Question Generation using a Scratchpad Encoder

Ryan Y Benmalek, Madian Khabsa, Suma Desu, Claire Cardie, Michele Banko

Abstract: In this paper we introduce the Scratchpad Encoder, a novel addition to the sequence to sequence (seq2seq) framework and explore its effectiveness in generating natural language questions from a given logical form. The Scratchpad encoder enables the decoder at each time step to modify all the encoder outputs, thus using the encoder as a "scratchpad" memory to keep track of what has been generated so far and to guide future generation. Experiments on a knowledge based question generation dataset show that our approach generates more fluent and expressive questions according to quantitative metrics and human judgments.

Keywords: Question Generation, Natural Language Generation, Scratchpad Encoder, Sequence to Sequence

TL;DR: In this paper we introduce the Scratchpad Encoder, a novel addition to the sequence to sequence (seq2seq) framework and explore its effectiveness in generating natural language questions from a given logical form.

Data: [SimpleQuestions](https://paperswithcode.com/dataset/simplequestions), [WebQuestions](https://paperswithcode.com/dataset/webquestions), [WebQuestionsSP](https://paperswithcode.com/dataset/webquestionssp)