2009

• D. Roth and Y. Tu, Aspect Guided Text Categorization with Unobserved Labels. Proceedings of ICDM  (2009)  [bibitem]
  • multiclass classification; Text classification, short text snippet, structure learning, Constrained optimization; constrained conditional models
• D. Roth and R. Samdani, Learning Multi-Linear Representations. Machine Learning  (2009) pp. 195--209 [bibitem]
• J. Pasternack and D. Roth, Learning Better Transliterations. The 18th ACM Conference on Information and Knowledge Management (CIKM)  (2009)  [bibitem]
  • State-of-the-art transliteration with unbounded substring-to-substring productions and capable of both discovery and generation.
• D. Roth, M. Sammons, and V. Vydiswaran, A Framework for Entailed Relation Recognition. Proc. of the Annual Meeting of the ACL  (2009)  [bibitem]
  • semantic retrieval, scalable textual entailment, structured query, similarity metrics, exhaustive search, relation recognition, relation extraction
• J. Eisenstein, J. Clarke, D. Goldwasser, and D. Roth, Reading to Learn: Constructing Features from Semantic Abstracts. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-2009)  (2009) pp. xx--yy [bibitem]
  • Proposes a novel form of semantic analysis where the goal is to obtain a high-level semantic abstract of documents in a representation that facilitates learning. The abstract is obtained through a generative model that requires no labeled data. The semantic abstract is converted into a transformed feature space for relational learning.
• A. Klementiev, D. Roth, K. Small, and I. Titov, Unsupervised Rank Aggregation with Domain-Specific Expertise. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)  (2009)  [bibitem]
  • Proposes a framework for learning to aggregate votes of rankers with domain specific expertise without supervision. Applies the learning framework to the settings of aggregating full rankings and aggregating top-k lists, demonstrating significant improvements over a domain-agnostic baseline in both cases.
• M. Connor, Y. Gertner, C. Fisher, and D. Roth, Minimally Supervised Model of Early Language Acquisition. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2009)  [bibitem]
  • Minimal supervision; language acquisition; BabySRL; a semantic role labeling system with simple, psycholinguistically plausible features; trained using background knowledge plus linguistic constraints
• D. Roth and K. Small, Interactive Feature Space Construction using Semantic Information. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2009)  [bibitem]
• L. Ratinov and D. Roth, Design Challenges and Misconceptions in Named Entity Recognition. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2009)  [bibitem]
  • Named entity recognition; information extraction; knowledge resources; word class models; gazetteers; non-local features; global features; inference methods; BIO vs. BIOLU; text chunk representation
• M. Chang, D. Goldwasser, D. Roth, and Y. Tu, Unsupervised Constraint Driven Learning For Transliteration Discovery. NAACL  (2009)  [bibitem]
  • Transliteration; Constrained optimization; constrained conditional models, unsupervised learning; named entity discovery; multilingual corpora; bootstrapping, romanization table, feature selection for transliteration; Discriminative training of Objective function; Dynamic Programming
• J. Pasternack and D. Roth, Extracting Article Text from the Web with Maximum Subsequence Segmentation. The International World Wide Web Conference  (2009)  [bibitem]
  • A new global optimization technique, maximum subsequence, is used to accurately identify and extract article text from HTML documents in linear time
• D. Roth, K. Small, and I. Titov, Sequential Learning of Classifiers for Structured Prediction Problems. Proc. of the 12th International Conference on Artificial Intelligence and Statistics (AISTATS)  (2009) pp. 440--447 [bibitem]
  • Structured prediction; Learning algorithm; Pipelines; An alternative both to joint and to independent learning of classifiers
• S. Riedel and J. Clarke, Revisiting Optimal Decoding for Machine Translation IBM Model~4. Proceedings of the NAACL HLT 2009 Short Papers  (2009)  [bibitem]
• D. Goldwasser, M. Chang, Y. Tu, and D. Roth, Constraint Driven Transliteration Discovery. Recent Advances in Natural Language Processing  (2009) pp. xx--yy [bibitem]
  • Extending Constrained Conditional Model based transliteration; Combines EMNLP'08 and NAACL'09

