Student seminar

From CLSP Wiki
(Redirected from Student Seminar)
Jump to: navigation, search

Also see the external speaker schedule.

CLSP student seminar presentations are recorded and archived on the CLSP grid under: /export/a08/clsp-seminar-videos/internal/

See the Student seminar committee page for information about managing the CLSP student seminar.

Fall 2017

Date Speaker Title
Sep 1 (Fri) Lucas Ondel (Visiting Student) Structured Variational AutoEncoder for Phone Recognition and Discovery
Sep 5 (Tue) Chandler May Ethics in artificial intelligence (in context)
Sep 12 (Tue) Vimal Manohar Lightly supervised transcriptions for ASR
Sep 15 (Fri) Tim Veira Learning to be Fast and Accurate
Sep 19 (Tue) Pegah Ghahremani Investigation of transfer learning for ASR using LF-MMI trained neural networks
Oct 6 (Fri) Laureano Moro-Velázquez Detection and assessment of pathologies using speech processing
Oct 24 (Tue) Katharina Kann (visitor)
Oct 27 (Fri) Rachel Rudinger
Nov 3 (Fri)) Katie Henry
Nov 17 (Fri) Huda Khayrallah
Nov 28 (Tue) Adrian Benton
Dec 1 (Fri) TBA
Dec 8 (Fri) Adam Teichert

Spring 2017

Date Speaker Title
Feb. 7, Tuesday Jonathan Jones Building a model of block construction
Feb. 17, Friday Hainan Xu Zipporah, an automatic data cleaning system for noisy web-crawled parallel corpus
Feb 24, Friday Keisuke Sakaguchi Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network (followed by CLSP overview talk for the visiting CS grad students)
Feb 28, Tuesday Courtney Napoles Identifying Good Conversations Online (Yes, they do exist!)
Mar. 07, Tuesday Peter Schlulam Disease Trajectory Maps
Mar. 14, Tuesday No student seminar (University closed due to snow day)
Apr. 04, Tuesday Xiaohui Zhang Acoustic data-driven lexicon learning for ASR
Apr. 11, Tuesday Gaurav Kumar Beyond Beam Search for Decoding Sequences with Recurrent Neural Architectures
Apr. 21 Friday Dr. Jesús Villalba (Post Doc) Bayesian Models for Speaker Recognition
Apr. 25, Tuesday No student seminar Replaced by external speaker seminar (Dr. Yishay Carmiel)
May. 02, Tuesday Frank Ferraro Visual Storytelling: Events in Image Sequences

Fall 2016

Date Speaker Title
Sep. 6, Tuesday Debmalya Chakrabarty Temporal Trajectories for Acoustic Event Identification
Sep. 16, Friday Ryan Cotterell Modeling Word Forms Using Latent Underlying Morphs and Phonology
Sep. 23, Friday David Snyder Deep Neural Network-based Speaker Embeddings for End-to-End Speaker Verification
Sep. 27, Tuesday Rebecca Knowles Analyzing Learner Understanding of Novel L2 Vocabulary
Oct. 4, Tuesday Dingquan Wang The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New Languages
Oct. 11, Tuesday No Student Seminar Student seminar replaced with external speaker seminar (Dr. Hendrik Kayser)
Oct. 25, Tuesday Tongfei Chen Discriminative Information Retrieval for Knowledge Discovery
Oct. 28, Friday Matthew Maciejewski Ivector Tutorial
Nov. 1, Tuesday Ruizhi Li Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition
Nov. 11 Matthew Weisner Graphemic Lexicons in Automatic Speech Recognition
Nov. 15, Tuesday Shuoyang Ding JHU Machine Translation Systems for WMT 2016
Nov. 29, Tuesday No Student Seminar Student seminar replaced with external speaker seminar ( Dr. Jonathan May )
Dec. 6, Tuesday Poorya Mianjy Stochastic Optimization for Multiview Representation Learning using Partial Least Squares

