A Joint Model for Question Answering and Question Generation

By Tong Wang, Xingdi Yuan, Adam Trischler. 2017

108 citations recorded by the source corpus.

We propose a generative machine comprehension model that learns jointly to ask and answer questions based on documents. The proposed model uses a sequence-to-sequence framework that encodes the document and generates a question (answer) given an answer (question). Significant improvement in model performance is observed empirically on the SQuAD corpus, confirming our hypothesis that the model benefits from jointly learning to perform both tasks. We believe the joint model's novelty offers a new perspective on machine comprehension beyond architectural engineering, and serves as a first step towards autonomous information seeking.

Subfields: Artificial Intelligence, Information Systems, 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 Information Systems

In Natural Language Processing

Citations in the corpus

Towards a Better Metric for Evaluating Question Generation Systems (2018, background): “A few models (Wang et al., 2017; Tang et al., 2017) treat question answering (QA) and question generation (QG) as complementary tasks and focus on jointly training for these two tasks.”
Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks (2018, background): “This is the exact setting of SQuAD, and similar problems have been addressed in, e.g. (Zhou et al., 2017; Yuan et al., 2017; Wang et al., 2017a).”
Learning with Limited Data for Multilingual Reading Comprehension (2019, methodology): “Combining models of QG and QA: Several works (Wang et al., 2017; Tang et al., 2017; Tang et al.) propose a framework jointly optimizing QG and QA model as dual.”
Self-Training for Jointly Learning to Ask and Answer Questions (2018, background): “Finally, some very recent works have concurrently recognized the relationship between QA and QG and have proposed joint training (Tang et al., 2017; Wang et al., 2017) for the two.”
A Recurrent BERT-based Model for Question Generation (2019, background): “Further, (Tang et al., 2017; Wang et al., 2017) proposed joint models to address QG and question answering as a multi-task learning setting.”
Learning by Asking Questions (2017, methodology): “Such evaluation has also been used in recent works in the language community [54, 56].”
A Unified Query-based Generative Model for Question Generation and Question Answering (2017, methodology): “For question generation (QG), our work extends previous work (Du, Shao, and Cardie, 2017; Zhou et al., 2017; Yang et al., 2017; Subramanian et al., 2017; Tang et al., 2017; Wang, Yuan, and Trischler, 2017; Yuan et al., 2017) by performing query understanding.”
Towards Solving Text-based Games by Producing Adaptive Action Spaces (2018, background): “Pointer-based sequence to sequence networks (Vinyals et al., 2015; Gulcehre et al., 2016; Wang et al., 2017) help dealing with out-of-vocabulary words by introducing a mechanism for choosing between outputting a word from the vocabulary or referencing an input word during decoding.”
Leveraging Context Information for Natural Question Generation (2018, methodology): “We adopt the multi-perspective context matching (MPCM) algorithm (Wang et al., 2017b), which takes two texts as input before producing a vector of numbers, representing similarity under different perspectives.”
Neural Models for Key Phrase Extraction and Question Generation (2018, background): “Wang et al. (2017) proposed a generative model that learns jointly to generate questions or answers from documents.”