2008

• A. Klementiev and D. Roth, Named Entity Transliteration and Discovery in Multilingual Corpora. Learning Machine Translation  (2008)  [bibitem]
• D. Goldwasser and D. Roth, Transliteration as Constrained Optimization. EMNLP  (2008) pp. xx--yy [bibitem]
  • Transliteration; Constrained optimization; Named entity discovery; bilingual corpora; feature selection for transliteration; Discriminative training of Objective function; Integer Linear Programming;ILP; Hebrew transliteration
• E. Bengtson and D. Roth, Understanding the Value of Features for Coreference Resolution. EMNLP  (2008) pp. xx--yy [bibitem]
  • The importance of good features for coreference resolution
• A. Klementiev, D. Roth, and K. Small, A Framework for Unsupervised Rank Aggregation. Proc. of the SIGIR Workshop on Learning to Rank for Information Retrieval  (2008) pp. 32-39 [bibitem]
• M. Chang, L. Ratinov, and D. Roth, Constraints as Prior Knowledge. ICML Workshop on Prior Knowledge for Text and Language Processing  (2008) pp. 32-39 [bibitem]
• D. Roth and M. Sammons, A Unified Representation and Inference Paradigm for Natural Language Processing.  (2008)  [bibitem]
• M. Connor, Y. Gertner, C. Fisher, and D. Roth, Baby SRL: Modeling Early Language Acquisition. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2008) pp. xx--yy [bibitem]
  • Evaluating the psycholinguistics structure-mapping assumption; a semantic role labeling system with simple, psycholinguistically plausible features; language acquisition
• V. Punyakanok, D. Roth, and W. Yih, The Importance of Syntactic Parsing and Inference in Semantic Role Labeling. Computational Linguistics  (2008)  [bibitem]
• E. Daya, D. Roth, and S. Wintner, Learning Hebrew Roots: Machine Learning with Linguistic Constraints. Computational Linguistics  (2008)  [bibitem]
• V. Srikumar, R. Reichart, M. Sammons, A. Rappoport, and D. Roth, Extraction of Entailed Semantic Relations Through Syntax-based Comma Resolution. Proc. of the Annual Meeting of the ACL  (2008)  [bibitem]
• D. Goldwasser and D. Roth, Active Sample Selection for Named Entity Transliteration. Proceedings of ACL-08: HLT, Short Papers  (2008)  [bibitem]
  • Named entity discovery; bilingual corpora; active sampling; data selection; domain adaptation; Russian transliteration; Hebrew transliteration
• B. Liebald, D. Roth, N. Shah, and V. Srikumar, Proactive Intrusion Detection. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (2008)  [bibitem]
• M. Chang, L. Ratinov, D. Roth, and V. Srikumar, Importance of Semantic Represenation: Dataless Classification. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (2008)  [bibitem]
• D. Roth and K. Small, Active Learning for Pipeline Models. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (2008)  [bibitem]
• M. Chang, L. Ratinov, N. Rizzolo, and D. Roth, Learning and Inference with Constraints. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (2008)  [bibitem]
• A. Klementiev, D. Roth, and K. Small, Unsupervised Rank Aggregation with Distance-Based Models. Proc. of the International Conference on Machine Learning (ICML)  (2008)  [bibitem]
  • We propose a mathematical and algorithmic framework for learning to aggregate (partial) rankings without supervision. We instantiate the framework for the cases of combining permutations and combining top-k lists, and propose a novel metric for the latter.
• M. Rahurkar, D. Roth, and T. Huang, Which Apple are you talking about. Proceedings of WWW  (2008) pp. 1197-1198 [bibitem]
• R. de Salvo Braz, E. Amir, and D. Roth, A Survey of First-Order Probabilistic Models. Innovations in Bayesian Networks  (2008) pp. 289--317 [bibitem]
  • Lifted Probabilistic Inference

2007

• D. Roth and M. Sammons, Semantic and Logical Inference Model for Textual Entailment. Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing  (2007) pp. 107--112 [bibitem]
  • Textual Entailment; Compositional semantics; Search-based inference; Modular framework
• M. Chang, L. Ratinov, and D. Roth, Guiding Semi-Supervision with Constraint-Driven Learning. Proc. of the Annual Meeting of the ACL  (2007) pp. 280--287 [bibitem]
  • Semi-supervised learning with very little supervision; Constraints; Constraints Driven Learning; Information Extraction
• N. Rizzolo and D. Roth, Modeling Discriminative Global Inference. Proceedings of the First International Conference on Semantic Computing (ICSC)  (2007) pp. 597-604 [bibitem]
  • Learning Based Java: a Modeling language that facilitates developing of systems with learning and inference componenets.
• M. Connor and D. Roth, Context Sensitive Paraphrasing with a Single Unsupervised Classifier. Proc. of the European Conference on Machine Learning (ECML)  (2007)  [bibitem]
  • Trains a single classifier to decided context sensitive paraphrases of verbs. Bootstraps training set through unsupervised training of subtask classifiers and confident example selection.
• A. Klementiev, D. Roth, and K. Small, An Unsupervised Learning Algorithm for Rank Aggregation. Proc. of the European Conference on Machine Learning (ECML)  (2007)  [bibitem]
• D. Roth and W. Yih, Global Inference for Entity and Relation Identification via a Linear Programming Formulation. Introduction to Statistical Relational Learning  (2007)  [bibitem]
  • Learning and Inference with Constraints; Integer Linear Programming for Information extraction; Simultaneous recognition of entities and Relations
• R. de Salvo Braz, E. Amir, and D. Roth, Lifted First-Order Probabilistic Inference. Introduction to Statistical Relational Learning  (2007)  [bibitem]
  • Relational Inference; Probabilistic Relational (first order) Models; First-order probabilistic inference without propositionalization; Lifted Probabilistic Inference
• S. Har-Peled, D. Roth, and D. Zimak, Maximum Margin Coresets for Active and Noise Tolerant Learning. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)  (2007) pp. LT [bibitem]
  • Learning large margin halfspaces using coresets; algorithm and analysis; applications include analysis of large margin active learning and an algorithm for agnostic learning in the presence of outlier noise.
• Z. Zeng, J. Tu, M. Liu, T. Huang, B. Pianfetti, D. Roth, and S. Levinson, Audio-Visual Affect Recognition. IEEE Transactions on Multimedia  (2007) pp. 424-428 [bibitem]

