Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT EMNLP

Shijie Wu | Mark Dredze |

Mental Health Surveillance over Social Media with Digital Cohorts NAACL WS

Silvio Amir | Mark Dredze | John W. Ayers |

Challenges of Using Text Classifiers for Causal Inference EMNLP

Zach Wood-Doughty | Ilya Shpitser | Mark Dredze |

Deep Dirichlet Multinomial Regression NAACL

Adrian Benton | Mark Dredze |

Johns Hopkins or johnny-hopkins: Classifying Individuals versus Organizations on Twitter NAACL PEOPLES WS

Zach Wood-Doughty | Praateek Mahajan | Mark Dredze |

Predicting Twitter User Demographics from Names Alone NAACL PEOPLES WS

Zach Wood-Doughty | Nicholas Andrews | Rebecca Marvin | Mark Dredze |

Using Author Embeddings to Improve Tweet Stance Classification EMNLP WS

Adrian Benton | Mark Dredze |

Convolutions Are All You Need (For Classifying Character Sequences) EMNLP WS

Zach Wood-Doughty | Nicholas Andrews | Mark Dredze |

CADET: Computer Assisted Discovery Extraction and Translation IJCNLP

Benjamin Van Durme | Tom Lippincott | Kevin Duh | Deana Burchfield | Adam Poliak | Cash Costello | Tim Finin | Scott Miller | James Mayfield | Philipp Koehn | Craig Harman | Dawn Lawrie | Chandler May | Max Thomas | Annabelle Carrell | Julianne Chaloux | Tongfei Chen | Alex Comerford | Mark Dredze | Benjamin Glass | Shudong Hao | Patrick Martin | Pushpendre Rastogi | Rashmi Sankepally | Travis Wolfe | Ying-Ying Tran | Ted Zhang |

Bayesian Modeling of Lexical Resources for Low-Resource Settings ACL

Nicholas Andrews | Mark Dredze | Benjamin Van Durme | Jason Eisner |

Pocket Knowledge Base Population ACL

Travis Wolfe | Mark Dredze | Benjamin Van Durme |

Proceedings of ACL 2017, Student Research Workshop ACL

Allyson Ettinger | Spandana Gella | Matthieu Labeau | Cecilia Ovesdotter Alm | Marine Carpuat | Mark Dredze |

Ethical Research Protocols for Social Media Health Research EthNLP WS

Adrian Benton | Glen Coppersmith | Mark Dredze |

Multi-task Domain Adaptation for Sequence Tagging Rep4NLP WS

Nanyun Peng | Mark Dredze |

How Does Twitter User Behavior Vary Across Demographic Groups? NLP+CSS WS

Zach Wood-Doughty | Michael Smith | David Broniatowski | Mark Dredze |

Constructing an Alias List for Named Entities during an Event WNUT WS

Anietie Andy | Mark Dredze | Mugizi Rwebangira | Chris Callison-Burch |

Embedding Lexical Features via Low-Rank Tensors NAACL

Mo Yu | Mark Dredze | Raman Arora | Matthew R. Gormley |

Geolocation for Twitter: Timing Matters NAACL

Mark Dredze | Miles Osborne | Prabhanjan Kambadur |

Learning Multiview Embeddings of Twitter Users ACL

Adrian Benton | Raman Arora | Mark Dredze |

Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning ACL

Nanyun Peng | Mark Dredze |

Knowledge Base Population for Organization Mentions in Email WS

Ning Gao | Mark Dredze | Douglas Oard |

Name Variation in Community Question Answering Systems WNUT WS

Anietie Andy | Satoshi Sekine | Mugizi Rwebangira | Mark Dredze |

Demographer: Extremely Simple Name Demographics NLP+CSS WS

Rebecca Knowles | Josh Carroll | Mark Dredze |

A Study of Imitation Learning Methods for Semantic Role Labeling WS

Travis Wolfe | Mark Dredze | Benjamin Van Durme |

Twitter at the Grammys: A Social Media Corpus for Entity Linking and Disambiguation SocialNLP WS

