Answer-focused and Position-aware Neural Question Generation

By Xingwu Sun, Jing Liu, Yajuan Lyu, Wei He, Yanjun Ma, Shi Wang. 2018

188 citations recorded by the source corpus.

In this paper, we focus on the problem of question generation (QG). Recent neural network-based approaches employ the sequence-to-sequence model which takes an answer and its context as input and generates a relevant question as output. However, we observe two major issues with these approaches: (1) The generated interrogative words (or question words) do not match the answer type. (2) The model copies the context words that are far from and irrelevant to the answer, instead of the words that are close and relevant to the answer. To address these two issues, we propose an answer-focused and position-aware neural question generation model. (1) By answer-focused, we mean that we explicitly model question word generation by incorporating the answer embedding, which can help generate an interrogative word matching the answer type. (2) By position-aware, we mean that we model the relative distance between the context words and the answer. Hence the model can be aware of the position of the context words when copying them to generate a question. We conduct extensive experiments to examine the effectiveness of our model. The experimental results show that our model significantly improves the baseline and outperforms the state-of-the-art system.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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

In Computer Vision and Pattern Recognition

In Natural Language Processing

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).”
Quiz-Style Question Generation for News Stories (2021, unknown): “There have also been various extensions, including copy or pointer mechanisms to overcome out-ofvocabulary issues [11, 44], mechanisms for handling paragraphlength inputs [50, 51], and more [19, 33].”
Review-based Question Generation with Adaptive Instance Transfer and Augmentation (2019, background): “, 2018), answer position (Sun et al., 2018), long passage modeling (Zhao et al.”
Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring (2019, methodology): “2016) is exploited to enhance the output quality of decoders (Zhao et al. 2018; Sun et al. 2018).”
Learning to Generate Questions by LearningWhat not to Generate (2019, methodology): “ representation using the observed variable. •NQG++ [42] proposed a Seq2Seq model with a feature-rich encoder to encode answer position, POS and NER tag information. •Answer-focusedPosition-awaremodel[33]incorporates the answer embedding to help generate an interrogative word matching the answer typ”
Low-Resource Generation of Multi-hop Reasoning Questions (2020, methodology): “In the pre-processing phase, we ﬁrst mask the answer from the input contents by a special token < UNK > , to avoid the answer inclusion problem (Sun et al., 2018).”
Large Language Models are Better Reasoners with Self-Verification (2022, background): “For question generation, the diversity of the problems makes it difficult to balance the need for coherence and fact consistency between questions and answers in practical operation (Sun et al., 2018; Ji et al., 2022).”