2006

• M. Chang, Q. Do, and D. Roth, Multilingual Dependency Parsing: A Pipeline Approach. Recent Advances in Natural Language Processing  (2006) pp. 55--78 [bibitem]
  • Analysis of A pipeline model with applications to dependency parsing. Combines ACL'06 and CoNLL'06
• D. Roth and K. Small, Margin-based Active Learning for Structured Output Spaces. Proc. of the European Conference on Machine Learning (ECML)  (2006)  [bibitem]
  • Active Learning; Structured Output
• R. de Salvo Braz, E. Amir, and D. Roth, MPE and Partial Inversion in Lifted Probabilistic Variable Elimination. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (2006)  [bibitem]
  • Relational Inference; Probabilistic Relational (first order) Models; First-order probabilistic inference without propositionalization; Lifted Probabilistic Inference
• A. Klementiev and D. Roth, Weakly Supervised Named Entity Transliteration and Discovery from Multilingual Comparable Corpora. Proc. of the Annual Meeting of the ACL  (2006) pp. USS,TL,ADAPT [bibitem]
  • Multilingual named entities; multilingual search; multilingual named entities discovery and recognition; discriminatory transliteration model; Fourier Transform for temporal sequence similarity
• M. Chang, Q. Do, and D. Roth, Local Search for Bottom-Up Dependency Parsing. Proc. of the Annual Meeting of the ACL  (2006)  [bibitem]
  • Analysis of A pipeline model with applications to dependency parsing
• M. Chang, Q. Do, and D. Roth, A Pipeline Model for Bottom-Up Dependency Parsing Shared Task Paper. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2006) pp. 186--190 [bibitem]
  • Multilingual Dependency Parsing; a shift reduced parsing model; study of shift reduced parsing as a pipeline model
• R. de Salvo Braz, E. Amir, and D. Roth, MPE and Partial Inversion in Lifted Probabilistic Variable Elimination. ICML Workshop on Open Problems in Statistical Relational Learning  (2006)  [bibitem]
  • Earlier Version of a AAAI'06 paper.
• D. Roth and K. Small, Active Learning with Perceptron for Structured Output. ICML-06 Workshop on Learning in Structured Output Spaces  (2006)  [bibitem]
  • Earlier Version of an ECML'06 paper
• A. Klementiev and D. Roth, Named Entity Transliteration and Discovery from Multilingual Comparable Corpora. Proc. of the Annual Meeting of the North American Association of Computational Linguistics (NAACL)  (2006) pp. 82--88 [bibitem]
  • Multilingual named entities; multilingual search; multilingual named entities discovery and recognition; discriminatory transliteration model; Fourier Transform for temporal sequence similarity
• R. de Salvo Braz, R. Girju, V. Punyakanok, D. Roth, and M. Sammons, An Inference Model for Semantic Entailment in Natural Language. Machine Learning Challenges, Evaluating Predictive Uncertainty, Visual Object Classification and Recognizing Textual Entailment, First PASCAL Machine Learning Challenges Workshop, Revised Selected Papers  (2006) pp. 261--286 [bibitem]
  • Revised version of PASCAL RTE Challenge. Textual Entailment, integrating NLP text analyis, shallow semantic inference
• O. Mengshoel, D. Roth, and D. Wilkins, Controlled generation of hard and easy Bayesian networks: Impact on maximal clique size in tree clustering. Artificial Intelligence  (2006)  [bibitem]

