adaptive attention mechanism. It has the capability to decide which sememes to focus on and when to pay attention to sememes. SAAM further replaces recurrent connections in AAM with self-attention and relies entirely on the attention mechanism, reducing the path length between word, sememes and definition. Experiments on CDM demonstrate that by incorporating sememes, our best proposed model can outperform the state-of-the-art method by +6.0 BLEU.