Improving Neural Question Generation using Answer Separation
This addresses a specific bottleneck in neural question generation for NLP applications, representing an incremental improvement.
The paper tackled the problem of neural question generation models producing unintended questions by including answer words, by proposing an answer-separated seq2seq model and keyword-net module to better utilize passage and answer information. The result was a significant reduction in improper questions and outperforming previous state-of-the-art models.
Neural question generation (NQG) is the task of generating a question from a given passage with deep neural networks. Previous NQG models suffer from a problem that a significant proportion of the generated questions include words in the question target, resulting in the generation of unintended questions. In this paper, we propose answer-separated seq2seq, which better utilizes the information from both the passage and the target answer. By replacing the target answer in the original passage with a special token, our model learns to identify which interrogative word should be used. We also propose a new module termed keyword-net, which helps the model better capture the key information in the target answer and generate an appropriate question. Experimental results demonstrate that our answer separation method significantly reduces the number of improper questions which include answers. Consequently, our model significantly outperforms previous state-of-the-art NQG models.