2005

• D. Roth and W. Yih, Integer Linear Programming Inference for Conditional Random Fields. Proc. of the International Conference on Machine Learning (ICML)  (2005) pp. 737--744 [bibitem]
  • Extending Conditional Random Fields with expressive, non-sequential, constraints. Comparing multiple joint inference training paradigms for structure learning in the context of SRL.
• V. Punyakanok, D. Roth, and W. Yih, The Necessity of Syntactic Parsing for Semantic Role Labeling. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)  (2005) pp. 1117--1123 (abstract) [bibitem]
  • An Analysis of the impact of syntactic parsing on semantic role labeling. Joint inference is used both to guarantee coherent SRL output and to combine several SRL systems.
• V. Punyakanok, D. Roth, W. Yih, and D. Zimak, Learning and Inference over Constrained Output. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)  (2005) pp. 1124--1129 [bibitem]
  • Structure Learning; Joint Inference; Learning + Inference vs. Inference based Training Algorithms
• R. de Salvo Braz, E. Amir, and D. Roth, Lifted First-order Probabilistic Inference. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)  (2005) pp. 1319--1125 (abstract) [bibitem]
  • Relational Inference; Probabilistic Relational (first order) Models; First-order probabilistic inference without propositionalization
• R. Braz, R. Girju, V. Punyakanok, D. Roth, and M. Sammons, An Inference Model for Semantic Entailment in Natural Language. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (2005) pp. 1678--1679 [bibitem]
  • Textual Entailment; Mapping sentences to a description logic based representation, Pascal Entailment Task
• R. Braz, R. Girju, V. Punyakanok, D. Roth, and M. Sammons, Knowledge Representation for Semantic Entailment and Question-Answering. IJCAI-05 Workshop on Knowledge and Reasoning for Question Answering  (2005)  [bibitem]
  • Analysis of our Textual Entailment system
• R. de Salvo Braz, R. Girju, V. Punyakanok, D. Roth, and M. Sammons, An Inference Model for Semantic Entailment in Natural Language. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)  (2005)  [bibitem]
  • Poster Presentation
  • Textual Entailment; Mapping sentences to a description logic based representation
• C. Alm, D. Roth, and R. Sproat, Emotions from text: machine learning for text-based emotion prediction.. Proceedings of HLT/EMNLP 2005  (2005)  [bibitem]
• S. Agarwal and D. Roth, Learnability of Bipartite Ranking Functions. Proc. of the Annual ACM Workshop on Computational Learning Theory (COLT)  (2005) pp. 16--31 (abstract) [bibitem]
• S. Agarwal, S. Har-Peled, and D. Roth, A Uniform Convergence Bound for the Area Under the ROC Curve. Artificial IntelligenceSTAT  (2005) pp. 1-8 (abstract) [bibitem]
  • Bipartite Ranking: uniform convergence properties of the AUC in terms of bipartite rank-shatter coefficients.
• S. Agarwal, T. Graepel, R. Herbrich, and D. Roth, A Large Deviation Bound for the Area Under the ROC Curve. The Conference on Advances in Neural Information Processing Systems (NIPS)  (2005) pp. 9--16 (abstract) [bibitem]
  • Bipartite Ranking: bounding the expected accuracy of a ranking function in terms of its empirical AUC.
• S. Agarwal, T. Graepel, R. Herbrich, S. Har-Peled, and D. Roth, Generalization Bounds for the Area Under the ROC Curve. Journal of Machine Learning Research  (2005) pp. 393--425 (abstract) [bibitem]
• R. Khardon, D. Roth, and R. Servedio, Efficiency versus Convergence of Boolean Kernels for On-Line Learning Algorithms. Journal of Machine Learning Research  (2005) pp. 341-356 [bibitem]
• P. Fung and D. Roth, Guest Editors Introduction: Machine Learning in Speech and Language Technologies. Machine Learning  (2005) pp. 1-6 [bibitem]
• D. Roth, Learning based Programming. Innovations in Machine Learning: Theory and Applications  (2005)  [bibitem]
  • Suggests a paradigm and a programming language for the programming of learning intensive computer systems. Springer: http://dx.doi.org/10.1007/3-540-33486-6_3
• R. Girju, D. Roth, and M. Sammons, Token-level Disambiguation of VerbNet classes. The Interdisciplinary Workshop on Verb Features and Verb Classes  (2005)  [bibitem]
  • Context Sensitive Identification of VerbNet Classes; Levin Classes.
• X. Li, P. Morie, and D. Roth, Semantic Integration in Text: From Ambiguous Names to Identifiable Entities. AI Magazine. Special Issue on Semantic Integration  (2005) pp. 45--68 (abstract) [bibitem]
  • Named Entity Recognition; coreference resolution; entity identification; matching Entities Mentions within and across documents.
• W. Shen, X. Li, and A. Doan, Constraint-Based Entity Matching. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (2005)  [bibitem]
  • Entity Identification, Generative Model, Record Linkage, Constraint, Relaxation Labeling
• X. Li and D. Roth, Discriminative Training of Clustering Functions: Theory and Experiments with Entity Identification. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2005) pp. 64--71 [bibitem]
  • Clustering; metric learning; training metrics; entity identification
• P. Koomen, V. Punyakanok, D. Roth, and W. Yih, Generalized Inference with Multiple Semantic Role Labeling Systems Shared Task Paper. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2005) pp. 181-184 [bibitem]
  • Semantic Parsing; joint inference; integer linear programming; combining SRL systems via joint inference; Top system in CoNLL shared task
• X. Li and D. Roth, Learning Question Classifiers: The Role of Semantic Information. Journal of Natural Language Engineering  (2005)  [bibitem]
  • Question Classification; Hierarchical classifiers; Sequential Model; Expressive Feature generation with semantic information.
• V. Punyakanok and D. Roth, Inference with Classifiers: The Phrase Identification Problem. Computational Linguistics  (2005)  [bibitem]
  • In submission
  • Shallow Parsing; Chunking; HMMs, Conditional Models and Constraint Satisfaction Models. Top results on phrase chunking
• B. Ziebart, A. Dey, R. Campbell, and D. Roth, Learning Automation Policies for Pervasive Computing Environments. ICAC'05, The IEEE International Conference on Autonomic Computing  (2005) pp. 204-215 [bibitem]

