Inflected Forms Are Redundant in Question Generation Models

TL;DR

This paper improves question generation models by reducing inflected form redundancy through word root replacement and a combined generation-copy-transformation approach, leading to better performance and efficiency.

Contribution

It introduces a novel method to fuse word transformation with question generation, decreasing decoder complexity and noise, and enhancing model accuracy.

Findings

Significant improvements in BLEU, ROUGE-L, and METEOR scores.

Reduced time cost and noise in question generation.

Effective application to RNN-based and UniLM models.

Abstract

Neural models with an encoder-decoder framework provide a feasible solution to Question Generation (QG). However, after analyzing the model vocabulary we find that current models (both RNN-based and pre-training based) have more than 23\% inflected forms. As a result, the encoder will generate separate embeddings for the inflected forms, leading to a waste of training data and parameters. Even worse, in decoding these models are vulnerable to irrelevant noise and they suffer from high computational costs. In this paper, we propose an approach to enhance the performance of QG by fusing word transformation. Firstly, we identify the inflected forms of words from the input of encoder, and replace them with the root words, letting the encoder pay more attention to the repetitive root words. Secondly, we propose to adapt QG as a combination of the following actions in the encode-decoder framework: generating a question word, copying a word from the source sequence or generating a word transformation type. Such extension can greatly decrease the size of predicted words in the decoder as well as noise. We apply our approach to a typical RNN-based model and \textsc{UniLM} to get the improved versions. We conduct extensive experiments on SQuAD and MS MARCO datasets. The experimental results show that the improved versions can significantly outperform the corresponding baselines in terms of BLEU, ROUGE-L and METEOR as well as time cost.