Carnegie Mellon University
School of Computer Science  ›  Language Technologies Institute  ›  Research  ›  LTI Ph.D. Dissertations  ›  LTI Ph.D. Dissertations

2024

Graduate Advisor Dissertation Employer Upon Graduation
James Fiacco Rosé Functional Components as a Paradigm for Neural Model Explainability

2023

Graduate Advisor Dissertation Employer Upon Graduation
Chaitanya Ahuja Morency Communication Beyond Words: Grounding Visual Body Motion with Language Researcher, Meta
Prakhar Gupta Bigham Improving Reliability in Dialogue Systems Research Scientist, Google
Sachin Kumar Tsvetkov Optimization Methods For Modeling Diversity In Language Technologies Post-Doc AI2, Asst Professor, Ohio State University
Juncheng Billy Li Metze Towards Robust Large-scale Audio/Visual Learning Quantitative Researcher, Two Sigma Investment
Xinjian Li Watanabe, Black Low-Resource Speech Recognition for Thousands of Languages Research Scientist, Google
Kaixin Ma Nyberg Hybrid Knowledge Architectures for Question Answering NLP Researcher, Tencent AI Lab
Salvador Bedredín Medina Maza Hauptmann Talking us into the Metaverse: Towards Realistic Streaming Speech-to-Face Animation Research Scientist, Epic Games
Sanket Vaibhav Mehta Strubell Efficient Lifelong Learning in Deep Neural Networks: Optimizing Architecture, Training, and Data Research Scientist, Google
Chirag Nagpal Dubrawski Leveraging Heterogeneity in Time-to-Event Predictions Research Scientist, Google
Raphaël Olivier Raj Assessing and enhancing adversarial robustness in context and applications to speech security
Naoki Otani Hovy Leveraging Eventuality-Centric Implicit Knowledge for Natural Language Understanding Research Scientist, Megagon Labs
Hai Pham Póczos, Woodruff  Towards Efficient and Scalable Representation Learning Technical Staff, Reka AI
Torsten Wörtwein Morency Towards Improving Transparency in Multimodal Affect Perception Multimodal AI/ML Engineer, ETS
Donghan Yu Yang Leveraging Textual Semantics for Knowledge Graph Acquisition and Application Senior Researcher, Microsoft
Shikun Zhang Sadeh Understanding People’s Diverse Privacy Attitudes: Notification, Control, and Regulatory Implications TikTok
Zhisong Zhang Hovy, Strubell Exploring Language Structured Prediction in Resource-limited Scenarios
Zhong Zhou Waibel Massively Multilingual Text Translation for Low-Resource Languages

2022

Khyathi Raghavi Chandu Black Effective Anchoring of Multiview Narrative Generation Research Scientist, Meta AI
Aditi Swanand Chaudhary Neubig Automatic Extraction and Application of Language Descriptions for Under-Resourced Languages Researcher, Google Research
Volkan Cirik Morency, Berg-Kirkpatrick Understanding Language Referring To The VisualWorld Research Scientist, ASAPP
Siddharth Dalmia Metze, Black Exploiting Compositionality in Sequence Models Research Scientist, Google
Anjalie Field Tsvetkov Integrating Language Technologies and Social Theories Post-Doctoral Fellow - Stanford University
Jonathan Francis Nyberg, Oh Knowledge-enhanced Representation Learning for Multiview Context Understanding Research Scientist, Bosch
Varun Gangal Hovy A Suite of Low-Data Generation Settings Necessitating Interventions on End-to-End NLG Models Tenure-Track Assistant Professor in the School of Computing at Clemson University (SC)
Junxian He Neubig, Berg-Kirkpatrick Towards Efficient Natural Language Generation Tenure Track Asst. Professor, Shanghai Jiao Tong University
Ting-Yao Hu Hauptmann Disentangled Representations beyond Vectors for Multimedia Content Researcher, Apple Inc.
Divyansh Kaushik Lipton, Hovy Robustifying NLP with Humans in the Loop Associate Director for Emerging Technologies & National Security Policy, Federation of American Scientists
Xiang Kong Hovy Towards Efficient Neural Machine Translation Machine Learning Researcher, Apple
Shikib (Ahmad) Mehri Eskenazi Towards Generalization in Dialog through Inductive Biases Applied Scientist II - Amazon (Sunnyvale)
Aakanksha Naik Rosé Adapting to the Long Tail in Language Understanding Research Scientist, Allen Institute for Artificial Intelligence
Shruti Palaskar Metze, Black Multimodal Learning from Videos: Exploring Models and Task Complexities Research Scientist, Apple
Hy Hieu Pham Yang, Le Reducing the Costs to Design, Train, and Collect Data for Neural Networks with Combinatorial Optimization
Dheeraj Rajagopal Hovy Explanations for Natural Language: From Theory to Practice Researcher, Google (Seattle)
Sai Krishna Rallabandi Black De-Entanglement: A Framework towards building Ubiquitous speech technologies Fidelity
Shruti Rijhwani Neubig Improving Optical Character Recognition for Endangered Languages Research Scientist, Google
Maria Ryskina Gormley, Hovy Learning Computational Models of Non­ Standard Language Post-Doctoral Associate, McGovern Institute for Brain Research, MIT
Evangelia Spiliopoulou Hovy Modeling Event Implications via Multi-faceted Entity Representations Applied Scientist, AWS AI Amazon
Xinyi (Cindy) Wang Neubig Data Efficient Multilingual Natural Language Processing Research Scientist, Google
Chunting Zhou Neubig Mitigating Semantic and Distributional Discrepancies in Natural Language Processing Research Scientist, Meta AI

