Publications

2025

Sewoong Lee, Adam Davies, Marc E Canby, Julia Hockenmaier. (2025) Evaluating and Designing Sparse Autoencoders by Approximating Quasi-Orthogonality. arXiv preprint arXiv:2503.24277
Seungone Kim, Ian Wu, Jinu Lee, Xiang Yue, Seongyun Lee, Mingyeong Moon, Kiril Gashteovski, Carolin Lawrence, Julia Hockenmaier, Graham Neubig, Sean Welleck. (2025) Scaling Evaluation-time Compute with Reasoning Models as Process Evaluators. arXiv preprint arXiv:2503.19877
Jerry Huang, Siddarth Madala, Risham Sidhu, Cheng Niu, Julia Hockenmaier, Tong Zhang. (2025) RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning. arXiv preprint arXiv:2503.12759
Jinu Lee, Qi Liu, Runzhi Ma, Vincent Han, Ziqi Wang, Heng Ji, Julia Hockenmaier. (2025) Entailment-Preserving First-order Logic Representations in Natural Language Entailment. arXiv preprint arXiv:2502.16757
Jinu Lee, Julia Hockenmaier. (2025) Evaluating step-by-step reasoning traces: A survey. arXiv preprint arXiv:2502.12289
Prashant Jayannavar, Liliang Ren, Marisa Hudspeth, Charlotte Lambert, Ariel Cordes, Elizabeth Kaplan, Anjali Narayan-Chen, Julia Hockenmaier. (2025) BAP v2: An Enhanced Task Framework for Instruction Following in Minecraft Dialogues. arXiv preprint arXiv:2501.10836

2024

Ikhyun Cho, Gaeul Kwon, Julia Hockenmaier. (2024) Tutor-ICL: Guiding Large Language Models for Improved In-Context Learning Performance.
Marc Canby, Adam Davies, Chirag Rastogi, Julia Hockenmaier. (2024) Measuring the reliability of causal probing methods: Tradeoffs, limitations, and the plight of nullifying interventions. arXiv preprint arXiv:2408.15510
Rajarshi Haldar, Julia Hockenmaier. (2024) Analyzing the performance of large language models on code summarization. arXiv preprint arXiv:2404.08018
Ikhyun Cho, Changyeon Park, Julia Hockenmaier. (2024) ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers. arXiv preprint arXiv:2403.09681
Yoonhwa Jung, Ikhyun Cho, Shun-Hsiang Hsu, Julia Hockenmaier. (2024) Attack and reset for unlearning: Exploiting adversarial noise toward machine unlearning through parameter re-initialization. arXiv preprint arXiv:2401.08998
Yoonhwa Jung, Julia Hockenmaier, Mani Golparvar-Fard. (2024) Transformer language model for mapping construction schedule activities to uniformat categories. Automation in Construction

2023

Ikhyun Cho, Yoonhwa Jung, Julia Hockenmaier. (2023) SIR-ABSC: Incorporating Syntax into RoBERTa-based Sentiment Analysis Models with a Special Aggregator Token.
Marc E Canby, Julia Hockenmaier. (2023) A Framework for Bidirectional Decoding: Case Study in Morphological Inflection. arXiv preprint arXiv:2305.12580
Julia Constanze Hockenmaier. (2023) Graph-based event schema induction for information retrieval.
Rajarshi Haldar, Yu Deng, Lingfei Wu, Ruchi Mahindru, Julia Constanze Hockenmaier, Sinem Guven Kaya. (2023) Graph-based event schema induction for information retrieval.
Yoonhwa Jung, Julia Hockenmaier, Mani Golparvar-Fard. (2023) Feasibility analysis on the use of nlp-based schedule analytics for 4d project planning and controls.
Neeloy Chakraborty, Risham Sidhu, Blerim Abdullai, Haomiao Chen, Nikil Ravi, Abhinav Ankur, Devika Prasad, Julia Hockenmaier, Team Kingfisher. (2023) Beast: Building an embodied action-prediction system with trajectory data.

2022

Qingyun Wang, Manling Li, Hou Pong Chan, Lifu Huang, Julia Hockenmaier, Girish Chowdhary, Heng Ji. (2022) Multimedia generative script learning for task planning. arXiv preprint arXiv:2208.12306
Harsha Kokel, Mayukh Das, Rakibul Islam, Julia Bonn, Jon Cai, Soham Dan, Anjali Narayan-Chen, Prashant Jayannavar, Janardhan Rao Doppa, Julia Hockenmaier, Sriraam Natarajan, Martha Palmer, Dan Roth. (2022) Human-guided collaborative problem solving: A natural language based framework. arXiv preprint arXiv:2207.09566
Fouad Amer, Julia Hockenmaier, Mani Golparvar-Fard. (2022) Learning and critiquing pairwise activity relationships for schedule quality control via deep learning-based natural language processing. Automation in Construction