Spring 2016

Date Speaker Title
Jan. 29, Friday Pushpendre Rastogi Best of Both Worlds: Neural Encoding with Structural Decoding
Feb. 5, Friday Roy Schwartz (Hebrew University of Jerusalem) Pattern-based Solutions to Limitations of Leading Word Embeddings
Feb. 12, Friday Adam Teichert An Adventure in Learning to Prioritize Message Passing
Feb. 19, Friday No Seminar CLSP recruiting week
Feb. 26, Friday Vijayaditya Peddinti A $30,000 Improvement in Automatic Transcription of Reverberant Speech
Mar. 1, Tuesday Adrian Benton Learning Multiview Embeddings of Twitter Users
Mar. 8, Tuesday Sri Harish Mallidi Noise Robust Automatic Speech Recognition using Multistream framework
Mar. 18, Friday No Seminar Spring Break
Mar. 22, Friday No Seminar Canceled
Mar. 25, Friday Katharine Henry Acute event detection in the ICU with application to septic shock
Apr. 1, Friday Adi Renduchintala Learning to Read in a Foreign Language via Macaronic Texts
Apr. 5, Tuesday Chunxi Liu Context-Dependent Point Process Models for Keyword Search and Detection-Based ASR
Apr. 19, Tuesday Vijayaditya Peddinti Fast and accurate sequence recognition with neural networks
Apr. 22, Friday Keisuke Sakaguchi Reassessing the Goals of Grammatical Error Correction: Fluency Instead of Grammaticality
Apr. 26, Tuesday No Seminar Canceled

Fall 2015

Date Speaker Title
Sep. 4, Friday Hainan Xu Modeling Phonetic Context with Non-random Forests for Speech Recognition
Sep. 8, Tuesday Chandler May Identification and Discovery on Text and Speech
Sep. 18, Friday No Seminar WSE Picnic / EMNLP
Sep. 25, Friday Miguel Ballesteros (CMU) Greedy Transition-based Dependency Parsing with Global State-Stack LSTMs
Oct. 2, Friday Vimal Manohar Semi-supervised maximum mutual information training of deep neural networks
Oct. 9, Friday No Seminar Canceled
Oct. 16, Friday No Seminar Fall Break
Oct. 20, Tuesday Peter Schulam A Probabilistic Model for Individualizing Prognosis in Chronic, Complex Diseases
Oct. 30, Friday Aaron White (postdoctoral fellow) Semantic representation learning and linguistic theory
Nov. 6, Friday Rachel Rudinger Script Induction as Language Modeling
Nov. 13, Friday Eleanor Chodroff (cognitive science) Structured Variability in Stop Consonant Realization
Nov. 27, Friday No Seminar Thanksgiving Vacation
Dec. 1, Friday Karel Vesely (Brno University of Technology) Semi-supervised training of Deep Neural Networks: What can we get from the untranscribed data?

Spring 2015

Date Speaker Title
Feb. 3, Tuesday Darcey Riley Locally Renormalized PCFGs
Feb 13, Friday John Sylak-Glassman (postdoctoral fellow) Modeling Phonological Natural Classes in Optimality Theory Using Phonetics and Entailments
Feb 20, Friday No Seminar CLSP recruiting week
Feb 27, Friday No Seminar ACL (long) Due
Mar. 3, Tuesday Gaurav Kumar Machine Translation and Neural Networks
Mar. 10, Tuesday Francis Ferraro Probabilistic Models of Event Semantics
Mar. 17, Tuesday No Seminar Spring Break
Mar. 24, Tuesday Xiaohui Zhang A review of activation functions in feed-forward neural networks and an introduction to p-norm networks
Mar. 31, Tuesday Pegah Ghahremani Pitch and voicing features for Speech Recognition
Apr. 10, Friday Travis Wolfe Margin-based Methods for Structured Prediction
Apr. 14, Tuesday Tim Vieira Learning to Prune: Pushing the Frontier of Fast and Accurate Parsing
Apr. 24, Friday Emine Merve Kaya Bottom-up auditory attention in the cortex
May. 1, Friday Nanyun Peng Dual Decomposition Inference for Graphical Models over Strings