2021

Graduate Advisor(s) Dissertation Employer Upon Graduation
Maria Joana Correia Raj, Trancoso In-the-wild detection of speech affecting diseases Research Scientist, Spotify
Kartik Goyal Dyer Characterizing and Overcoming the Limitations of Neural Autoregressive Models Research Assistant Professor, Toyota Technological Institute of Chicago
Hiroaki Hayashi Neubig Neural Aspect-based Text Generation Researcher, Salesforce
Junjie Hu Neubig Leveraging Word and Phrase Alignments for Multilingual Learning Assistant Professor, University of Wisconsin-Madison
Po Yao Huang Hauptmann Towards Multilingual Vision-Language Models Research Scientist, Facebook AI
Harsh Jhamtani Berg-Kirkpatrick Grounded Natural Language Generation via Interpretable Hierarchical Operations Senior Researcher, Microsoft Research
Yohan Jo Hovy Toward Computational Argumentation with Reasoning and Knowledge Applied Scientist, Amazon
Guokun Lai Yang Neural Sequential Modeling and Applications Research Scientist, Bytedance
Junwei Liang Hauptmann From Recognition to Prediction: Analysis of Human Action and Trajectory Prediction in Video Computer Vision Researcher, Tencent
Paul Michel Neubig Learning Neural Models for Natural Language Processing in the Face of Distributional Shift Laplace Post-Doctoral Chair, Ecole Normale Superieure
Shrimai Prabhumoye Black, Salakhutdinov Controllable Text Generation And Ethical Implications
Hugo Patinho Rodrigues Nyberg, Coheur Learning Semantic Patterns for Question Generation Software Engineer at freiheit.com technologies
Qinlan Shen Rosé Evaluating and Recontextualizing the Social Impacts of Moderating Online Discussions Research Scientist, Oracle Labs
Zirui (Edward) Wang Tsvetkov, Strubell Mitigating Negative Transfer for Better Generalization and Efficiency in Transfer Learning Research Scientist, Google
Pengcheng Yin Neubig Learning Structured Neural Semantic Parsers Research Scientist, Google Research
Michael Miller Yoder Rosé Computational Models of Identity Presentation in Language Postdoctoral Researcher, Collaboratory Against Hate & Center for Informed Democracy and Social-cybersecurity, CMU

2020

Graduate Advisor(s) Dissertation Employer Upon Graduation
Joseph Chang Kittur Supporting Global Context under Evolving User Intents during Data Exploration CMU Post-Doc - Center for Knowledge Acceleration.
Wei-Cheng Chang Yang Learning with Kernals at Scale and Applications in Generative Modeling Applied Scientist, Amazon Search
Zhuyun Dai Callan Neural Matching and Importance Learning in Information Retrieval Software Engineer, Google
Zihang Dai Yang Improving Deep Generative Modeling with Practical Applications Researcher, Google
Bhuwan Dhingra Cohen, Salakhutdinov End-to-End Learning with Text and Knowledge Bases Duke University - Professor
Jesse Dodge Smith Towards Efficient and Reproducible Natural Language Processing University of Washington - Research Staff
Dongyeop Kang Hovy Linguistically Informed Language Generation: A Multi-faceted Approach UC Berkeley - Post Doc
Xuezhe Ma Hovy Neural Networks for Linguistic Structured Prediction and Their Interpretability University of Southern California - Research Faculty - Dept ISI
Elijah Mayfield Black Defensible Explanations for Algorithmic Decisions about Writing in Education LightSide Labs
Daniel Schwartz Mitchell Using Multitask Learning to Understand Language Processing in the Brain Applied Scientist, Microsoft
John Wieting Berg-Kirkpatrick, Neubig Learning and Applications of Paraphrastic Representations for Natural Language Researcher, Google
Yuexin Wu Yang Learning with Graph Structures and Neural Networks Researcher, Google

