ABSTRACT
This paper provides a unified account of two schools of thinking in information retrieval modelling: the generative retrieval focusing on predicting relevant documents given a query, and the discriminative retrieval focusing on predicting relevancy given a query-document pair. We propose a game theoretical minimax game to iteratively optimise both models. On one hand, the discriminative model, aiming to mine signals from labelled and unlabelled data, provides guidance to train the generative model towards fitting the underlying relevance distribution over documents given the query. On the other hand, the generative model, acting as an attacker to the current discriminative model, generates difficult examples for the discriminative model in an adversarial way by minimising its discrimination objective. With the competition between these two models, we show that the unified framework takes advantage of both schools of thinking: (i) the generative model learns to fit the relevance distribution over documents via the signals from the discriminative model, and (ii) the discriminative model is able to exploit the unlabelled data selected by the generative model to achieve a better estimation for document ranking. Our experimental results have demonstrated significant performance gains as much as 23.96% on Precision@5 and 15.50% on MAP over strong baselines in a variety of applications including web search, item recommendation, and question answering.
- Ricardo Baeza-Yates, Berthier Ribeiro-Neto, and others. 1999. Modern information retrieval.Google Scholar
- Oren Barkan and Noam Koenigstein 2016. Item2vec: neural item embedding for collaborative filtering MLSP Workshop.Google Scholar
- Chris Burges, Tal Shaked, Erin Renshaw, Ari Lazier, Matt Deeds, Nicole Hamilton, and Greg Hullender 2005. Learning to Rank Using Gradient Descent. In ICML. Google ScholarDigital Library
- Christopher J. C. Burges. 2010. From RankNet to LambdaRank to LambdaMART: An Overview. Learning (2010).Google Scholar
- Christopher J. C. Burges, Robert Ragno, and Quoc Viet Le. 2006. Learning to Rank with Nonsmooth Cost Functions. In NIPS.Google Scholar
- Zhe Cao, Tao Qin, Tie-Yan Liu, Ming-Feng Tsai, and Hang Li 2007. Learning to rank: from pairwise approach to listwise approach ICML.Google Scholar
- Wei Chen, Tie-Yan Liu, Yanyan Lan, Zhi-Ming Ma, and Hang Li 2009. Ranking Measures and Loss Functions in Learning to Rank NIPS. 315--323.Google Scholar
- Paul Covington, Jay Adams, and Emre Sargin. 2016. Deep neural networks for youtube recommendations. RecSys. Google ScholarDigital Library
- Cícero Nogueira dos Santos, Ming Tan, Bing Xiang, and Bowen Zhou 2016. Attentive Pooling Networks. CoRR (2016).Google Scholar
- Minwei Feng, Bing Xiang, Michael R Glass, Lidan Wang, and Bowen Zhou 2015. Applying deep learning to answer selection: A study and an open task ASRU Workshop.Google Scholar
- Yoav Freund, Raj Iyer, Robert E Schapire, and Yoram Singer. 2003. An Efficient Boosting Algorithm for Combining Preferences. JMLR (2003).Google Scholar
- Ian Goodfellow. 2016. NIPS 2016 Tutorial: Generative Adversarial Networks. arXiv preprint arXiv:1701.00160 (2016).Google Scholar
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In NIPS.Google Scholar
- Ian J. Goodfellow. 2014. On Distinguishability Criteria for Estimating Generative Models. arXiv:1412.6515 (2014).Google Scholar
- Michael Gutmann and Aapo Hyvärinen 2010. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models AISTATS.Google Scholar
- Ralf Herbrich, Thore Graepel, and Klaus Obermayer. 2000. Large Margin Rank Boundaries for Ordinal Regression. Advances in Large Margin Classifiers.Google Scholar
- Thomas Hofmann. 1999. Probabilistic Latent Semantic Indexing. In SIGIR. Google ScholarDigital Library
- Ferenc Huszár. 2015. How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary? arXiv preprint arXiv:1511.05101 (2015).Google Scholar
- Thorsten Joachims. 2002. Optimizing search engines using clickthrough data. KDD. Google ScholarDigital Library
- Yoon Kim 2014. Convolutional Neural Networks for Sentence Classification. arXiv preprint arXiv:1408.5882 (2014).Google Scholar
- Yehuda Koren, Robert Bell, and Chris Volinsky. 2009. Matrix factorization techniques for recommender systems. Computer (2009).Google ScholarDigital Library
- John Lafferty and Chengxiang Zhai 2002. Probabilistic Relevance Models Based on Document and Query Generation Language Modeling and Information Retrieval.Google Scholar
- Ping Li, Christopher J. C. Burges, Qiang Wu, J. C. Platt, D. Koller, Y. Singer, and S. Roweis 2007. McRank: Learning to Rank Using Multiple Classification and Gradient Boosting. NIPS.Google Scholar
- Tie-Yan Liu. 2009. Learning to rank for information retrieval. Foundations and Trends in Information Retrieval (2009).Google Scholar
- Tie-Yan Liu, Jun Xu, Tao Qin, Wenying Xiong, and Hang Li 2007. LETOR: Benchmark Dataset for Research on Learning to Rank for Information Retrieval Proceedings of SIGIR 2007 Workshop on Learning to Rank for Information Retrieval.Google Scholar