2021

Jinjun Xiong, Rajarshi Haldar, Julia Constanze Hockenmaier, Lingfei Wu. (2021) Multi-perspective, multi-task neural network model for matching text to program code.
Lingfei Wu, JinJun Xiong, Julia Constanze Hockenmaier, Rajarshi Haldar. (2021) Multi-perspective, multi-task neural network model for matching text to program code.
Liliang Ren, Chenkai Sun, Heng Ji, Julia Hockenmaier. (2021) HySPA: Hybrid span generation for scalable text-to-graph extraction. arXiv preprint arXiv:2106.15838

2020

Marc Canby, Aidana Karipbayeva, Bryan Lunt, Sahand Mozaffari, Charlotte Yoder, Julia Hockenmaier. (2020) University of Illinois submission to the SIGMORPHON 2020 shared task 0: Typologically diverse morphological inflection.
Prashant Jayannavar, Anjali Narayan-Chen, Julia Hockenmaier. (2020) Learning to execute instructions in a Minecraft dialogue.
Rajarshi Haldar, Lingfei Wu, Jinjun Xiong, Julia Hockenmaier. (2020) A multi-perspective architecture for semantic code search. arXiv preprint arXiv:2005.06980

2019

Jiacheng Liu, Julia Hockenmaier. (2019) Phrase Grounding by Soft-Label Chain Conditional Random Field.
Anjali Narayan-Chen, Prashant Jayannavar, Julia Hockenmaier. (2019) Collaborative dialogue in Minecraft.
Charlotte Lambert, Ariel Cordes, Elli Kaplan, Prashant Jayannavar, Julia Hockenmaier. (2019) Virtual world context encoding for grounded dialogue in minecraft.

2018

David Chiang, Julia Hockenmaier, Jun'ichi Tsujii. (2018) Preface by the program committee co-chairs. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii. (2018) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.

2017

Alice Lai, Yonatan Bisk, Julia Hockenmaier. (2017) Natural language inference from multiple premises.
Anjali Narayan-Chen, Colin Graber, Mayukh Das, Md Rakibul Islam, Soham Dan, Sriraam Natarajan, Janardhan Rao Doppa, Julia Hockenmaier, Martha Palmer, Dan Roth. (2017) Towards problem solving agents that communicate and learn.
Alice Lai, Julia Hockenmaier. (2017) Learning to predict denotational probabilities for modeling entailment.
Bryan A Plummer, Arun Mallya, Christopher M Cervantes, Julia Hockenmaier, Svetlana Lazebnik. (2017) Phrase localization and visual relationship detection with comprehensive image-language cues.

2016

Yonatan Bisk, Siva Reddy, John Blitzer, Julia Hockenmaier, Mark Steedman. (2016) Evaluating induced CCG parsers on grounded semantic parsing. arXiv preprint arXiv:1609.09405
Micah Hodosh, Julia Hockenmaier. (2016) Focused evaluation for image description with binary forced-choice tasks.

2015

Yonatan Bisk, Julia Hockenmaier. (2015) Probing the linguistic strengths and limitations of unsupervised grammar induction.
Yonatan Bisk, Christos Christodoulopoulos, Julia Hockenmaier. (2015) Labeled grammar induction with minimal supervision.
Bryan A Plummer, Liwei Wang, Chris M Cervantes, Juan C Caicedo, Julia Hockenmaier, Svetlana Lazebnik. (2015) Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models.

2014

Alice Lai, Julia Hockenmaier. (2014) Illinois-lh: A denotational and distributional approach to semantics.
Peter Young, Alice Lai, Micah Hodosh, Julia Hockenmaier. (2014) From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics (TACL)
Yunchao Gong, Liwei Wang, Micah Hodosh, Julia Hockenmaier, Svetlana Lazebnik. (2014) Improving image-sentence embeddings using large weakly annotated photo collections.

2013

Sean Massung, ChengXiang Zhai, Julia Hockenmaier. (2013) Structural parse tree features for text representation.
Micah Hodosh, Peter Young, Julia Hockenmaier. (2013) Framing image description as a ranking task: Data, models and evaluation metrics. Journal of Artificial Intelligence Research
Julia Hockenmaier, Sebastian Riedel. (2013) Proceedings of the Seventeenth Conference on Computational Natural Language Learning.
Julia Hockenmaier, Tamara Berg. (2013) Proceedings of the Workshop on Vision and Natural Language Processing.
Annie Louis, Richard Socher, Julia Hockenmaier, Eric Ringger. (2013) Proceedings of the 2013 NAACL HLT Student Research Workshop.
Yonatan Bisk, Julia Hockenmaier. (2013) An HDP Model for Inducing Combinatory Categorial Grammars. Transactions of the Association for Computational Linguistics (TACL)
Micah Hodosh, Julia Hockenmaier. (2013) Sentence-based image description with scalable, explicit models.