2019

Graduate Advisor(s) Dissertation Employer Upon Graduation
Pradeep Dasigi Hovy Knowledge-Aware Natural Language Understanding Research Scientist Allen Institute for Artificial Intelligence
Ting-Hao (Kenneth) Huang Bigham A Crowd-Powered Conversational Assistant that Automates Itself Over Time Asst. Professor, Penn State
Austin Matthews Dyer Linguistic Knowledge for Neural Language Generation and Machine Translation Unbabel, Pittsburgh
Pedro Mota Eskenazi, Coheur BeamSeg: a Joint Model for Multi-Document Segmentation and Topic Identification inesc id, Lisboa
Swabha Swayamdipta Smith, Dyer Syntactic Inductive Biases for Natural Language Processing Assistant Professor, University of Southern California
Samuel Thomson Smith Encoding and Decoding Graph Representations of Natural Language Researcher at Semantic Machines
Di Wang Nyberg Example-Driven Question Answering CTO, Wooboo, Inc.
Ruochen Xu Yang Learning Cross-language and Cross-style Mappings with Limited Supervision Researcher at Microsoft Redmond
Diyi Yang Kraut, Hovy Computational Social Roles Post-Doc, Google, Fall 2019 - Assistant Professor Georgia Tech.
Zhilin Yang Salakhutdinov, Cohen Advances in Generative Feature Learning Start up
Ran Zhao Rudnicky, Black Socially-Aware Dialogue System Bain & Company, Asia
Tiancheng (Tony) Zhao Eskenazi Learning to Converse with Latent Actions CEO, Scientist - ConvMind

2018

Graduate Advisor(s) Dissertation Employer Upon Graduation
Jun Araki Mitamura Extraction of Event Structures from Text Senior Research Scientist at Bosch Research
Pallavi Baljekar Black Speech Synthesis from Found Data
Leonid Boytsov Nyberg Efficient and Accurate Non-Metric k-NN Search with Applications to Text Matching Research Scientist at 3M/M*Modal
Xinlei Chen Gupta Visual Knowledge Learning Research Scientist at Facebook
Justin Chiu Rudnicky Features for Search and Understanding of Noisy Conversational Speech Research Engineer at Avrio AI
Rui Correia Eskenazi, Mamede Automatic Classification of Metadiscourse inesc id, Lisboa
Jeffrey Flanigan Carbonell Parsing and Generation for the Abstract Meaning Representation Post-Doc, UMass - Fall 19 - Asst. Professor, UC Santa Cruz
Andrew Hsi Yang, Carbonell Event Extraction for Document-Level Structured Summarization Software Engineer at Bloomberg LP
Rose Kanjirathinkal Cohen Explainable Recommendations Research Scientist, Facebook
Yubin Kim Callan Robust Selective Search Senior Data Scientist, UPMC Enterprises
Anurag Kumar Raj Acoustic Intelligence in Machines Research Scientist, Facebook
Hanxiao Liu Yang Large-Scale Machine Learning over Graphs Research Scientist, Google
Seungwhan Moon Carbonell Proactive Transfer Learning Research Scientist, Facebook
Keerthiram Murugesan Carbonell Online and Adaptive Methods for Multitask Learning Research Scientist at IBM T.J. Watson Research Ctr.
Yun Wang Metze Polyphonic Sound Event Detection with Weak Labeling Research Scientist, Facebook
Chenyan Xiong Callan Text Representation, Retrieval, and Understanding with Knowledge Graphs Research Scientist at Microsoft Research & AI
Guoqing Zheng Yang, Carbonell Empowering Probabilistic Inference with Stochastic Deep Neural Networks Research Scientist at Microsoft Research

