Improving Neural Question Generation using Answer Separation

By Yanghoon Kim, Hwanhee Lee, Joongbo Shin, Kyomin Jung. 2018

175 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mohit Bansal
2. Jimmy J. Lin
3. Shiyue Zhang
4. Haejun Lee
5. Jian Yin
6. Jianfeng Gao
7. Ming Li
8. Xiaolin Li

In Natural Language Processing

1. Mohit Bansal
2. Jimmy J. Lin
3. Shiyue Zhang
4. Jian Yin
5. Haejun Lee
6. Qinliang Su
7. Wei David Liu
8. Hamidreza Shahidi

Citations in the corpus

• Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering (2019, background): “, 2019) or by directly taking the whole paragraph as input (Zhao et al., 2018; Kim et al., 2018; Sun et al., 2018).”
• Low-Resource Generation of Multi-hop Reasoning Questions (2020, methodology): “(a) the basic model with the copy mechanism, i.e., NQG++ (Zhou et al., 2017); (b) ASs2s (Kim et al., 2019), which encoded the answer separately to form answer-focused questions; (c) CorefNQG (Du and Cardie, 2018) that incorporated linguistic features to represent the inputs better; (d) MaxPointer (Z”
• Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data (2019, methodology): “It is noteworthy that a similar version of our model has served as a baseline in previous papers (Liu et al., 2018; Kim et al., 2019; Liu et al., 2019a).”
• Learning to Generate Questions by LearningWhat not to Generate (2019, background): “To resolve this issue, recent works assume the aspect is known when generating a question [16, 31, 32, 38, 42] or can be detected by a third-party pipeline [7].”
• Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring (2019, background): “Enriched linguistic features with Part-Of-Speech (POS) tags, relative position information, and paragraph context are incorporated in the embedding layers (Zhou et al. 2017; Kim et al. 2018; Zhao et al. 2018).”
• Learning to Generate Questions by Learning to Recover Answer-containing Sentences (2021, background): “Kim et al. (2019) separately encoded the answer and the rest of the paragraph for question generation.”