2004

• X. Li, P. Morie, and D. Roth, Identification and Tracing of Ambiguous Names: Discriminative and Generative Approaches. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (2004) pp. 419--424 (abstract) [bibitem]
  • Comparing discriminatory and generative models for entity identification; named entity recognition; coreference resolution; matching entities mentions within and across documents; distance metrics for named entities
• X. Li, P. Morie, and D. Roth, Robust Reading: Identification and Tracing of Ambiguous Names. Proc. of the Annual Meeting of the North American Association of Computational Linguistics (NAACL)  (2004) pp. 17--24 (abstract) [bibitem]
  • A generative model for entity identification; Named Entity Recognition; coreference resolution; matching entities mentions within and across documents
• E. Daya, D. Roth, and S. Wintner, Learning Hebrew Roots: Machine Learning with Linguistic Constraints. EMNLP  (2004) pp. 168--178 (abstract) [bibitem]
  • Inference with Classifiers; Learning and Inference with Constraints; Hebrew Morphology
• D. Roth and W. Yih, A Linear Programming Formulation for Global Inference in Natural Language Tasks. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2004) pp. 1--8 (abstract) [bibitem]
  • Simultaneous recognition of Named Entities and Relations between them. Learning and Inference via an Integer Linear Programming framework; Structure Learning; Avoiding Pipeline Processing
• V. Punyakanok, D. Roth, W. Yih, and D. Zimak, Semantic Role Labeling via Integer Linear Programming Inference. Proc. the International Conference on Computational Linguistics (COLING)  (2004) pp. 1346--1352 (abstract) [bibitem]
  • Semantic Parsing; Structure Learning with Expressive Constraints; Constraint Optimization; Integer Linear Programming
• V. Punyakanok, D. Roth, W. Yih, D. Zimak, and Y. Tu, Semantic Role Labeling via Generalized Inference over Classifiers Shared Task Paper. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2004) pp. 130--133 (abstract) [bibitem]
  • Semantic Parsing; Structure Learning with Expressive Constraints; Constraint Optimization; Integer Linear Programming
• Z. Zeng, J. Tu, M. Liu, T. Zhang, N. Rizzolo, Z. Zhang, T. Huang, D. Roth, and S. Levinson, Bimodal HCI-related Affect Recognition. ICMI'04, The 6th International Conference on Multimodal Interfaces  (2004) pp. 137--143 (abstract) [bibitem]
• V. Punyakanok, D. Roth, W. Yih, and D. Zimak, Natural Language Inference via Dependency Tree Mapping: An Application to Question Answering. Computational Linguistics  (2004)  [bibitem]
  • In submission
  • Tree transformations; Answer selection via a mapping of dependency tree representations.
• X. Li, D. Roth, and K. Small, The Role of Semantic Information in Learning Question Classifiers. Proc. of the International Joint Conference on Natural Language Processing (IJCNLP)  (2004)  (abstract) [bibitem]
  • Question Classification; Hierarchical classifiers; Sequential Model; Expressive Feature Generation with semantic information.
• S. Agarwal, A. Awan, and D. Roth, Learning to Detect Objects in Images via a Sparse, Part-Based Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence  (2004) pp. 1475--1490 (abstract) [bibitem]
• W. Yih, P. Chang, and W. Kim, Mining Online Deal Forums for Hot Deals. Web Intelligence  (2004) pp. 384--390 [bibitem]
  • Applying topic and sentiment text classification to online web forums

2003

• S. Har-Peled, D. Roth, and D. Zimak, Constraint Classification for Multiclass Classification and Ranking. The Conference on Advances in Neural Information Processing Systems (NIPS)  (2003) pp. 785--792 [bibitem]
• C. Cumby and D. Roth, On Kernel Methods for Relational Learning. Proc. of the International Conference on Machine Learning (ICML)  (2003) pp. 107--114 (abstract) [bibitem]
  • Parameterized kernels over structures. Relational Kernels. Advantages and disadvantages of graph kernels.
• A. Garg and D. Roth, Margin Distribution and Learning Algorithms. Proc. of the International Conference on Machine Learning (ICML)  (2003) pp. 210--217 (abstract) [bibitem]
  • Linear classifiers that optimize the margin distribution
• X. Li, D. Roth, and Y. Tu, Phrasenet: towards context sensitive lexical semantics. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2003)  (abstract) [bibitem]
  • Extending WordNet to taxonomy over phrases
• C. Cumby and D. Roth, Feature Extraction Languages for Propositionalized Relational Learning. IJCAI Workshop on Learning Statistical Models from Relational Data  (2003)  (abstract) [bibitem]
• S. Agarwal and D. Roth, Minimum Risk Feature Transformations.  (2003)  [bibitem]
  • UIUC Tech Report UIUCDCS-R-2003-2627. A preliminary framework for Feature Generation

2002

• A. Garg, S. Har-Peled, and D. Roth, On generalization bounds, projection profile, and margin distribution. ICML  (2002) pp. 171--178 (abstract) [bibitem]
  • Random Projection; Generalization Bounds for Linear Classifiers.
• C. Cumby and D. Roth, Learning with Feature Description Logics. Proc. of the International Conference Inductive Logic Programming  (2002) pp. 32-47 (abstract) [bibitem]
  • A Description Logic based Formalism for Feature Extraction; Expressive Features; A language for Feature Extraction
• D. Roth and W. Yih, Probabilistic Reasoning for Entity and Relation Recognition. Proc. the International Conference on Computational Linguistics (COLING)  (2002) pp. 835--841 (abstract) [bibitem]
  • Entity And Relation Recognition. Simultaneous Identification of Entities and Relations.
• X. Li and D. Roth, Learning Question Classifiers. Proc. the International Conference on Computational Linguistics (COLING)  (2002) pp. 556--562 (abstract) [bibitem]
  • Classifying Answer Type for Question Answering. Sequential Classification. Multiclass Classification.
• X. Carreras, L. M`arquez, V. Punyakanok, and D. Roth, Learning and Inference for Clause Identification. Proc. of the European Conference on Machine Learning (ECML)  (2002) pp. 35--47 (abstract) [bibitem]
  • Shallow Parsing; Chunking and Clause identification.
• S. Har-Peled, D. Roth, and D. Zimak, Constraint Classification: a new approach to Multiclass Classification. Proc. of the International Workshop on Algorithmic Learning Theory (ALT)  (2002) pp. 135--150 (abstract) [bibitem]
• S. Agarwal and D. Roth, Learning a Sparse Representation for Object Detection. Proc. of the European Conference on Computer Vision (ECCV)  (2002) pp. 113--128 (abstract) [bibitem]
• M. Yang, D. Roth, and N. Ahuja, A Tale of Two Classifiers: SNoW vs. SVM in Visual Recognition. Proc. of the European Conference on Computer Vision (ECCV)  (2002) pp. 685--700 (abstract) [bibitem]
• D. Roth, M. Yang, and N. Ahuja, Learning to Recognize 3D Objects. Neural Computation  (2002) pp. 1071--1104 (abstract) [bibitem]
• D. Roth, C. Cumby, X. Li, P. Morie, R. Nagarajan, V. Punyakanok, N. Rizzolo, K. Small, and W. Yih, Question-Answering via Enhanced Understanding of Questions. TREC  (2002)  (abstract) [bibitem]
• R. Greiner, A. Grove, and D. Roth, Learning Cost-Sensitive Active Classifiers. Artificial Intelligence  (2002) pp. 137--174 (abstract) [bibitem]
  • Earlier version appeared in ICML'96