2017

Graduate Advisor(s) Dissertation Employer Upon Graduation
Hyeju Jang Rosé Computational Modeling of Metaphor in Discourse Postdoctoral Research Fellow, University of British Columbia
Sujay Kumar Jauhar Hovy A Relation-Centric View of Semantic Representational Learning Research Scientist, Microsoft Research
Lu Jiang Mitamura Web-scale Multimedia Search for Internet Video Content Google Research
Lingpeng Kong Smith, Dyer Neural Representation Learning in Linguistic Structured Prediction Research Scientist, Google DeepMind
Zhen-Zhong Lan Hauptmann Towards Usable Multimedia Event Detection Computer Vision Researcher, WiZR
Rui Liu Nyberg A Phased Ranking Model for Information Systems Amazon
Zhou Yu Black Situated Intelligent Interactive Systems Assistant Professor, UC Davis

2016

Graduate Advisor(s) Dissertation Employer Upon Graduation
Waleed Ammar Dyer, Smith Towards a Universal Analyzer of Natural Languages Research Scientist, Allen Institute for Artificial Intelligence
Yun-Nung (Vivian) Chen Rudnicky, Gershman Unsupervised Learning and Modeling of Knowledge and Intent for Spoken Dialogue Systems Assistant Professor, National Taiwan University
Manaal Faruqui Dyer Diverse Context for Learning Word Representations Google Research, NY
Steven Gardiner Tomasic Crowed-Sourced Wrapper Construction with End Users Post-Doctoral Research, CMU, Pittsburgh, PA
Yajie Miao Metze Incorporating Context Information into Deep Neural Network Acoustic Models
Prasanna Kumar Muthukumar Black Towards Integrated Acoustic Models for Speech Synthesis BBN Technologies, Cambridge, MA
Udhyakumar Nallasamy Metze, Schultz Adaptation techniques to improve ASR performance on accented speakers Apple, CA
Yan Chuan Sim Smith Text as Strategic Choice Institute for Infocomm Research (I2R)
Sunayana Sitaram Black Pronunciation Modeling for Synthesis of Low Resource Languages Microsoft Research, India
Ming Sun Rudnicky Adapting Spoken Dialog Systems Towards Domains and Users Disney Research, Pittsburgh, PA
Yulia Tsvetkov Dyer Linguistic Knowledge in Data-Driven Natural Language Processing Assistant Professor, Language Technologies Institute (Beginning Fall 2017)
Yi-Chia Wang Kraut Modeling Self-Disclosure in Social Networking Sites Research Scientist at Uber AI
William Yang Wang Cohen Learning to Reason with a Scalable Probabilistic Logic Asst. Professor, UC Santa Barbara, Santa Barbara, CA
Miaomiao Wen Rosé Investigating Virtual Teams in Massive Open Online Courses: Deliberation-based Virtual Team Formation, Discussion Mining and Sup Coursera
Derry Tanti Wijaya Mitchell VerbKB: A Knowledge Base of Verbs for Natural Language Understanding Post-Doctoral Fellow, University of Pennsylvania
Shoou-I Yu Hauptmann Surveillance Video Analysis with External Knowledge and Internal Constraints Oculus

2015

Graduate Advisor(s) Dissertation Employer Upon Graduation
David Bamman Smith People-Centric Natural Language Processing Faculty, University of California Berkeley
Jonathan Clark Lavie Locally Non-Linear Learning via Feature Induction and Structured Regularization in Statistical Machine Translation Microsoft Corporation
Bhavana Dalvi Cohen, Callan Constrained Semi-supervised Learning in the Presence of Unanticipated Classes Allen Institute for Artificial Intelligence
Michael Denkowski Lavie Machine Translation for Human Translators Safaba
Matthew Gardner Mitchell Reading and Reasoning with Knowledge Graphs Research Scientist, Allen Institute for Artificial Intelligence
Meghana Kshirsagar Carbonell Combine and conquer: methods for multitask learning in biology and language Yahoo! NYC
Wang Ling Black, Dyer Machine Translation 4 Microblogs Research Scientist, Google DeepMind
Matthew Marge Rudnicky Miscommunication Detection and Recovery for Spoken Dialogue Systems in Physically Situated Contexts ARL Army Research Lab
Luis Marujo Gershman, Carbonell, Matos, Neto Event-based Multi-document Summarization Research Scientist, Snapchat
Joao Miranda Black, Neto, Coheur Combining multiple parallel streams for improved speech processing INESC-ID
Subhodeep Moitra Langmead Feature Learning and Graphical Models for Protein Sequences Google Inc.
Agha Ali Raza Rosenfeld Viral Entertainment as a Vehicle for Disseminating Core Development Services Assistant Professor, Information Technology University, Punjab, Pakistan
Hideki Shima Mitamura Paraphrase Pattern Acquisition by Diversifiable Bootstrapping Duolingo
Reyyan Yeniterzi Callan Effective and Efficient Approaches to Retrieving and Using Expertise in Social Media Assistant Professor, Ozyegin University
Dani Yogatama Smith Sparse Models of Natural Language Text Research Scientist, Google DeepMind