2012

Hyungsul Kim, Yizhou Sun, Julia Hockenmaier, Jiawei Han. (2012) Etm: Entity topic models for mining documents associated with entities.
Matt Garley, Julia Hockenmaier. (2012) Beefmoves: dissemination, diversity, and dynamics of English borrowings in a German hip hop forum.
Mark Steedman, James Curran, Julia Hockenmaier, Tom Kwiatkowski, Mike Lewis, Jong Park, Emily Thomforde, Prachya Boonkwan, Greg Copolla, Sharon Goldwater. (2012) Combinatory Categorial Grammars for Robust Natural Language Processing. University of Edinburgh
Yonatan Bisk, Julia Hockenmaier. (2012) Induction of linguistic structure with combinatory categorial grammars.
Yonatan Bisk, Julia Hockenmaier. (2012) Simple robust grammar induction with combinatory categorial grammars. Proceedings of the AAAI Conference on Artificial Intelligence

2011

Julia Hockenmaier. (2011) Lecture 6: Topic Models (Latent Dirichlet Allocation). Published online at cs. illinois. edu/class/sp10/cs598jhm/.../Lecture06HO. pdf. Last visited November
Hannaneh Hajishirzi, Julia Hockenmaier, Erik T Mueller, Eyal Amir. (2011) Reasoning about robocup soccer narratives.

2010

Julia Hockenmaier, Yonatan Bisk. (2010) Normal-form parsing for Combinatory Categorial Grammars with generalized composition and type-raising.
Parikshit Sondhi, Manish Gupta, ChengXiang Zhai, Julia Hockenmaier. (2010) Shallow information extraction from medical forum data.
Yuancheng Tu, Nikhil Johri, Dan Roth, Julia Hockenmaier. (2010) Citation author topic model in expert search.
Micah Hodosh Peter Young Cyrus Rashtchian, Julia Hockenmaier. (2010) Cross-caption coreference resolution for automatic image understanding. CoNLL-2010
Julia Hockenmaier, Yusuke Miyao, Josef van Genabith. (2010) Wide-coverage NLP with Linguistically Expressive Grammars.
Micah Hodosh, Peter Young, Cyrus Rashtchian, Julia Hockenmaier. (2010) Cross-caption coreference resolution for automatic image understanding.
Julia Hockenmaier, Diane Litman, Adriane Boyd, Mahesh Joshi, Frank Rudzicz. (2010) Proceedings of the NAACL HLT 2010 Student Research Workshop.
Cyrus Rashtchian, Peter Young, Micah Hodosh, Julia Hockenmaier. (2010) Collecting image annotations using amazon’s mechanical turk.
Julia Hockenmaier. (2010) The future role of language resources for natural language parsing (We won't be able to rely on Pierre Vinken forever... or will we have to?).
Ali Farhadi, Mohsen Hejrati, Mohammad Amin Sadeghi, Peter Young, Cyrus Rashtchian, Julia Hockenmaier, David Forsyth. (2010) Every picture tells a story: Generating sentences from images.

2009

David A Forsyth, Tamana Berg, Cecilia Ovesdotter Alm, Ali Farhadi, Julia Hockenmaier, Nicolas Loeff, Gang Wang. (2009) Words and pictures: Categories, modifiers, depiction, and iconography. Object categorization: Computer and human vision perspectives

2008

Johan Bos, Ted Briscoe, Aoife Cahill, John A Carroll, Stephen Clark, Ann Copestake, Dan Flickinger, Josef van Genabith, Julia Hockenmaier, Aravind Joshi, Ronald M Kaplan, Tracy Holloway King, Sandra Kuebler, Dekang Lin, Jan Tore Loenning, Christopher D Manning, Yusuke Miyao, Joakim Nivre, Stephan Oepen, Kenji Sagae, Nianwen Xue, Yi Zhang. (2008) Coling 2008: Proceedings of the workshop on cross-framework and cross-domain parser evaluation.
Julia Hockenmaier, Peter Young. (2008) Non-local scrambling: The equivalence of TAG and CCG revisited.

