Publications

Download BibTeX.

2020 October	Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm Ke Chen, Cheng-i Wang, Taylor Berg-Kirkpatrick, and Shlomo Dubnov. The 21st International Society for Music Information Retrieval Conferencec (ISMIR).
2020 July	Refer360°: A Referring Expression Recognition Dataset in 360° Images Volkan Cirik, Taylor Berg-Kirkpatrick, and Louis-Philippe Morency. The 58th Annual Meeting of the Association for Computational Linguistics (ACL).
2020 July	A Probabilistic Generative Model for Typographical Analysis of Early Modern Printing Kartik Goyal, Chris Dyer, Christopher Warren, Max G'Sell, and Taylor Berg-Kirkpatrick. The 58th Annual Meeting of the Association for Computational Linguistics (ACL).
2020 July	Phonetic and Visual Priors for Decipherment of Informal Romanization Maria Ryskina, Matthew R. Gormley, and Taylor Berg-Kirkpatrick. The 58th Annual Meeting of the Association for Computational Linguistics (ACL).
2020 April	A Probabilistic Formulation of Unsupervised Text Style Transfer Junxian He*, Xinyi Wang*, Graham Neubig, and Taylor Berg-Kirkpatrick. The Eighth International Conference on Learning Representations (ICLR).
2020 April	Domain Adaptation via Context Prediction for Engineering Diagram Search Harsh Jhamtani and Taylor Berg-Kirkpatrick. The 42nd European Conference on Information Retrieval (ECIR).
2020 January	Where New Words Are Born: Distributional Semantic Analysis of Neologisms and Their Semantic Neighborhoods Maria Ryskina, Ella Rabinovich, Taylor Berg-Kirkpatrick, David R. Mortensen, and Yulia Tsvetkov. The Third Annual Meeting of the Society for Computation in Linguistics (SCiL).
2019 November	A Bilingual Generative Transformer for Semantic Sentence Embedding John Wieting, Graham Neubig, and Taylor Berg-Kirkpatrick. arXiv preprint.
2019 November	A Deep Factorization of Style and Structure in Fonts Nikita Srivatsan, Jonathan T. Barron, Dan Klein, and Taylor Berg-Kirkpatrick. The 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP-IJCNLP).
2019 November	Learning Rhyming Constraints using Structured Adversaries Harsh Jhamtani, Sanket Vaibhav Mehta, Jaime Carbonell, and Taylor Berg-Kirkpatrick. The 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP-IJCNLP).
2019 November	A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text Junxian He*, Bohan Li*, Graham Neubig, Taylor Berg-Kirkpatrick, and Yiming Yang. The 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP-IJCNLP).
2019 July	Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections Junxian He, Zhisong Zhang, Taylor Berg-Kirkpatrick, and Graham Neubig. The 57th Annual Meeting of the Association for Computational Linguistics (ACL).
2019 July	Simple and Effective Paraphrastic Similarity from Parallel Translations John Wieting, Kevin Gimpel, Graham Neubig, and Taylor Berg-Kirkpatrick. The 57th Annual Meeting of the Association for Computational Linguistics (ACL).
2019 July	Beyond BLEU: Training Neural Machine Translation with Semantic Similarity John Wieting, Taylor Berg-Kirkpatrick, Kevin Gimpel, and Graham Neubig. The 57th Annual Meeting of the Association for Computational Linguistics (ACL).
2019 June	Modeling Self-Repetition in Music Generation using Generative Adversarial Networks Harsh Jhamtani and Taylor Berg-Kirkpatrick. Machine Learning for Music Discovery Workshop (ML4MD) at ICML 2019.
2019 June	An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search Kartik Goyal, Chris Dyer, and Taylor Berg-Kirkpatrick. The 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL).
2019 May	Lagging Inference Networks and Posterior Collapse in Variational Autoencoders Junxian He, Daniel Spokoyny, Graham Neubig, and Taylor Berg-Kirkpatrick. The Seventh International Conference on Learning Representations (ICLR).
2018 December	Unsupervised Text Style Transfer using Language Models as Discriminators Zichao Yang, Zhiting Hu, Chris Dyer, Eric P. Xing, and Taylor Berg-Kirkpatrick. The Thirty-second Conference on Neural Information Processing Systems (NeurIPS).
2018 December	Speaker-Follower Models for Vision-and-Language Navigation Volkan Cirik*, Daniel Fried*, Ronghang Hu*, Anna Rohrbach, Jacob Andreas, Louis-Philippe Morency, Taylor Berg-Kirkpatrick, Kate Saenko, Dan Klein**, and Trevor Darrell**. The Thirty-second Conference on Neural Information Processing Systems (NeurIPS).
2018 November	Modeling Online Discourse with Coupled Distributed Topics Nikita Srivatsan, Zachary Wojtowicz, and Taylor Berg-Kirkpatrick. The 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP).
2018 November	Learning to Describe Differences Between Pairs of Similar Images Harsh Jhamtani and Taylor Berg-Kirkpatrick. The 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP).
2018 November	Unsupervised Learning of Syntactic Structure with Invertible Neural Projections Junxian He, Graham Neubig, and Taylor Berg-Kirkpatrick. The 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP).
2018 June	Learning to Generate Move-by-Move Commentary for Chess Games from Large-Scale Social Forum Data Harsh Jhamtani*, Varun Gangal*, Eduard Hovy, Graham Neubig, and Taylor Berg-Kirkpatrick. The 56th Annual Meeting of the Association for Computational Linguistics (ACL).
2018 June	Visual Referring Expression Recognition: What Do Our Systems Actually Learn? Volkan Cirik, Louis-Philippe Morency, and Taylor Berg-Kirkpatrick. The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL).
2018 February	A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models Kartik Goyal, Graham Neubig, Chris Dyer, and Taylor Berg-Kirkpatrick. The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI).
2018 February	Using Syntax to Ground Referring Expressions in Natural Images Volkan Cirik, Taylor Berg-Kirkpatrick, and Louis-Phillipe Morency. The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI).
2018 February	SPINE - Sparse Interpretable Neural Embeddings Harsh Jhamtani*, Danish Pruthi*, Anant Subramanian*, Taylor Berg-Kirkpatrick, and Eduard Hovy. The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI).
2017 August	Improved Variational Autoencoders for Text Modeling using Dilated Convolutions Zichao Yang, Zhiting Hu, Ruslan Salakhutdinov, and Taylor Berg-Kirkpatrick. The Thirty-Fourth International Conference on Machine Learning (ICML).
2017 August	Efficient Correlated Topic Modeling with Topic Embedding Junxian He*, Zhiting Hu*, Taylor Berg-Kirkpatrick, Ying Huang, and Eric P. Xing. The 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD).
2017 July	Automatic Compositor Attribution in the First Folio of Shakespeare Maria Ryskina, Hannah Alpert-Abrams, Dan Garrette, and Taylor Berg-Kirkpatrick. The 55th annual meeting of the Association for Computational Linguistics (ACL).
2017 July	Differentiable Scheduled Sampling for Credit Assignment Kartik Goyal, Chris Dyer, and Taylor Berg-Kirkpatrick. The 55th Annual Meeting of the Association for Computational Linguistics (ACL).
2016 August	Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints Greg Durrett, Taylor Berg-Kirkpatrick, and Dan Klein. The 54th Annual Meeting of the Association for Computational Linguistics (ACL).
2016 January	Using Accelerometers to Remotely and Automatically Characterize Behavior in Small Animals Talisin T. Hammond, Dwight Springthorpe, Rachel E. Walsh, and Taylor Berg-Kirkpatrick. Journal of Experimental Biology.