2014

Graduate Advisor(s) Dissertation Employer Upon Graduation
Siddharth Gopal Yang Large-scale Structured Learning Google Inc.
Aasish Pappu Rudnicky Knowledge Discovery Through Spoken Dialog Yahoo Inc.
Nathan Schneider Smith Lexical Semantic Analysis in Natural Language Text Postdoc, University of Edinburgh

2013

Graduate Advisor(s) Dissertation Employer Upon Graduation
Gopala Krishna Anumanchipalli Black, Oliveira Intra-Lingual and Cross-Lingual Prosody Modelling Postdoc, University of California San Francisco
Sivaraman Balakrishnan Carbonell Finding and Leveraging Structure in Learning Problems Postdoc, University of California Berkeley
Ramnath Balasubramanyan Cohen Specifying Latent Structure Characteristics in Mixed-membership Models Twitter, Inc.
Sourish Chaudhuri Raj Structured Models for Semantic Analysis of Audio Content Google Inc.
Sourish Chaudhuri Hauptmann Structured Models for Semantic Analysis of Audio Content Google Inc.
Jose Pablo Gonzalez-Brenes Mostow What and When Do Students Learn? Methods For Knowledge Tracing With Data-Driven Mapping of Items to Skills Pearson Research Network
Kenneth Heafield Lavie Efficient Language Modeling Algorithms with Applications to Statistical Machine Translation Postdoc, Stanford University
Mahesh Joshi Rosé Multi-Domain Learning: Analysis, and Methods for Multi-Attribute Domains eBay Inc.
Anagha Kulkarni Callan Efficient and Effective Large-scale Search Assistant Professor, San Francisco State University
Mohit Kumar Carbonell, Rudnicky Extending Active Learning for Improved Long-Term Return on Investment of Learning Systems Flipkart.com, India
Alok Parlikar Black Style-Specific Phrasing in Speech Synthesis Amazon.com, Inc.
Kriti Puniyani Xing Spatiotemporal Gene Networks from ISH Images Google Inc.
Long Qin Rudnicky Learning Out-of-Vocabulary Words in Automatic Speech Recognition Duolingo
Pradipta Ray Xing, Hinman Computational Methods for Analyzing the Architecture and Evolution of the Regulatory Genome Postdoc, University of Texas Center for Systems Biology
Konstantin Salomatin Yang Large-scale Hierarchical Optimization for Online Advertising and Wind Farm Planning Twitter, Inc.
Narges Sharif Razavian Langmead Continuous Graphical Models for Static and Dynamic Distributions: Application to Structural Biology Postdoc, New York University
Selen Uguroglu Carbonell Robust Learning with Highly Skewed Category Distributions Apple Inc.
Guang Xiang Hong, Rosé Toward a Phish Free World: A Feature-type-aware Cascade Learning Framework for Phish Detection Twitter, Inc.
Tae Yano Smith, Cohen Text as Actuator: Text-Driven Response Modeling and Prediction in Politics Microsoft Corporation

2012

Graduate Advisor(s) Dissertation Employer Upon Graduation
Vamshi Ambati Carbonell, Vogel Active Learning and Crowdsourcing for Machine Translation in Low Resource Scenarios Base CRM
Shilpa Arora Nyberg Minimizing the Costs in Generalized Interactive Annotation Learning Google Inc.
Nguyen Bach Waibel, Vogel Dependency Structures for Statistical Machine Translation Microsoft Corporation
Wei Chen Mostow Detecting Off-Task Speech Google Inc.
Dipanjan Das Smith Semi-Supervised and Latent-Variable Models of Natural Language Semantics Google Inc.
Kevin Gimpel Smith Discriminative Feature-Rich Modeling for Syntax-Based Machine Translation Toyota Technological Institute
Abhay Harpale Yang Multi-Task Active Learning GE Global Research
Sanjika Hewavitharana Vogel Detecting Translational Equivalences in Comparable Corpora BBN Technologies
Wend-Huu (Roger) Hsiao Schultz Generalized Discriminative Training for Speech Recognition
Ni Lao Cohen Efficient Random Walk Inference with Knowledge Bases Airbnb
Frank Lin Cohen Scalable Methods for Graph-Based Unsupervised and Semi-Supervised Learning
Andre F. T. Martins Smith, Xing, Figueiredo, Aguiar The Geometry of Constrained Structured Prediction Applications to Inference and Learning of Natural Language Syntax Priberam Labs
Manas Pathak Raj Privacy-Preserving Machine Learning for Speech Processing Walmart Labs
Aaron Phillips Brown Modeling Relevance in Statistical Machine Translation Scoring Alignment, Context, and Annotations of Translation Instances Google Inc.
Nico Schlaefer Nyberg Statistical Source Expansion for Question Answering Citadel Investment Group
Mehrbod Sharifi Carbonell, Fink Interpretation of User Comments for Detection of Malicious Websites Google Inc.
Ravi Starzl Carbonell Computational Modeling of Immune Signals Faculty, LTI CMU
Le Zhao Callan Modeling and Solving Term Mismatch for Full-Text Retrieval Google Inc.

