Sememe Prediction: Learning Semantic Knowledge from Unstructured Textual Wiki Descriptions

TL;DR

This paper introduces a novel sequence-to-sequence model for automatically predicting semantic units called sememes from wiki descriptions, significantly improving over baselines and amateur human annotators.

Contribution

It proposes the LD-seq2seq model with a soft loss function for weakly ordered multi-label sememe prediction from textual descriptions.

Findings

LD-seq2seq outperforms all baseline models.

The model surpasses amateur human annotators.

Results demonstrate effective automatic sememe prediction.

Abstract

Huge numbers of new words emerge every day, leading to a great need for representing them with semantic meaning that is understandable to NLP systems. Sememes are defined as the minimum semantic units of human languages, the combination of which can represent the meaning of a word. Manual construction of sememe based knowledge bases is time-consuming and labor-intensive. Fortunately, communities are devoted to composing the descriptions of words in the wiki websites. In this paper, we explore to automatically predict lexical sememes based on the descriptions of the words in the wiki websites. We view this problem as a weakly ordered multi-label task and propose a Label Distributed seq2seq model (LD-seq2seq) with a novel soft loss function to solve the problem. In the experiments, we take a real-world sememe knowledge base HowNet and the corresponding descriptions of the words in Baidu Wiki for training and evaluation. The results show that our LD-seq2seq model not only beats all the baselines significantly on the test set, but also outperforms amateur human annotators in a random subset of the test set.