Mark Dredze | Nicholas Andrews | Jay DeYoung |

Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings EMNLP

Nanyun Peng | Mark Dredze |

Improved Relation Extraction with Feature-Rich Compositional Embedding Models EMNLP

Matthew R. Gormley | Mo Yu | Mark Dredze |

Predicate Argument Alignment using a Global Coherence Model NAACL

Travis Wolfe | Mark Dredze | Benjamin Van Durme |

Entity Linking for Spoken Language NAACL

Adrian Benton | Mark Dredze |

Combining Word Embeddings and Feature Embeddings for Fine-grained Relation Extraction NAACL

Mo Yu | Matthew R. Gormley | Mark Dredze |

A Concrete Chinese NLP Pipeline NAACL

Nanyun Peng | Francis Ferraro | Mo Yu | Nicholas Andrews | Jay DeYoung | Max Thomas | Matthew R. Gormley | Travis Wolfe | Craig Harman | Benjamin Van Durme | Mark Dredze |

An Empirical Study of Chinese Name Matching and Applications ACL IJCNLP

Nanyun Peng | Mo Yu | Mark Dredze |

FrameNet+: Fast Paraphrastic Tripling of FrameNet ACL IJCNLP

Ellie Pavlick | Travis Wolfe | Pushpendre Rastogi | Chris Callison-Burch | Mark Dredze | Benjamin Van Durme |

Sprite: Generalizing Topic Models with Structured Priors TACL

Michael J. Paul | Mark Dredze |

Learning Composition Models for Phrase Embeddings TACL

Mo Yu | Mark Dredze |

Approximation-Aware Dependency Parsing by Belief Propagation TACL

Matthew R. Gormley | Mark Dredze | Jason Eisner |

From ADHD to SAD: Analyzing the Language of Mental Health on Twitter through Self-Reported Diagnoses CLPsych WS

Glen Coppersmith | Mark Dredze | Craig Harman | Kristy Hollingshead |

CLPsych 2015 Shared Task: Depression and PTSD on Twitter CLPsych WS

Glen Coppersmith | Mark Dredze | Craig Harman | Kristy Hollingshead | Margaret Mitchell |

Robust Entity Clustering via Phylogenetic Inference ACL

Nicholas Andrews | Jason Eisner | Mark Dredze |

Low-Resource Semantic Role Labeling ACL

Matthew R. Gormley | Margaret Mitchell | Benjamin Van Durme | Mark Dredze |

Improving Lexical Embeddings with Semantic Knowledge ACL

Mo Yu | Mark Dredze |

Learning Polylingual Topic Models from Code-Switched Social Media Documents ACL

Nanyun Peng | Yiming Wang | Mark Dredze |

Quantifying Mental Health Signals in Twitter WS

Glen Coppersmith | Mark Dredze | Craig Harman |

Drug Extraction from the Web: Summarizing Drug Experiences with Multi-Dimensional Topic Models NAACL

Michael J. Paul | Mark Dredze |

What’s in a Domain? Multi-Domain Learning for Multi-Attribute Data NAACL

Mahesh Joshi | Mark Dredze | William W. Cohen | Carolyn P. Rosé |

Separating Fact from Fear: Tracking Flu Infections on Twitter NAACL

Alex Lamb | Michael J. Paul | Mark Dredze |

Broadly Improving User Classification via Communication-Based Name and Location Clustering on Twitter NAACL

Shane Bergsma | Mark Dredze | Benjamin Van Durme | Theresa Wilson | David Yarowsky |

Topic Models and Metadata for Visualizing Text Corpora NAACL

Justin Snyder | Rebecca Knowles | Mark Dredze | Matthew Gormley | Travis Wolfe |

PARMA: A Predicate Argument Aligner ACL

Travis Wolfe | Benjamin Van Durme | Mark Dredze | Nicholas Andrews | Charley Beller | Chris Callison-Burch | Jay DeYoung | Justin Snyder | Jonathan Weese | Tan Xu | Xuchen Yao |