2011

Graduate Advisor(s) Dissertation Employer Upon Graduation
Amr Ahmed Xing Modeling Content and Users: Structured Probabilistic Representation and Scalable Online Inference Algorithms Google Inc.
Jaime Arguello Callan Federated Search in Heterogenous Environments Assistant Professor, University of North Carolina Chapel Hill
Kai-Min Kevin Chang Just, Mitchell Quantitative Modeling of the Neural Representation of Nouns and Phrases Language Technologies Institute, Carnegie Mellon University.
Shay Cohen Smith Computational Learning of Probabilistic Grammars in the Unsupervised Setting Chancellor's Fellow, University of Edinburgh
Jonathan Elsas Carbonell Leveraging Collection Structure in Information Retrieval with Applications to Search in Conversational Social Media Google Inc.
Rashmi Gangadharaiah Carbonell, Brown Coping with Data-sparsity in Example-Based Machine Translation IBM Corporation, Bangalore
Michael Heilman Smith Automatic Factual Question Generation from Text ETS
David Huggins-Daines Rudnicky An Architecture for Scalable, Universal Speech Recognition Nuance Communications
Jae Dong Kim Carbonell, Brown Chunk Alignment for Corpus-Based Machine Translation Google Inc.
Rohit Kumar Rosé Socially Capable Conversational Agents for Multi-Party Interactive Situations BBN Technologies
Abhimanyu Lad Yang A Framework for Evaluation and Optimization of Relevance and Novelty-based Retrieval LinkedIn Corporation
Kornel Laskowski Stern Predicting, Detecting, and Explaining the Occurrence of Vocal Activity in Multi-Party Conversation Voci Technologies
Tien-Ho Lin Bar-Joseph Learning Cellular Sorting Pathways Using Protein Interactions and Sequence Motifs Google Inc.
Oznur Tastan Klein-Seetharaman, Carbonell Prediction of Host-Virus Protein-Protein Interactions Microsoft Corporation
Hui (Grace) Yang Callan Personalized Concept Hierarchy Construction Assistant Professor, Georgetown University
Andreas Zollmann Vogel Learning Multiple-Nonterminal Synchronous Grammars for Statistical Machine Translation zollsoft GmbH

2010

Graduate Advisor(s) Dissertation Employer Upon Graduation
Satanjeev Banerjee Rudnicky Extracting and Using Implicit Supervision to Automatically Improve Meeting-Understanding Twitter, Inc.
Ming-Yu Chen Hauptmann Long Term Activity Analysis in Surveillance Video Archives Microsoft Corporation
Pinar Donmez Carbonell Proactive Learning: Towards Learning with Multiple Imperfect Predictors Yahoo Research
Lingyun Gu Stern Single-Channel Speech Separation Based on Instantaneous Frequency California Institute of Technology
Yifen Huang Mitchell Mixed-Initiative Clustering Google Inc.
Chanwoo Kim Stern Signal Processing for Robust Speech Recognition Motivated by Auditory Processing Microsoft Corporation
Brian Langner Black Data-driven Natural Language Generation Making Machines Talk Like Humans Using Natural Corpora
Yung-Hui Li Savvides Robust Long Range Iris Recognition from Video Using Super Resolution Assistant Professor, Feng Chia University (Taiwan)
Paul Ogilvie Callan Retrieval Using Document Structure and Annotations LinkedIn Corporation
Kishore Prahallad Black Automatic Building of Synthetic Voices using Audio Books Assistant Professor IIIT, Hyderabad
Alicia Tribble Fahlman Textual Inference for Retrieving Labeled Object Descriptions Alelo (Los Angeles) - Artificial Intelligence for Education
Shinjae Yoo Yang Machine Learning Methods for Personalized Email Prioritization Computational Science Center, Brookhaven National Laboratory

