5th Pacific Northwest Regional NLP Workshop: NW-NLP 2018

Call for Submissions and Participation

The fifth Pacific Northwest Regional Natural Language Processing Workshop will be held on Friday April 27 2018, in Redmond, WA. We welcome submissions of extended abstracts in all aspects of natural language text and speech processing, computational linguistics, and human language technologies.

As with past four workshops, the goal of this one-day NW-NLP event is to provide a less-formal setting in the Pacific Northwest to present research ideas, make new acquaintances, and learn about the breadth of exciting work currently being pursued in North-West area.

We encourage submissions of both completed and ongoing work. Accepted submissions will be presented as either an oral presentation or a poster. Students and less established researchers are especially encouraged to submit their work. This workshop will provide a venue for feedback on early-stage research.

Further information about the workshop is provided below. We look forward to your submissions and participation.


Ryan Georgi, Maryam Siahbani, General Co-chairs

Will Lewis, Local Chair

Important Dates

  • Friday, March 2: Submission deadline
  • Friday, March 9: Submission Deadline (Extended!)
  • Friday, March 23: Notification of acceptance
  • Friday, March 30: Notification of acceptance
  • Friday. April 6 : Camera­-ready extended abstracts due
  • Friday. April 20: Camera­-ready extended abstracts due
  • Friday, April 27: NW-NLP 2018 Workshop


Microsoft Research Redmond

14820 NE 36th Street

Redmond, WA 98052


Ben Taskar Invited Talk

Invited Speaker: Yejin Choi

Title: Learning and Reasoning about the World using Language


Understanding a narrative often requires reading between the lines, which in turn, requires rich background knowledge about how the world works. However, learning and reasoning about the obvious, but unspoken facts about the world is nontrivial, as people rarely state the obvious, e.g., "my house is bigger than me." In this talk, I will discuss how we can reverse engineer aspects of commonsense knowledge—ranging from Naive Physics type knowledge to more abstract social commonsense—from how people use language. I will then discuss neural network architectures that can provide structural priors to understand the latent process underlying a procedural text through (neural) simulation of action dynamics. I will conclude the talk by discussing the challenges in current models and formalisms, pointing to avenues for future research.


Yejin Choi is an associate professor of Paul G. Allen School of Computer Science & Engineering at the University of Washington and also a senior research manager at AI2. Her research interests include language grounding with vision, physical and social commonsense, language generation with long-term coherence, conversational AI, and AI for social good. She was among the IEEE’s AI Top 10 to Watch in 2015, a co-recipient of the Marr Prize at ICCV 2013, and a faculty advisor for the Sounding Board team that won the inaugural Alexa Prize Challenge in 2017. Her work on detecting deceptive reviews, predicting the literary success, and interpreting bias and connotation has been featured by numerous media outlets including NBC News for New York, NPR Radio, New York Times, and Bloomberg Business Week. She received her Ph.D. in Computer Science at Cornell University.

Welcome (9:00-10:00)

9:00 Gather (Coffee Break Food Available)

9:30 Introduction Blitz

Morning Talks (10:00-11:00)

10:00 Semantic Matching Against a Corpus: New Applications and Methods(Withheld by author request)

10:20 Synthetic and Natural Noise Both Break Neural Machine TranslationYonatan Belinkov and Yonatan Bisk.

10:40 Syntactic Scaffolds for Semantic Structures — (Withheld by author request)

Coffee Break (11:00-11:20)

Short Talks (11:20-12:20)

11:20 Compositional Language Modeling for Icon-Based Augmentative and Alternative CommunicationShiran Dudy and Steven Bedrick.

11:32 Keep your bearings: Lightly-supervised Information Extraction with Ladder Networks that avoids Semantic DriftAjay Nagesh and Mihai Surdeanu.

11:44 Infrequent Discourse Relation Identification Using Data ProgrammingXing Zeng, Giuseppe Carenini, Raymond Ng and Hyeju Jang.

11:56 Community Member Retrieval on Social Media using Textual Information Aaron Jaech, Shobhit Hathi and Mari Ostendorf.

12:08 Semantic similarity of conversational speech between children with and without ASDJoel Adams and Alexandra Salem.

Lunch (12:20-13:40)

Ben Taskar Invited Talk (13:40-14:30)

Yejin Choi: Learning and Reasoning about the World using Language

Afternoon Talks 1 (14:30-15:10)

14:30 Annotation Artifacts in Natural Language Inference Data Suchin Gururangan, Swabha Swayamdipta, Omer Levy, Roy Schwartz, Samuel Bowman and Noah Smith.

14:50 Simulating Action Dynamics with Neural Process NetworksAntoine Bosselut, Omer Levy, Ari Holtzman, Corin Ennis, Dieter Fox and Yejin Choi.

Coffee Break (15:10-15:30)

Poster Session (15:30-17:15)

Room A

  1. Lexicalized Reordering for Left-to-Right Hierarchical Phrase-based TranslationMaryam Siahbani and Anoop Sarkar.
  2. Simultaneous Translation using Optimized SegmentationMaryam Siahbani, Hassan S. Shavarani, Ashkan Alinejad and Anoop Sarkar.
  3. Joint Prediction of Word Alignment with Alignment TypesAnahita Mansouri Bigvand, Te Bu and Anoop Sarkar.
  4. GraphNER: Using Corpus Level Similarities and Graph Propagation for Named Entity RecognitionGolnar Sheikhshab, Elizabeth Stark, Aly Karsan, Anoop Sarkar and Inanc Birol.
  5. Analysis of Social Media Texts Concerning Climate Change and Sustainable DevelopmentLydia Odilinye, Fred Popowich, Bdour Alzeer, Brie Hoffman, Volodymyr Kozyr and Chelsea Li.
  6. Exploring Discourse Coherence Features for Dementia DetectionHyeju Jang, Vaden Masrani, Giuseppe Carenini, Raymond Ng, Gabriel Murray and Thalia Field.
  7. Partial Email Thread Summarization: Conversational Bayesian Surprise and Silver StandardsJordon Johnson, Vaden Masrani, Giuseppe Carenini and Raymond Ng.
  8. Mapping Distributional Semantics to Property Norms with Neural NetworksDandan Li and Douglas Summers-Stay.
  9. Extrapolative Models for Rich Text Generation — Withheld by author request

Room B

  1. The entrainment of creaky voice in spoken dialogueCourtney Mansfield.
  2. Forecasting the Future using Diverse Social Media SourcesKatherine Porterfield, Dustin Arendt, Nathan Hodas and Svitlana Volkova.
  3. