Adaptive Cross-Lingual Question Generation with Minimal Resources

The task of question generation (QG) aims to create valid questions and correlated answers from the given text. Despite the neural QG approaches have achieved promising results, they are typically developed for languages with rich annotated training data. Because of the high annotation cost, it is difficult to deploy to other low-resource languages. Besides, different samples have their own characteristics on the aspects of text contextual structure, question type and correlations. Without capturing these diversified characteristics, the traditional one-size-fits-all model is hard to generate the best results. To address this problem, we study the task of cross-lingual QG from an adaptive learning perspective. Concretely, we first build a basic QG model on a multilingual space using the labelled data. In this way, we can transfer the supervision from the high-resource language to the language lacking labelled data. We then design a task-specific meta-learner to optimize the basic QG model. Each sample and its similar instances are viewed as a pseudo-QG task. The asking patterns and logical forms contained in the similar samples can be used as a guide to fine-tune the model fitly and produce the optimal results accordingly. Considering that each sample contains the text, question and answer, with unknown semantic correlations among them, we propose a context-dependent retriever to measure the similarity of such structured inputs. Experimental results on three languages of three typical data sets show the effectiveness of our approach.

[1]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[2]  Xiaojun Quan,et al.  Generating Multi-hop Reasoning Questions to Improve Machine Reading Comprehension , 2020, WWW.

[3]  Yuting Lai,et al.  DRCD: a Chinese Machine Reading Comprehension Dataset , 2018, ArXiv.

[4]  Bernhard Schölkopf,et al.  A Kernel Two-Sample Test , 2012, J. Mach. Learn. Res..

[5]  Percy Liang,et al.  A Retrieve-and-Edit Framework for Predicting Structured Outputs , 2018, NeurIPS.

[6]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[7]  Kevin Gimpel,et al.  Controllable Paraphrase Generation with a Syntactic Exemplar , 2019, ACL.

[8]  Ganesh Ramakrishnan,et al.  Cross-Lingual Training for Automatic Question Generation , 2019, ACL.

[9]  Mitesh M. Khapra,et al.  Towards a Better Metric for Evaluating Question Generation Systems , 2018, EMNLP.

[10]  Ming Zhou,et al.  Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing , 2019, ACL.

[11]  Ming Zhou,et al.  Question Generation for Question Answering , 2017, EMNLP.

[12]  Jianfeng Gao,et al.  Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation , 2017, IJCNLP.

[13]  Richard Socher,et al.  A Deep Reinforced Model for Abstractive Summarization , 2017, ICLR.

[14]  Nicola De Cao,et al.  Hyperspherical Variational Auto-Encoders , 2018, UAI 2018.

[15]  Justus J. Randolph.  Free-Marginal Multirater Kappa (multirater K[free]): An Alternative to Fleiss' Fixed-Marginal Multirater Kappa. , 2005 .

[16]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[17]  A. Müller.  Integral Probability Metrics and Their Generating Classes of Functions , 1997, Advances in Applied Probability.

[18]  Hannes Schulz,et al.  Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation , 2017, ArXiv.

[19]  Wei Liu,et al.  Low-Resource Generation of Multi-hop Reasoning Questions , 2020, ACL.

[20]  Mark Dredze,et al.  Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT , 2019, EMNLP.

[21]  Mohammed Elmogy,et al.  Automatic English Question Generation System Based on Template Driven Scheme , 2014 .

[22]  Marcin Andrychowicz,et al.  Learning to learn by gradient descent by gradient descent , 2016, NIPS.

[23]  Gert R. G. Lanckriet,et al.  On the empirical estimation of integral probability metrics , 2012 .

[24]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

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

[26]  Yue Zhang,et al.  Leveraging Context Information for Natural Question Generation , 2018, NAACL.

[27]  Jian Yin,et al.  Inferential Machine Comprehension: Answering Questions by Recursively Deducing the Evidence Chain from Text , 2019, ACL.

[28]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[29]  Navdeep Jaitly,et al.  Pointer Networks , 2015, NIPS.

[30]  Hang Li,et al.  “ Tony ” DNN Embedding for “ Tony ” Selective Read for “ Tony ” ( a ) Attention-based Encoder-Decoder ( RNNSearch ) ( c ) State Update s 4 SourceVocabulary Softmax Prob , 2016 .

[31]  Christopher D. Manning,et al.  Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks , 2015, ACL.

[32]  Ming Zhou,et al.  Gated Self-Matching Networks for Reading Comprehension and Question Answering , 2017, ACL.

[33]  Jiacheng Xu,et al.  Spherical Latent Spaces for Stable Variational Autoencoders , 2018, EMNLP.

[34]  Jinjun Xiong,et al.  Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus , 2019, NAACL.

[35]  Dan Roth,et al.  Robust Cross-lingual Hypernymy Detection using Dependency Context , 2018, NAACL-HLT.

[36]  Holger Schwenk,et al.  Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond , 2018, Transactions of the Association for Computational Linguistics.

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

[38]  Vaibhava Goel,et al.  Self-Critical Sequence Training for Image Captioning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[40]  Alon Lavie,et al.  METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments , 2005, IEEvaluation@ACL.

[41]  Jakob Uszkoreit,et al.  Cross-lingual Word Clusters for Direct Transfer of Linguistic Structure , 2012, NAACL.

[42]  Wentao Ma,et al.  A Span-Extraction Dataset for Chinese Machine Reading Comprehension , 2019, EMNLP-IJCNLP.

[43]  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..

[44]  Tong Wang,et al.  Neural Models for Key Phrase Extraction and Question Generation , 2017, QA@ACL.

[45]  Kyomin Jung,et al.  Improving Neural Question Generation using Answer Separation , 2018, AAAI.

[46]  Mirella Lapata,et al.  Sentence Simplification with Deep Reinforcement Learning , 2017, EMNLP.

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

[48]  Boi Faltings,et al.  Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems , 2019, IJCAI.

[49]  A. Viera,et al.  Understanding interobserver agreement: the kappa statistic. , 2005, Family medicine.

[50]  Li Dong,et al.  Cross-Lingual Natural Language Generation via Pre-Training , 2020, AAAI.

[51]  Stephen D. Mayhew,et al.  Cross-Lingual Named Entity Recognition via Wikification , 2016, CoNLL.

[52]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[53]  Sergey Levine,et al.  Trust Region Policy Optimization , 2015, ICML.

[54]  Xin Wang,et al.  Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models , 2019, ACL.

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

[56]  Po-Sen Huang,et al.  Natural Language to Structured Query Generation via Meta-Learning , 2018, NAACL.

[57]  Guoxin Wang,et al.  Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources , 2019, AAAI.

[58]  Seungyoung Lim,et al.  KorQuAD1.0: Korean QA Dataset for Machine Reading Comprehension , 2019, ArXiv.

[59]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

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

[61]  Ayah Zirikly,et al.  Cross-lingual Transfer of Named Entity Recognizers without Parallel Corpora , 2015, ACL.

[62]  Tao Xiang,et al.  Learning to Compare: Relation Network for Few-Shot Learning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[63]  Razvan Pascanu,et al.  Meta-Learning with Latent Embedding Optimization , 2018, ICLR.

[64]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[65]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[66]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[67]  Xinya Du,et al.  Identifying Where to Focus in Reading Comprehension for Neural Question Generation , 2017, EMNLP.

[68]  John C. Nesbit,et al.  Generating Natural Language Questions to Support Learning On-Line , 2013, ENLG.

[69]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[70]  Xuanjing Huang,et al.  Meta Multi-Task Learning for Sequence Modeling , 2018, AAAI.