2009

Graduate Advisor(s) Dissertation Employer Upon Graduation
Matthew Bilotti Nyberg Linguistic and Semantic Passage Retrieval Strategies for Question Answering Twitter, Inc.
John Kominek Black TTS From Zero: Building Synthetic Voices for New Languages Silicon Vox Corporation
Einat Minkov Cohen Adaptive Graph Walk Based Similarity Measures in Entity-Relation Graphs Nokia Research Labs
Christian Monson Carbonell, Lavie Paramor From Paradigm Structure to Natural Language Morphology Induction Postdoc, Center for Spoken Language Understanding, Oregon Health and Science University
Hyaejin (Jean) Oh Smith Multiagent Social Learning in Large Repeated Games Postdoc, CMU RI
Vasco Pedro Carbonell Federated Ontology Search
Jade Goldstein Stewart Carbonell Genre Oriented Summarization U.S. Government
Yik-Cheung (Wilson) Tam Schultz Rapid Unsupervised Topic Adaptation - A Latent Semantic Approach Nuance Communications Inc.
Arthur Toth Black Using Articulatory Position Data to Improve Voice Transformation Yap Inc.
Ashish Venugopal Vogel Preference Grammars and Decoding Algorithms for Probabilistic Synchronous Context Free Grammar Based Translation Google Inc.
Richard Wang Cohen Language-Independent Class Instance Extraction Using the Web Google Inc.
Wen Wu J. Yang Multimedia Technologies for Landmark-Based Vehicle Navigation Siemens Corporate Research, Princeton NJ
Jun Yang Hauptmann A General Framework for Classifier Adaptation and its Applications in Multimedia Google Inc.
Ying Zhang Vogel Structured Language Models for Statistical Machine Translation Faculty, Carnegie Mellon Silicon Valley

2008

Graduate Advisor(s) Dissertation Employer Upon Graduation
Vitor R. Carvalho Cohen Modeling Intention in E-Mail Microsoft Live Labs
Ananlada Chotimongkol Rudnicky Learning the Structure of Task-Oriented Conversations from the Corpus of In-Domain Dialogs Assistant Researcher, NECTEC (Thailand)
Kevyn Collins-Thompson Callan Robust Model Estimation Methods for Information Retrieval Microsoft Corporation
Szu-Chen Stan Jou Schultz, Waibel Automatic Speech Recognition on Vibrocervigraphic and Electromyographic Signals
Wei-Hao Lin Hauptmann Identifying Ideological Perspectives in Text and Video Google Inc.
Yanjun Qi Bar-Joseph, Klein-Seetharaman Learning of Protein Interaction Networks NEC Laboratories America, Inc.
Antoine Raux Eskenazi Flexible Turn-Taking for Spoken Dialog Systems Honda Research Institute

2007

Graduate Advisor(s) Dissertation Employer Upon Graduation
Ulas Bardak Carbonell Information Eliciation in Scheduling Problems
Ariadna Font-Llitjos Carbonell Automatic Improvement of Machine Translation Systems Vivisimo, Inc.
Madhavi Ganapathiraju Klein-Seetharaman, Reddy Application of Language Technologies in Biology: Feature Extraction and Modeling for Transmembrane Helix Prediction Assistant Professor, Department of Biomedical Informatics, School of Medicine, University of Pittsburgh
Qin Jin Schultz, Waibel Robust Speaker Recognition Postdoc, CMU Language Technologies Institute
Jeongwoo Ko Nyberg Probabilistic Approaches for Answer Selection in Multilingual Question Answering Oracle Corporation
Fan Li Yang Structure Learning with Large Sparse Undirected Graphs and its Applications Yahoo Research
Jie Lu Callan Full-Text Federated Search in Peer-to-Peer Networks IBM Corporation
Stefanie Tomko Rosenfeld Improving User Interaction with Spoken Dialog Systems via Shaping Microsoft Corporation
Rong Zhang Rudnicky Making an Effective Use of Speech Data for Acoustic Modeling IBM Systems and Technology Group
Bing Zhao Waibel Statistical Alignment Models for Translational Equivalence IBM Thomas J. Watson Research Center