2001

• R. Khardon, D. Roth, and R. Servedio, Efficiency versus Convergence of Boolean Kernels for On-Line Learning Algorithms. The Conference on Advances in Neural Information Processing Systems (NIPS)  (2001)  [bibitem]
  • Kernel Perceptron with Exponentially Many mistakes; Hardness of Kernel Winnow.
• V. Punyakanok and D. Roth, The Use of Classifiers in Sequential Inference. The Conference on Advances in Neural Information Processing Systems (NIPS)  (2001) pp. 995--1001 (abstract) [bibitem]
  • Structured, sequential output; Sequence Prediction: HMM with classifiers, Conditional Models, Constraint Satisfaction
• D. Roth and W. Yih, Relational Learning via Propositional Algorithms: An Information Extraction Case Study. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)  (2001) pp. 1257--1263 (abstract) [bibitem]
  • Expressive, Relational Features for Information Extraction
• D. Roth, Reasoning with Classifiers. Proc. of the European Conference on Machine Learning (ECML)  (2001) pp. 506--510 [bibitem]
  • Paper written to accompany an invited talk at ECML'01. Sequential Inference: Conditional Models, Constraint Satisfaction
• A. Garg and D. Roth, Understanding Probabilistic Classifiers. Proc. of the European Conference on Machine Learning (ECML)  (2001) pp. 179--191 (abstract) [bibitem]
  • An Information Theory based explanation of the good performance of naive Bayes
• A. Garg and D. Roth, Learning Coherent Concepts. Proc. of the International Workshop on Algorithmic Learning Theory (ALT)  (2001) pp. 135--150 (abstract) [bibitem]
• X. Li and D. Roth, Exploring Evidence for Shallow Parsing. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2001) pp. 107--110 (abstract) [bibitem]
  • Learning Shallow Parsers vs. Full Parsers for Chunking tasks
• Y. Even-Zohar and D. Roth, A Sequential Model for Multi Class Classification. Proc. of the Conference on Empirical Methods for Natural Language Processing (EMNLP)  (2001) pp. 10-19 (abstract) [bibitem]
  • Multiclass classification: reducing the number of candidate classes; part-of-speech (POS) tagging
• J. Chuang and D. Roth, Gene Recognition based on DAG shortest paths. The International Conference on Intelligent Systems for Molecular Biology  (2001) pp. 1-9 (abstract) [bibitem]
• J. Chuang and D. Roth, Gene Recognition based on DAG shortest paths. Bioinformatics  (2001) pp. S56--S64 (abstract) [bibitem]
• A. Carlson, J. Rosen, and D. Roth, Scaling Up Context Sensitive Text Correction. Proceedings of the National Conference on Innovative Applications of Artificial Intelligence (IAAI)  (2001) pp. 45--50 (abstract) [bibitem]
• D. Roth, G. Kao, X. Li, R. Nagarajan, V. Punyakanok, N. Rizzolo, W. Yih, C. Alm, and L. Moran, Learning Components for a Question Answering System. TREC  (2001) pp. 539-548 (abstract) [bibitem]
• M. Yang, D. Roth, and N. Ahuja, Face Detection Using Large Margin Classifiers. Proceedings of IEEE International Conference on Image Processing  (2001) pp. 665--668 (abstract) [bibitem]
• A. Grove and D. Roth, Linear concepts and hidden variables. Machine Learning  (2001) pp. 123--141 (abstract) [bibitem]

