How to Ask Good Questions? Try to Leverage Paraphrases

Abstract

Given a sentence and its relevant answer, how to ask good questions is a challenging task, which has many real applications. Inspired by human's paraphrasing capability to ask questions of the same meaning but with diverse expressions, we propose to incorporate paraphrase knowledge into question generation(QG) to generate human-like questions. Specifically, we present a two-hand hybrid model leveraging a self-built paraphrase resource, which is automatically conducted by a simple back-translation method. On the one hand, we conduct multi-task learning with sentence-level paraphrase generation (PG) as an auxiliary task to supplement paraphrase knowledge to the task-share encoder. On the other hand, we adopt a new loss function for diversity training to introduce more question patterns to QG. Extensive experimental results show that our proposed model obtains obvious performance gain over several strong baselines, and further human evaluation validates that our model can ask questions of high quality by leveraging paraphrase knowledge.

Paragraph Level Multi-Perspective Context Modeling for Question Generation

“…We find that our full model outperforms the best previous paragraph-level model: S2S+GSA+MP [3] on all evaluations except BLEU-1, which indicates that our method performs better on the modeling of paragraph context. We also achieve higher scores than the recently promising methods with multi-task [7,8], it is worth noting that our method does not resort to any auxiliary task, thus any ingenious training method can be employed for further promotion. Effect of ALBERT We remove the ALBERT in this ablation, we can see that there is a significant improvement especially on METEOR, which benefits from the contextualization power of ALBERT.…”

“…PG enhanced QG [8], a sentence-level model that is assisted by auxiliary paraphrase generation task.…”

“…Kang et al [6] utilized the type of interrogative word to drive QG task. Zhou et al [7] and Jia et al [8] treated language modeling and paraphrase generation respectively as auxiliary task to assist QG context modeling with multi-task learning.…”

Improving Paraphrase Detection with the Adversarial Paraphrasing Task

“…TwitterPPDB subset of AP T 5 2005; Fernando and Stevenson, 2008;Socher et al, 2011;Jia et al, 2020) is an important task in the field of NLP, finding downstream applications in machine translation (Callison-Burch et al, 2006;Apidianaki et al, 2018;Mayhew et al, 2020), text summarization, plagiarism detection (Hunt et al, 2019), question answering, and sentence simplification (Guo et al, 2018). Paraphrases have proven to be a crucial part of NLP and language education, with research showing that paraphrasing helps improve reading comprehension skills (Lee and Colln, 2003;Hagaman and Reid, 2008).…”

Learning to Ask Conversational Questions by Optimizing Levenshtein Distance

“…and Qi et al (2020) define a question utility function to guide the generation of conversational questions. Nakanishi et al (2019); Jia et al (2020) incorporate knowledge with auxiliary tasks. These methods may generate irrelevant questions due to their pure generation nature.…”