2006

Graduate Advisor(s) Dissertation Employer Upon Graduation
Fei Huang Waibel Multilingual Named Entity Extraction and Translation from Text and Speech IBM Thomas J. Watson Research Center
Chun Jin Carbonell Optimizing Multiple Continuous Queries
Yan Liu Carbonell Conditional Graphical Models for Protein Structure Prediction IBM Thomas J. Watson Research Center
Robert Malkin Waibel Machine Listening for Context-Aware Computing Google Inc.
Kenji Sagae Lavie A Multi-Strategy Approach for Parsing of Grammatical Relations in Transcripts of Parent-Child Dialogs Researcher, University of Tokyo
Luo Si Callan Federated Search of Text Search Engines in Uncooperative Environments Assistant Professor, Purdue University
Rong Yan Hauptmann Probabilistic Models for Combining Diverse Knowledge Sources in Multimedia Retrieval IBM Thomas J. Watson Research Center
Jian Zhang Yang A Probabilistic Framework for Multi-Task Learning Assistant Professor, Purdue University

2005

Graduate Advisor(s) Dissertation Employer Upon Graduation
Rosie Jones Mitchell Learning to Extract Entities from Labeled and Unlabeled Text Yahoo Inc.
Guy Lebanon Lafferty Riemannian Geometry and Statistical Machine Learning Assistant Professor, Purdue University
Octav Popescu Koedinger Logic-Based Natural Language Understanding in Intelligent Tutoring Systems Research Programmer, CMU Human-Computer Interaction Institute
Katharina Probst Lavie Learning Transfer Rules for Machine Translation with Limited Data Accenture
Yi Zhang Callan Bayesian Graphical Models for Adaptive Filtering Assistant Professor, University of California Santa Cruz
Xiaojin (Jerry) Zhu Lafferty, Rosenfeld Semi-Supervised Learning with Graphs Assistant Professor, University of Wisconsin

2004

Graduate Advisor(s) Dissertation Employer Upon Graduation
Hua Yu Waibel Recognizing Sloppy Speech Google Inc.

2003

Graduate Advisor(s) Dissertation Employer Upon Graduation
Rong Jin Hauptmann Statistical Approach toward Automatic Title Generation Assistant Professor, Michigan State University
Chad Langley Lavie Domain Acion Classification and Argument Parsing for Interlingua-Based Spoken Language Translation U.S. Government

2002

Graduate Advisor(s) Dissertation Employer Upon Graduation
Kathy Baker Carpenter, Mitamura Guarded Constraints in Natural Language Processing U.S. Government
Paul Placeway Nyberg High-Performance Multi-Pass Unification Parsing Google Inc.
ChengXiang Zhai Lafferty Risk Minimization and Language Modeling in Text Retrieval Assistant Professor, University of Illinois Urbana-Champaign

2001

Graduate Advisor(s) Dissertation Employer Upon Graduation
Yan Qu Carbonell, Green A Constraint-Based Model of Mixed-Initiative Dialogue for Information-Seeking Interactions Clairvoyance
Laura Tomokiyo Waibel Recognizing Non-Native Speech: Characterizing and Adapting to Non-Native Usage in Speech Recognition Cepstral
Klaus Zechner Waibel Automatic Summarization of Spoken Dialogues in Unrestricted Domains Educational Testing Service

2000

Graduate Advisor(s) Dissertation Employer Upon Graduation
Gregory Aist Mostow Helping Children Learn Vocabulary During Computer-Assisted Oral Reading
Marsal Gavalda Waibel Growing Semantic Grammars Dictaphone
Gerald Penn Carpenter The Algebraic Structure of Attributed Type Signatures Associate Professor, University of Toronto
Akira Ushioda Carbonell, Lafferty Word and Compound Clustering for Natural Language Processing Fujitsu

1999

Graduate Advisor(s) Dissertation Employer Upon Graduation
Thomas Polzin Waibel Detecting Verbal and Non-verbal Cues in the Communication of Emotions ISI (Speech Company)

1998

Graduate Advisor(s) Dissertation Employer Upon Graduation
Ye Yi Wang Waibel Grammar Inference and Statistical Machine Translation Microsoft Corporation

1997

Graduate Advisor(s) Dissertation Employer Upon Graduation
Stephen Beale Nirenburg Hunter-Gatherer: Applying Constraint Satisfaction, Branch-and-Bound and Solution Synthesis to Computational Semantics Faculty, New Mexico State University
Boyan Onyshkevych Nirenburg An Ontological-Semantic Framework for Text Analysis U.S. Government
Carolyn Rosé Levin Robust Interactive Dialogue Interpretation Faculty, LTI CMU