2000

• D. Roth and D. Zelenko, Towards a theory of Coherent Concepts. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (2000) pp. 639--644 (abstract) [bibitem]
• E. Kim-Sang, W. Daelemans, H. Dejean, R. Koeling, Y. Krymolowski, V. Punyakanok, and D. Roth, Applying System Combination to Base Noun Phrase Identification. COLING-ACL, The 18th International Conference on Computational Linguistics  (2000) pp. 857--863 (abstract) [bibitem]
• Y. Even-Zohar and D. Roth, A classification approach to word prediction. Proc. of the Annual Meeting of the North American Association of Computational Linguistics (NAACL)  (2000) pp. 124-131 (abstract) [bibitem]
  • Learning with expressive features; dependency parse based features; verb prediction
• C. Cumby and D. Roth, Relational Representations that facilitate learning. Proc. of the International Conference on the Principles of Knowledge Representation and Reasoning  (2000) pp. 425--434 (abstract) [bibitem]
  • FEX: feature extraction language; relational features; relational generation functions
• D. Roth, Learning in Natural Language: Theory and Algorithmic Approaches. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2000) pp. 1--6 (abstract) [bibitem]
  • A paper written to accompany and invited talk at CoNLL.
• M. Yang, D. Roth, and N. Ahuja, A SNoW-based Face Detector. The Conference on Advances in Neural Information Processing Systems (NIPS)  (2000) pp. 855--861 (abstract) [bibitem]
• M. Yang, D. Roth, and N. Ahuja, Learning To Recognize 3D Objects With SNoW. Proc. of the European Conference on Computer Vision (ECCV)  (2000)  (abstract) [bibitem]
• M. Yang, D. Roth, and N. Ahuja, View-Based 3D Object Recognition Using SNoW. Proceedings of the Asian Conference on Computer Vision (ACCV)  (2000) pp. 830--835 (abstract) [bibitem]
• D. Roth, M. Yang, and N. Ahuja, Learning to Recognize Objects. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  (2000) pp. 724--731 (abstract) [bibitem]
• V. Punyakanok and D. Roth, Shallow Parsing by Inferencing with Classifiers. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL)  (2000) pp. 107--110 (abstract) [bibitem]

1999

• D. Roth, Learning in Natural Language. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)  (1999) pp. 898--904 (abstract) [bibitem]
  • Probabilistic classifiers (Naive Bayes; HMM) as linear models; generative vs. discriminative; Best Paper Award
• M. Munoz, V. Punyakanok, D. Roth, and D. Zimak, A Learning Approach to Shallow Parsing. EMNLP-VLC, the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora  (1999) pp. 168--178 (abstract) [bibitem]
• R. Khardon, D. Roth, and L. Valiant, Relational Learning for NLP using Linear Threshold Elements. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)  (1999) pp. 911--917 (abstract) [bibitem]
• R. Khardon and D. Roth, Learning to Reason with a Restricted View. Machine Learning  (1999) pp. 95--117 (abstract) [bibitem]
• R. Khardon, H. Mannila, and D. Roth, Reasoning with Examples: Propositional Formulae and Database Dependencies. Acta Informatica  (1999) pp. 267--286 (abstract) [bibitem]
• A. Golding and D. Roth, A Winnow based approach to Context-Sensitive Spelling Correction. Machine Learning  (1999) pp. 107--130 (abstract) [bibitem]
  • Special Issue on Machine Learning and Natural Language.
• D. Roth and D. Zelenko, Coherent Concepts, Robust Learning Invited. SOFSEM 99: Theory and Practice of Informatics  (1999) pp. 260--272 (abstract) [bibitem]
  • Lecture notes in Artificial Intelligence, vol. 1725
• D. Roth, Memory Based Learning in NLP.  (1999)  (abstract) [bibitem]
• M. Mavronicolas and D. Roth, Linearizable Read/Write Objects. Theoretical Computer Science  (1999) pp. 267--319 (abstract) [bibitem]
• Y. Even-Zohar, D. Roth, and D. Zelenko, Word Clustering via Classification. BISFAI99  (1999)  (abstract) [bibitem]
• A. Carlson, C. Cumby, J. Rosen, and D. Roth, The SNoW Learning Architecture.  (1999)  [bibitem]

1998

• D. Roth and D. Zelenko, Part of Speech Tagging Using a Network of Linear Separators. COLING-ACL, The 17th International Conference on Computational Linguistics  (1998) pp. 1136--1142 (abstract) [bibitem]
• D. Roth, Learning to Resolve Natural Language Ambiguities: A Unified Approach. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (1998) pp. 806--813 (abstract) [bibitem]
  • Many Natural Language Classifiers are Linear; including probabilistic classifiers; argues for a discriminative approach; SNoW
• D. Roth, Learning and Reasoning with Connectionist Representations. Neural Computing Surveys  (1998) pp. 1--40 [bibitem]
  • A contribution to ``Connectionist Symbol Processing: Dead or Alive''
• Y. Krymolowski and D. Roth, Incorporating Knowledge in Natural Language Learning: A Case Study. COLING-ACL workshop on the Usage of WordNet in Natural Language Processing Systems  (1998) pp. 121--127 (abstract) [bibitem]
  • Prepositional Phrase Attachment (PPA); using WordNet to generate expressive features.
• A. Grove and D. Roth, Linear concepts and hidden variables: An empirical study. The Conference on Advances in Neural Information Processing Systems (NIPS)  (1998) pp. 500--506 [bibitem]
  • Margin Winnow (Perceptron); discriminative vs. generative
• D. Basri and D. Jacobs, Clustering Appearances of 3D Objects. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  (1998) pp. 414-420 (abstract) [bibitem]
  • Clustering of Curves
• H. Aizenstein, A. Blum, R. Khardon, A. Kushilevitz, L. Pitt, and D. Roth, On learning read-k satisfy-j DNF. SIAM Journal of Computing  (1998) pp. 1515--1530 (abstract) [bibitem]