Fall 2014

Date Speaker Title
Sept. 2, Tuesday Guoguo Chen MyHotword: A prototype for user specified hotword
Sept. 9, Tuesday Chunxi Liu A Unified Modeling Framework for for Multi-turn Multi-task Spoken Language Understanding Based on Recurrent Convolutional Neural Networks
Sept. 12, Friday Matt Gormley Low-Resource Semantic Role Labeling
Sept. 19, Friday No Seminar WSE Picnic
Sept. 23, Tuesday Courtney Napoles NLP and Student Writing
Sept. 30, Tuesday Jonathan Wintrode Combining Local and Broad Topic Information to Improve Speech Retrieval
Oct. 10, Friday Svitlana Volkova Language, Demographics and Emotions in Social Media
Oct. 17, Friday No Seminar Fall Break
Oct. 24, Friday Yuan Cao Geometrically Motivated Online Learning
Nov 4, Tuesday Nathaniel Filardo
Nov 11, Tuesday Nicholas Andrews Non-Markov Word Segmentation via Particle MCMC
Nov 21, Friday Keith Levin Low-Resource Fixed-Dimensional Embeddings of Variable-Length Speech Audio Segments
Nov 28, Friday No Seminar Thanksgiving Break
Dec 5, Friday Sri Harish Mallidi AutoEncoder based stream selection technique: towards robust speech recognition

Spring 2014

Date Speaker Title
Jan, 31, Friday Scott Novotney Incorporating Weak Statistics to Improve Semi-Supervised Language Modeling
Feb, 4, Tuesday Jonathan Weese Classifying errors in synchronous parsing
Feb 14, Friday No Seminar SNOW DAY
Feb 21, Friday CLSP recruiting week
Feb 28, Friday Shuai Huang Manifold learning using Integrated Sensing and Processing Decision Trees
Mar 7, Friday Adam Teichart Loss-informed Dynamic Schedules via Adjoint-Belief Propagation
Mar 14, Friday Michael Paul Multi-factored models of text
Mar 28, Friday Keith Kintzley Phonetic Event-Based Whole-Word Modeling Approaches For Speech Recognition
Apr 1, Tuesday Dan Mendat MCMC Sampling on Brain-inspired, Energy-aware Hardware
Apr 11, Friday No Seminar ECE Faculty Candidate Seminar: Annalisa Scacchioli [1]
Apr 18, Friday Thomas Murray How do we incorporate physical constraints in models for statistical inference?
Apr 22, Tuesday Micheal Carlin Modeling attention-driven plasticity in auditory cortical receptive fields

Fall 2013

Date Speaker Title
Sept. 3, Tuesday Travis Wolfe PARMA: A Predicate Argument Aligner
Sept. 6, Friday Vijayaditya Peddinti DNN modeling of Deep Scatter Spectrum
Sept. 17, Tuesday Tim Vieira Learning Speed-Accuracy Tradeoffs for Parsing
Sept. 27, Friday Frank Ferraro Generalizing Event Descriptions: Probabilistic Template Induction
Oct. 4, Friday Dimitra Emmanouilidou Computerized lung sound analysis on pediatric auscultation in resource-poor settings
Oct. 18, Friday Scott Novotney Incorporating Weak Signals for Semi-Supervised Language Modeling
Oct. 25, Friday Ann Irvine Techniques for analyzing the effect of porting a machine translation system
Oct. 29, Tuesday Oguz Yilmaz Using proxies for OOV keywords in the keyword search task
Nov. 8, Friday Xuchen Yao Discriminative Models for Monolingual Alignment
Nov. 15, Friday Liang Huang [2] Scalable Training for Machine Translation Made Successful for the First Time (Special seminar by external speaker)
Nov. 22, Friday Emine Merve Kaya Computationally modeling auditory attention
Nov. 26, Tuesday Sri Harish Mallidi Robust Speaker Recognition Using Spectro-Temporal Autoregressive Models
Dec. 3, Friday Ehsan Variani DNNs for a small footprint text-dependent speaker verification

Spring 2013

Date Speaker Title
Feb 1, Friday Jeff Adams (Amazon.com) Speech & NLP at Amazon — Unique Challenges, Unique Resources
Feb 8, Friday Prospective Students Welcome
Feb 12, Tuesday Daniel Mendat Brain-inspired, Energy-aware Computing Architectures for Human Language Technology
Feb 19, Tuesday Tomas Figliolia Representation of Temporal Coherence: CHAINS algorithm and FPGA implementation
Feb 26, Tuesday Guoguo Chen The Babel Program: Keyword search on speech corpus
Mar 29, Friday Svitlana Volkova Lightly Supervised Learning of Procedural Dialog Systems
Apr 2, Tuesday Matt Gormley Nonconvex Global Optimization for Grammar Induction
Apr 12, Friday Yuan Cao Structured Winnow and M-MIRA: Multiplicative Updating Structured Predictors
Apr 16, Tuesday Nathaniel Filardo A Brief Introduction to Figaro
Apr 23, Tuesday Nicholas Andrews Phylogenetic Inference for Language
Apr 30, Tuesday Juri Ganitkevitch Large-Scale Paraphrasing and Natural Language Inference
May 3, Friday Meg Mitchell Generating Visible Object Descriptions