Name Phylogeny: A Generative Model of String Variation CoNLL EMNLP

Nicholas Andrews | Jason Eisner | Mark Dredze |

Multi-Domain Learning: When Do Domains Matter? CoNLL EMNLP

Mahesh Joshi | Mark Dredze | William W. Cohen | Carolyn Rosé |

Entity Clustering Across Languages NAACL

Spence Green | Nicholas Andrews | Matthew R. Gormley | Mark Dredze | Christopher D. Manning |

Shared Components Topic Models NAACL

Matthew R. Gormley | Mark Dredze | Benjamin Van Durme | Jason Eisner |

Fast Syntactic Analysis for Statistical Language Modeling via Substructure Sharing and Uptraining ACL

Ariya Rastrow | Mark Dredze | Sanjeev Khudanpur |

Revisiting the Case for Explicit Syntactic Information in Language Models NAACL WS

Ariya Rastrow | Sanjeev Khudanpur | Mark Dredze |

Learning Sub-Word Units for Open Vocabulary Speech Recognition ACL

Carolina Parada | Mark Dredze | Abhinav Sethy | Ariya Rastrow |

Entity Disambiguation for Knowledge Base Population COLING

Mark Dredze | Paul McNamee | Delip Rao | Adam Gerber | Tim Finin |

Streaming Cross Document Entity Coreference Resolution COLING

Delip Rao | Paul McNamee | Mark Dredze |

NLP on Spoken Documents Without ASR EMNLP

Mark Dredze | Aren Jansen | Glen Coppersmith | Ken Church |

We’re Not in Kansas Anymore: Detecting Domain Changes in Streams EMNLP

Mark Dredze | Tim Oates | Christine Piatko |

Contextual Information Improves OOV Detection in Speech NAACL

Carolina Parada | Mark Dredze | Denis Filimonov | Frederick Jelinek |

Learning Simple Wikipedia: A Cogitation in Ascertaining Abecedarian Language WS

Courtney Napoles | Mark Dredze |

Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon’s Mechanical Turk WS

Chris Callison-Burch | Mark Dredze |

Creating Speech and Language Data With Amazon’s Mechanical Turk WS

Chris Callison-Burch | Mark Dredze |

Annotating Named Entities in Twitter Data with Crowdsourcing WS

Tim Finin | William Murnane | Anand Karandikar | Nicholas Keller | Justin Martineau | Mark Dredze |

Non-Expert Correction of Automatically Generated Relation Annotations WS

Matthew R. Gormley | Adam Gerber | Mary Harper | Mark Dredze |

Multi-Class Confidence Weighted Algorithms EMNLP

Koby Crammer | Mark Dredze | Alex Kulesza |

Reading the Markets: Forecasting Public Opinion of Political Candidates by News Analysis COLING

Kevin Lerman | Ari Gilder | Mark Dredze | Fernando Pereira |

Online Methods for Multi-Domain Learning and Adaptation EMNLP

Mark Dredze | Koby Crammer |

Icelandic Data Driven Part of Speech Tagging ACL

Mark Dredze | Joel Wallenberg |

Active Learning with Confidence ACL

Mark Dredze | Koby Crammer |

Small Statistical Models by Random Feature Mixing WS

Kuzman Ganchev | Mark Dredze |

Frustratingly Hard Domain Adaptation for Dependency Parsing CoNLL EMNLP

Mark Dredze | John Blitzer | Partha Pratim Talukdar | Kuzman Ganchev | João Graça | Fernando Pereira |

Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification ACL

John Blitzer | Mark Dredze | Fernando Pereira |

Automatic Code Assignment to Medical Text WS

Koby Crammer | Mark Dredze | Kuzman Ganchev | Partha Pratim Talukdar | Steven Carroll |