- Jiyun Luo, Sicong Zhang, and Hui Yang 2014. Win-win search: dual-agent stochastic game in session search SIGIR.Google Scholar
- H. Brendan McMahan, Gary Holt, David Sculley, Michael Young, Dietmar Ebner, Julian Grady, Lan Nie, Todd Phillips, Eugene Davydov, Daniel Golovin, and others 2013. Ad click prediction: a view from the trenches. In KDD. Google ScholarDigital Library
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S. Corrado, and Jeff Dean 2013. Distributed representations of words and phrases and their compositionality NIPS.Google Scholar
- Mehdi Mirza and Simon Osindero 2014. Conditional Generative Adversarial Nets. arXiv preprint arXiv:1411.1784 (2014).Google Scholar
- In Jae Myung. 2003. Tutorial on maximum likelihood estimation. Journal of mathematical Psychology (2003).Google Scholar
- Ramesh Nallapati. 2004. Discriminative Models for Information Retrieval. SIGIR. Google ScholarDigital Library
- Jay M. Ponte and W. Bruce Croft 1998. A language modeling approach to information retrieval SIGIR.Google Scholar
- Steffen Rendle. 2010. Factorization machines. In ICDM. Google ScholarDigital Library
- Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme 2009. BPR: Bayesian personalized ranking from implicit feedback UAI.Google Scholar
- Stephen E. Robertson and K. Sparck Jones 1976. Relevance weighting of search terms. Journal of the American Society for Information science (1976).Google Scholar
- Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved Techniques for Training GANs. In NIPS.Google Scholar
- Aliaksei Severyn and Alessandro Moschitti 2015. Learning to rank short text pairs with convolutional deep neural networks SIGIR.Google Scholar
- Richard S. Sutton, David A. McAllester, Satinder P. Singh, Yishay Mansour, and others 1999. Policy Gradient Methods for Reinforcement Learning with Function Approximation NIPS.Google Scholar
- Tao Tao and ChengXiang Zhai 2006. Regularized estimation of mixture models for robust pseudo-relevance feedback SIGIR. ACM, 162--169.Google Scholar
- Di Wang and Eric Nyberg 2015. A Long Short-Term Memory Model for Answer Sentence Selection in Question Answering ACL.Google Scholar
- Jun Wang, Arjen P. De Vries, and Marcel J. T. Reinders. 2006. Unifying user-based and item-based collaborative filtering approaches by similarity fusion SIGIR.Google Scholar
- Ronald J. Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning (1992).Google Scholar
- Yingce Xia, Di He, Tao Qin, Liwei Wang, Nenghai Yu, Tie-Yan Liu, and Wei-Ying Ma 2016. Dual Learning for Machine Translation. In NIPS.Google Scholar
- Lantao Yu, Weinan Zhang, Jun Wang, and Yong Yu. 2017. SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient AAAI.Google Scholar
- Shipeng Yu, Deng Cai, Ji-Rong Wen, and Wei-Ying Ma. 2003. Improving pseudo-relevance feedback in web information retrieval using web page segmentation. In WWW. ACM, 11--18. Google ScholarDigital Library
- Fajie Yuan, Guibing Guo, Joemon M. Jose, Long Chen, Haitao Yu, and Weinan Zhang. 2016. Lambdafm: learning optimal ranking with factorization machines using lambda surrogates CIKM.Google Scholar
- ChengXiang Zhai. 2016. Towards a game-theoretic framework for text data retrieval. IEEE Data Eng. Bull. (2016).Google Scholar
- Chengxiang Zhai and John Lafferty 2004. A study of smoothing methods for language models applied to information retrieval. TOIS (2004).Google Scholar
- ChengXiang Zhai and John D. Lafferty 2001. Model-based Feedback in the Language Modeling Approach to Information Retrieval CIKM.Google ScholarDigital Library
- Peng Zhang, Qian Yu, Yuexian Hou, Dawei Song, Jingfei Li, and Bin Hu. 2017. A Distribution Separation Method Using Irrelevance Feedback Data for Information Retrieval. ACM TIST (2017).Google Scholar
- Weinan Zhang, Tianqi Chen, Jun Wang, and Yong Yu. 2013. Optimizing top-n collaborative filtering via dynamic negative item sampling SIGIR.Google Scholar
Index Terms
- IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models
Recommendations
Learning to find answers to questions on the Web
We introduce a method for learning to find documents on the Web that contain answers to a given natural language question. In our approach, questions are transformed into new queries aimed at maximizing the probability of retrieving answers from ...
Improving Convergence in IRGAN with PPO
CoDS COMAD 2020: Proceedings of the 7th ACM IKDD CoDS and 25th COMADInformation retrieval modeling aims to optimise generative and discriminative retrieval strategies, where, generative retrieval focuses on predicting query-specific relevant documents and discriminative retrieval tries to predict relevancy given a query-...
An intelligent platform for information retrieval
Proceedings of the 2005 joint Chinese-German conference on Cognitive systemsInformation Retrieval (IR) has played a very important role in our modern life. However, the results of search engines are not satisfactory for human intelligent activities. The platform proposed in this paper tried to solve the problems from three ...
Comments