Fall 2012

Date Speaker Title
Sept 7 Samuel Thomas Data-driven Posterior Features for Low Resource Speech Recognition Applications / Acoustic and Data-driven Features for Robust Speech Activity Detection
Sept 18 Xuchen Yao Answer Extraction with A Tree Edit Distance Assisted Sequence Tagger
Sept 21 Jason Smith Web-Scale Parallel Sentence Mining with Hadoop
Sept 25 Puyang Xu Compact representations of discriminatively trained language models
Oct 5 Jonathan Clark (CMU) Locally Non-Linear Learning via Feature Induction in Statistical Machine Translation
Oct 12 Jan Trmal Exploiting the feature vectors structure for,speaker adaptive training of neural networks
Oct 19 Jonathan Weese Using Categorial Grammar to Label Translation Rules
Oct 26 Ming Sun Data Fusion via Manifold Matching
Nov 2 Shuai Huang Constrained Maximum Mutual Information dimensionality reduction
Nov 9 Adam Teichert Learning Time-Sensitive Structured Prediction
Nov 16 Michael Paul Inference with Dual Decomposition and an Application to Optimal Sequence Finding
Nov 30 Keith Kintzley MAP Estimation of Whole-Word Acoustic Models with Dictionary Priors
Dec 4 Tom Murray Design of a Parallel Sampling Encoder for Signal to Information Converters

Spring 2012

Date Speaker Title
Feb 3 Juri Ganitkevitch Learning Sentential Paraphrases from Bilingual Parallel Corpora for Text-to-Text Generation
Feb 10 Ann Irvine Toward Statistical Machine Translation without Parallel Corpora
Feb 14 Courtney Napoles Generating and Evaluating Sentence Compressions
Feb 24 CLSP Faculty CLSP Overview for Prospective Graduate Students
Feb 28 Scott Novotney Semi-supervised Language Modeling for Keyword Search
Mar 9 E. Merve Kaya Modeling Auditory Saliency
Mar 16 Wes Filardo Flexible Solvers for Arithmetic Circuits
Apr 3 Michael Carlin @4:30PM Speech Enhancement Using Sparse Convolutive NMF with Basis Adaptation
Apr 10 N. Sridhar Krishna Robust Speech Processing by Humans and Machines: The Role of Spectro-Temporal Modulations
Apr 20 Jackie Lee (MIT Student) A Nonparametric Bayesian Approach to Acoustic Model Discovery
Apr 27 Kailash Patil Goal-Oriented Auditory Scene Recognition
May 4 Ehsan Variani Estimating classifier performance in unknown noise

Fall 2011

Date Speaker Title
Sep 9 Balakrishnan V. Beyond HMMs: Modeling Dexterous Motion using Switching Linear Dynamical Systems
Sep 13 Svitlana Volkova Collecting a Large Set of Grounded Natural Language Descriptions
Sep 23 HLTCOE Mid-Atlantic Student Colloquium on Speech, Language and Learning @ the Stieff Building
Sep 27 Dipanjan Das (CMU Student) Multilingual Learning for POS Tagging and Grammar Induction
Oct 7 Andreas G. Andreou Sound, Sight and the Language of Actions: The Telluride CogRobot Project
Oct 18 Ariya Rastrow Going beyond n-grams via Hill Climbing on Speech Lattices
Oct 21 Charley Chan Reranking Bilingually Extracted Paraphrases Using Monolingual Distributional Similarity
Oct 28 Matt Gormley Shared Components Topic Models with Application to Selectional Preference
Nov 4 Yuan Cao Semi-supervised Discriminative LM Training in Machine Translation
Nov 8 Feipeng Li (New Postdoc) What Causes the Confusion Patterns in Speech Perception?
Nov 18 Nicholas Andrews Transformation Process Priors
Nov 29 Keith Kintzley Event Selection from Phone Posteriorgrams Using Matched Filters

