Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension

We develop a technique for transfer learning in machine comprehension (MC) using a novel two-stage synthesis network (SynNet). Given a high-performing MC model in one domain, our technique aims to answer questions about documents in another domain, where we use no labeled data of question-answer pairs. Using the proposed SynNet with a pretrained model from the SQuAD dataset on the challenging NewsQA dataset, we achieve an F1 measure of 44.3% with a single model and 46.6% with an ensemble, approaching performance of in-domain models (F1 measure of 50.0%) and outperforming the out-of-domain baseline of 7.6%, without use of provided annotations.

[1]  O. Chapelle,et al.  Semi-Supervised Learning (Chapelle, O. et al., Eds.; 2006) [Book reviews] , 2009, IEEE Transactions on Neural Networks.

[2]  Zhiguo Wang,et al.  Multi-Perspective Context Matching for Machine Comprehension , 2016, ArXiv.

[3]  Kenton Lee,et al.  Learning Recurrent Span Representations for Extractive Question Answering , 2016, ArXiv.

[4]  Geoffrey Zweig,et al.  From captions to visual concepts and back , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Wang Ling,et al.  Latent Predictor Networks for Code Generation , 2016, ACL.

[6]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[7]  Jianfeng Gao,et al.  A Human Generated MAchine Reading COmprehension Dataset , 2018 .

[8]  Yoshua Bengio,et al.  Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus , 2016, ACL.

[9]  Deniz Yuret,et al.  Transfer Learning for Low-Resource Neural Machine Translation , 2016, EMNLP.

[10]  Trevor Darrell,et al.  Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding , 2016, EMNLP.

[11]  Andrew Chou,et al.  Semantic Parsing on Freebase from Question-Answer Pairs , 2013, EMNLP.

[12]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[13]  Kate Saenko,et al.  Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering , 2015, ECCV.

[14]  Danqi Chen,et al.  A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task , 2016, ACL.

[15]  Igor Labutov,et al.  Deep Questions without Deep Understanding , 2015, ACL.

[16]  Xavier Carreras,et al.  Simple Semi-supervised Dependency Parsing , 2008, ACL.

[17]  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 .

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

[19]  Ali Farhadi,et al.  Bidirectional Attention Flow for Machine Comprehension , 2016, ICLR.

[20]  Ruslan Salakhutdinov,et al.  Gated-Attention Readers for Text Comprehension , 2016, ACL.

[21]  Philip Bachman,et al.  Machine Comprehension by Text-to-Text Neural Question Generation , 2017, Rep4NLP@ACL.

[22]  Ruslan Salakhutdinov,et al.  Semi-Supervised QA with Generative Domain-Adaptive Nets , 2017, ACL.

[23]  Shuohang Wang,et al.  Machine Comprehension Using Match-LSTM and Answer Pointer , 2016, ICLR.

[24]  Yuandong Tian,et al.  Simple Baseline for Visual Question Answering , 2015, ArXiv.

[25]  Fei-Fei Li,et al.  Deep visual-semantic alignments for generating image descriptions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[27]  Richard Socher,et al.  Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Richard Socher,et al.  Dynamic Coattention Networks For Question Answering , 2016, ICLR.

[29]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[30]  Philip Bachman,et al.  NewsQA: A Machine Comprehension Dataset , 2016, Rep4NLP@ACL.

[31]  Jason Weston,et al.  The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations , 2015, ICLR.

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

[33]  Alexander J. Smola,et al.  Stacked Attention Networks for Image Question Answering , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[35]  K. P. Chow,et al.  LCCT: A Semi-supervised Model for Sentiment Classification , 2015, NAACL.

[36]  Xiaodong He,et al.  Character-Level Question Answering with Attention , 2016, EMNLP.

[37]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[38]  Jonathan Berant,et al.  Semantic Parsing via Paraphrasing , 2014, ACL.

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

[40]  Jonathan Berant,et al.  Building a Semantic Parser Overnight , 2015, ACL.

[41]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[42]  Oscar Saz-Torralba,et al.  Data-selective transfer learning for multi-domain speech recognition , 2015, INTERSPEECH.

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

[44]  Percy Liang,et al.  Data Recombination for Neural Semantic Parsing , 2016, ACL.

[45]  Alexander Zien,et al.  Semi-Supervised Learning , 2006 .

[46]  Richard S. Zemel,et al.  Exploring Models and Data for Image Question Answering , 2015, NIPS.