2007

Julia Hockenmaier, Mark Steedman. (2007) CCGbank: a corpus of CCG derivations and dependency structures extracted from the Penn Treebank. Computational Linguistics
Ken A Dill, Adam Lucas, Julia Hockenmaier, Liang Huang, David Chiang, Aravind K Joshi. (2007) Computational linguistics: a new tool for exploring biopolymer structures and statistical mechanics.
Timothy Baldwin, Mark Dras, Julia Hockenmaier, Tracy Holloway King, Gertjan van Noord. (2007) ACL 2007 Workshop on Deep Linguistic Processing.
Timothy Baldwin, Mark Dras, Julia Hockenmaier, Tracy Holloway King, Gertjan van Noord. (2007) The impact of deep linguistic processing on parsing technology.
David Reitter, Frank Keller, Julia Hockenmaier. (2007) Corpus-based evidence against sequence priming. Poster at 20th Annual CUNY Conference on Human Sentence Processing
Julia Hockenmaier, Aravind K Joshi, Ken A Dill. (2007) Routes are trees: the parsing perspective on protein folding. Proteins: Structure, Function, and Bioinformatics

2006

Julia Hockenmaier, Aravind Joshi, Ken A Dill. (2006) Protein folding and chart parsing.
David Reitter, Julia Hockenmaier, Frank Keller. (2006) Priming effects in combinatory categorial grammar.
Julia Hockenmaier. (2006) Creating a CCGbank and a wide-coverage CCG lexicon for German.

2005

Julia Hockenmaier, Aravind Joshi, Ken Dill. (2005) Routes are trees: The parsing view on protein folding. 13th Annual Conference on Intelligent Systems for Molecular Biology (ISMB 2005) Poster A-36
Julia Hockenmaier, Mark Steedman. (2005) Ccgbank: User’s manual. University of Pennsylvania, Philadelphia
Julia Hockenmaier, Mark Steedman. (2005) CCGbank. Linguistic Data Consortium, Philadelphia. LDC2005T13
Mark Steedman, Jason Baldridge, Cem Bozsahin, Stephen Clark, James Curran, Julia Hockenmaier. (2005) Grammar acquisition by child and machine. Invited Talk at the 17th European Summer School of Language, Logic and Information, Edinburgh

2004

Julia Hockenmaier, Gann Bierner, Jason Baldridger. (2004) Extending the coverage of a CCG system. Research on Language and Computation
Johan Bos, Stephen Clark, Mark Steedman, James R Curran, Julia Hockenmaier. (2004) Wide-coverage semantic representations from a CCG parser.

2003

Julia Hockenmaier. (2003) Parsing with generative models of predicate-argument structure.
Mark Steedman, Steven Baker, Jeremiah Crim, Stephen Clark, Julia Hockenmaier, Rebecca Hwa, Miles Osborne, Paul Ruhlen, Anoop Sarkar. (2003) CLSP WS-02 final report: Semi-supervised training for statistical parsing.
Mark Steedman, Steven Baker, Jeremiah Crim, Stephen Clark, Julia Hockenmaier, Rebecca Hwa, Miles Osborne, Paul Ruhlen, Anoop Sarkar. (2003) Semi-supervised training for statistical parsing.
Mark Steedman, Rebecca Hwa, Stephen Clark, Miles Osborne, Anoop Sarkar, Julia Hockenmaier, Paul Ruhlen, Steven Baker, Jeremiah Crim. (2003) Example selection for bootstrapping statistical parsers.
Mark Steedman, Miles Osborne, Anoop Sarkar, Stephen Clark, Rebecca Hwa, Julia Hockenmaier, Paul Ruhlen, Steven Baker, Jeremiah Crim. (2003) Bootstrapping statistical parsers from small datasets.
Daniel Gildea, Julia Hockenmaier. (2003) Identifying semantic roles using combinatory categorial grammar.
Julia Hockenmaier. (2003) Data and models for statistical parsing with Combinatory Categorial Grammar.

2002

Stephen Clark, Julia Hockenmaier, Mark Steedman. (2002) Building deep dependency structures using a wide-coverage CCG parser.
Julia Hockenmaier, Mark Steedman. (2002) Generative models for statistical parsing with Combinatory Categorial Grammar.
Julia Hockenmaier, Mark Steedman. (2002) Acquiring Compact Lexicalized Grammars from a Cleaner Treebank.. LREC
Mark Steedman, Stephen Clark, Julia Hockenmaier. (2002) Parsing with CCG.
Stephen Clark, Julia Hockenmaier. (2002) Evaluating a wide-coverage CCG parser. Proceedings of the LREC 2002 beyond PARSEVAL workshop

2001

Julia Hockenmaier. (2001) Statistical parsing for CCG with simple generative models.

2000

Julia Hockenmaier, Gann Bierner, Jason Baldridge. (2000) Providing robustness for a CCG system. Proceedings of ESSLLI’2000 Workshop on Linguistic Theory and Grammar Implementation

1998

Julia Hockenmaier, Chris Brew. (1998) Error-driven learning of Chinese word segmentation.