Spring 2011

Date Speaker Title
February 4 Michael Bloodgood Stopping Active Learning based on Stabilizing Predictions
February 11 Nash Borges Coping with Training Contamination in Acoustic Anomaly Detection
February 18 Jonathan Weese Thrax: a fast and flexible grammar extractor for machine translation
February 25 Samuel Thomas Phoneme Recognition Using Auditory Spectro-Temporal Receptive Fields
March 4 Recruiting Weekend n/a
March 11 Sriram Ganapathy Feature Normalization for Speaker Verification In Room Reverberation
March 15 Sivaram Garimella Sparse Multilayer Perceptron for Phoneme Recognition
March 25 Spring Break n/a
April 1 Carolina Parada Towards an Open Vocabulary Speech Recognition System
April 8 Michael Wolmetz (Postdoc Candidate) Neural representations of spoken words: Testing the neural predictions of theories of human spoken word recognition using supervised learning methods
April 15 Ming Sun Improved POS Tagging for Text-to-Speech Synthesis
April 22 Jason Smith Unsupervised Learning on an Approximate Corpus
April 29 Byung Gyu Ahn WikiTopics: What is popular on Wikipedia and why
May 6 Alex Klementiev (Departing Postdoc) Toward Statistical Machine Translation without Parallel Corpora
June 14 Michael Auli (Edinburgh Student) Integrated CCG Parsing and Supertagging

Fall 2010

Date Speaker Title
September 10 Brian Kjersten Arabic OCR Evaluation in Order to Develop a post-OCR Module
September 17 Sridhar Nemala Modulation Transfer Function (MTF) based features for robust speech recognition
September 24 Puyang Xu Modeling Event Streams
October 1 Brian Roark Open vocabulary language modeling for binary switch typing interfaces
October 8 Michael Paul Summarizing Contrastive Viewpoints in Opinionated Text
October 15 Wes Filardo Dyna: Weighted Logic Programming for Statistical AI
October 22 Anoop Deoras Variational Approximation of Long-Span Language Models for LVCSR
October 29 Kailash Patil Robust Recognition of the message and the messenger in Speech
November 5 No Seminar (FJ Memorial Service)
November 12 Michael Carlin Exploring the relationship between temporal coherence in natural sounds and coding strategies in the auditory system
November 19 Omar F. Zaidan Creating Machine Translation Datasets for Low-Resource Languages Using Non-Professional, Non-Fluent Translators
November 26 No Seminar (Thanksgiving Vacation)
December 3 Balakrishnan V Learning and Inference Algorithms for Partially Observed Structured Switching Vector Autoregressive Models

Spring 2010

Date Speaker Title
January 29 Veselin Stoyanov Reconcile: A Coreference Resolution Research Platform
February 5 Markus Dreyer Finite-state Graphical Models over Multiple Strings
February 12 Canceled due to weather
February 19 Tomas Mikolov Neural network based language models
February 26 Jason Smith Extracting Parallel Sentences from Comparable Corpora using Document Level Alignment
March 5 Canceled due to recruiting weekend
March 12 Sharon Goldwater From sounds to words: Bayesian modeling of early language acquisition
March 19 Spring Vacation (No seminar)
March 26 Anoop Deoras Language Model Adaptation using Random Forests
April 2 Scott Novotney Cheap, Fast and Good Enough: Speech Transcription with Mechanical Turk
April 9 Delip Rao Learning with Large-scale graphs
April 16 ByungGyu Ahn Chart Pruning using Beam Search in a Wide-coverage CCG Parser
April 23 Ann Irvine Transliterating Between All Languages
April 30 Ariya Rastrow Map decoding and Rescoring of Speech Lattices via Gibbs Sampling
May 7 Nima Mesgarani Selective Encoding of Phonemes in the Primary Auditory Cortex: Alternative Ways of Looking at Speech