1997

• D. Roth, Learning to perform knowledge intensive inferences Invited Abstract. MSCS: Mathematical Foundations of Computer Science  (1997) pp. 108--109 [bibitem]
  • Lecture notes in Computer Science (LNCS) 1295
• R. Khardon and D. Roth, Defaults and Relevance in Model Based Reasoning. Artificial Intelligence  (1997) pp. 169--193 (abstract) [bibitem]
• R. Khardon and D. Roth, Learning to Reason. Journal of the ACM  (1997) pp. 697--725 (abstract) [bibitem]
• K. Daniels, V. Milenkovic, and D. Roth, Finding the Maximum Area Axis-Parallel Rectangle in a Polygon. Computational Geometry: Theory and Applications  (1997) pp. 125--148 (abstract) [bibitem]
• I. Dagan, Y. Karov, and D. Roth, Mistake-Driven Learning in Text Categorization. EMNLP  (1997) pp. 55-63 (abstract) [bibitem]

1996

• D. Roth, On the hardness of approximate reasoning. Artificial Intelligence  (1996) pp. 273--302 (abstract) [bibitem]
  • Hardness of Reasoning with Bayesian Networks; Exact inference is #P-Complete; Approximate Reasoning is NP-Hard.
• E. Kushilevitz and D. Roth, On Learning Visual Concepts and DNF Formulae. Machine Learning  (1996) pp. 65--85 (abstract) [bibitem]
• R. Khardon and D. Roth, Reasoning with Models. Artificial Intelligence  (1996) pp. 187--213 (abstract) [bibitem]
  • Characteristic Models of Boolean Functions
• R. Greiner, A. Grove, and D. Roth, Learning Active Classifiers. Proc. of the International Conference on Machine Learning (ICML)  (1996) pp. 207--215 (abstract) [bibitem]
• A. Golding and D. Roth, Applying Winnow to Context-Sensitive Spelling Correction. Proc. of the International Conference on Machine Learning (ICML)  (1996) pp. 182--190 (abstract) [bibitem]
• D. Roth, Learning in Order to Reason Invited. AAAI Fall Symposium on Learning Complex Behaviors in Adaptive Intelligent Systems  (1996) pp. 46-52 (abstract) [bibitem]
• D. Roth, Learning in Order to Reason: The Approach. SOFSEM: Theory and Practice of Informatics  (1996) pp. 113--124 (abstract) [bibitem]
  • Lecture notes in Computer Science, vol. 1175
• D. Roth, On the hardness of approximate reasoning. AAAI Fall Symposium on AI and NP Hard Problems  (1996) pp. 137-143 (abstract) [bibitem]
• D. Roth, A Connectionist Framework for Reasoning: Reasoning with Examples. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (1996) pp. 1256--1261 (abstract) [bibitem]

1995

• D. Roth, Learning to Reason: The Non-Monotonic Case. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)  (1995) pp. 1178--1184 (abstract) [bibitem]
• R. Khardon and D. Roth, Defaults and Relevance in Model Based Reasoning.  (1995)  [bibitem]
• R. Khardon and D. Roth, Learning to Reason with a Restricted View. Proc. of the Annual ACM Workshop on Computational Learning Theory (COLT)  (1995) pp. 301--310 [bibitem]
• R. Khardon and D. Roth, Default-Reasoning with Models. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)  (1995) pp. 319--325 [bibitem]

1994

• R. Khardon and D. Roth, A note on Horn Theories.  (1994)  [bibitem]
  • Manuscript.
• R. Khardon and D. Roth, Exploiting Relevance through Model-based reasoning. AAAI Fall Symposium on Relevance  (1994) pp. 109-114 [bibitem]
• R. Khardon and D. Roth, Learning to Reason. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (1994) pp. 682--687 [bibitem]
• R. Khardon and D. Roth, Reasoning with Models. Proceedings of the National Conference on Artificial Intelligence (AAAI)  (1994) pp. 1148--1153 [bibitem]
• A. Blum, R. Khardon, A. Kushilevitz, L. Pitt, and D. Roth, On learning read-k satisfy-j DNF. Proc. of the Annual ACM Workshop on Computational Learning Theory (COLT)  (1994) pp. 110--117 (abstract) [bibitem]

1993

• D. Roth, On the hardness of approximate reasoning. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)  (1993) pp. 613--618 [bibitem]
  • Hardness of Reasoning with Bayesian Networks; Exact inference is #P-Complete; Approximate Reasoning is NP-Hard.
• E. Kushilevitz and D. Roth, On Learning Visual Concepts and DNF Formulae. Proc. of the Annual ACM Workshop on Computational Learning Theory (COLT)  (1993) pp. 317--326 [bibitem]
• K. Daniels, V. Milenkovic, and D. Roth, Finding the Maximum Area Axis-Parallel Rectangle in a Simple Polygon. CCCG, the Fifth Canadian Conference on Computational Geometry  (1993) pp. 322--327 [bibitem]

1992

• M. Mavronicolas and D. Roth, Efficient, Strongly Consistent Implementation of Shared Memory. WDAG, CCCG, the 6th International Workshop on Distributed Algorithms  (1992) pp. 346--361 [bibitem]

1991

• M. Mavronicolas and D. Roth, Sequential Consistency and Linearizability: Read/Write Objects. In Proceedings of the 29th Annual Allerton Conference on Communication, Control and Computing  (1991) pp. 683--692 [bibitem]