Cross-Lingual Training for Automatic Question Generation

Automatic question generation (QG) is a challenging problem in natural language understanding. QG systems are typically built assuming access to a large number of training instances where each instance is a question and its corresponding answer. For a new language, such training instances are hard to obtain making the QG problem even more challenging. Using this as our motivation, we study the reuse of an available large QG dataset in a secondary language (e.g. English) to learn a QG model for a primary language (e.g. Hindi) of interest. For the primary language, we assume access to a large amount of monolingual text but only a small QG dataset. We propose a cross-lingual QG model which uses the following training regime: (i) Unsupervised pretraining of language models in both primary and secondary languages and (ii) joint supervised training for QG in both languages. We demonstrate the efficacy of our proposed approach using two different primary languages, Hindi and Chinese. We also create and release a new question answering dataset for Hindi consisting of 6555 sentences.

[1]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[2]  Marc'Aurelio Ranzato,et al.  Sequence Level Training with Recurrent Neural Networks , 2015, ICLR.

[3]  Rico Sennrich,et al.  Improving Neural Machine Translation Models with Monolingual Data , 2015, ACL.

[4]  Wei Chen,et al.  Unsupervised Neural Machine Translation with Weight Sharing , 2018 .

[5]  Arun Kumar Sangaiah,et al.  A novel framework for Automatic Chinese Question Generation based on multi-feature neural network model , 2018, Comput. Sci. Inf. Syst..

[6]  Guillaume Lample,et al.  Phrase-Based & Neural Unsupervised Machine Translation , 2018, EMNLP.

[7]  Guillaume Lample,et al.  Cross-lingual Language Model Pretraining , 2019, NeurIPS.

[8]  Xinya Du,et al.  Learning to Ask: Neural Question Generation for Reading Comprehension , 2017, ACL.

[9]  Ganesh Ramakrishnan,et al.  A framework for automatic question generation from text using deep reinforcement learning , 2018, ArXiv.

[10]  Ganesh Ramakrishnan,et al.  Putting the Horse before the Cart: A Generator-Evaluator Framework for Question Generation from Text , 2018, CoNLL.

[11]  Ganesh Ramakrishnan,et al.  Automating Reading Comprehension by Generating Question and Answer Pairs , 2018, PAKDD.

[12]  Rico Sennrich,et al.  Neural Machine Translation of Rare Words with Subword Units , 2015, ACL.

[13]  Tao Qin,et al.  Question Answering and Question Generation as Dual Tasks , 2017, ArXiv.

[14]  Xinyan Xiao,et al.  DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications , 2017, QA@ACL.

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Mamoru Komachi,et al.  Improving Low-Resource Neural Machine Translation with Filtered Pseudo-Parallel Corpus , 2017, WAT@IJCNLP.

[17]  Tao Shen,et al.  DiSAN: Directional Self-Attention Network for RNN/CNN-free Language Understanding , 2017, AAAI.

[18]  Eneko Agirre,et al.  Unsupervised Neural Machine Translation , 2017, ICLR.

[19]  Noah A. Smith,et al.  Automatic factual question generation from text , 2011 .

[20]  Tong Wang,et al.  A Joint Model for Question Answering and Question Generation , 2017, ArXiv.

[21]  Sebastian Schuster,et al.  Cross-lingual Transfer Learning for Multilingual Task Oriented Dialog , 2018, NAACL.

[22]  Philip Gage,et al.  A new algorithm for data compression , 1994 .

[23]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[24]  Pushpak Bhattacharyya,et al.  The IIT Bombay English-Hindi Parallel Corpus , 2017, LREC.

[25]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.