Fall 2009

Date Speaker Title
September 11 Ming Sun Correcting English Spelling Errors
September 18 Mark Dredze Overview of COE research
September 25 Seminar Canceled (WSE picnic)
October 2 Ziyuan Wang N-best re-ranking for Machine Translation
October 9 Andrew Cassidy ASR Engines
October 16 Puyang Xu Self-supervised discriminative training of statistical language models
October 23 Abby Levenberg Stream-based Randomized LMs for SMT
October 30 Omar F. Zaidan Feasibility of Human-in-the-loop Minimum Error Rate Training
November 6 Dr. Ashish Verma Analytics for Contact Centers
November 13 Jenny Finkel Holistic Language Processing: Joint Models of Linguistic Structure
November 20 Rui Wang Recognizing textual entailment - A shortcut or a detour for logic inference
November 27 (Thanksgiving holiday, no seminar)
December 4 Haolang Zhou Semi-supervised Learning Extension to Heteroscedastic Linear Discriminant Analysis

Spring 2009

Date Speaker Title
January 30 Yi Su Boosting Ranking Models for Web Search
February 6 Juri Ganitkevitch Triplet Lexicon Models for Statistical Machine Translation
February 13 Jordan Boyd-Graber Syntactic Topic Models
February 20 Ariya Rastrow Discriminative Training of Language Models
February 27 Zhifei Li Variational Decoding for Statistical Machine Translation
March 6 (No Seminar, Recruiting Weekend)
March 13 Balakrishnan V Active and Semi-supervised Learning for Speech Recognition
March 20 (No Seminar, Spring Vacation)
March 27 Nikesh Garera Structural, Transitive and Latent Models for Biographic Fact Extraction
April 3 Sivaram Garimella Exploiting Spectral Sparsity of Speech to Enhance Noise Power Spectrum Estimate for ASR
April 10 Carolina Parada Modeling Spoken URLs for Google Search by Voice
April 17 Jason Smith Novel System Combination Techniques for Machine Translation
April 24 Sriram Ganapathy Signal Analysis Using Frequency Domain Perceptual Linear Prediction (FDPLP)
May 1 Samuel Thomas Recognition Of Reverberant Speech Using Frequency Domain Perceptual Linear Prediction (FDPLP)

Fall 2008

Date Speaker Title
September 5 Markus Dreyer Latent-Variable Modeling Of String Transductions
September 12 Arnab Goshal Web Derived Pronunciation
September 19 Malcom Slaney (from Yahoo!) Top-Down Auditory Processing and Why Yahoo Cares
September 26 Andrew Cassidy Production Models of Speech: Glottal Excitation Function
October 3 Satoshi Sekine On-Demand Information Extraction, Ngram Search Engine and Web People Search
October 10 Zhifei Li Large-scale Discriminative n-gram Language Models for Statistical Machine Translation
October 17 Omar F. Zaidan Modeling Annotators: A Generative Approach to Learning from Annotator Rationales
October 24 Haolang Zhou Semi-tied Covariance versus HLDA for speech recognition
October 31 Balakrishnan V Structure Induction of a random process.
November 7 Erin Fitzgerald Reconstructing false start errors in spontaneous speech text
November 14 Micha Jellinghaus The Best of Two Worlds – Combining Rule-Based and Statistical
November 21 Michael Subotin Generalizing Local Translation Models
November 28 Thanksgiving (No Seminar)
December 5 Ariya Rastrow New Method for OOV detection using Hybrid Word/Fragment System

Spring 2008

Date Speaker Title
February 8 Balakrishnan V. Quick f-MLLR for speaker adaptation
February 15 Marco Kuhlmann Dependency Structures and Lexicalized Grammars
February 22 Zhifei Li Optimal Dialog in Consumer-Rating Systems using a POMDP Framework
February 29 Moving to new building(no speaker)
March 7 Recruitment Weekend (no speaker)
March 14 No Speaker(Seminar canceled)
March 21 Spring Break(No Student Seminar)
March 28 David Smith Probabilistic Models of Nonprojective Dependency Trees
April 4 No Speaker(Seminar canceled)
April 11 Yi Su Exploiting Prosodic Breaks in Language Modeling with Random Forests
April 18 Anoop Deoras Decoding-Time Prediction of Non-Verbalized Punctuation
April 25 No Speaker(Seminar canceled)
May 2 Nikesh Garera Translation Lexicon Induction for Compound Words using Component Gloss Translation Models via Multiple Languages
May 9 Exam Period (no speaker)
May 16 Exam Period (no speaker)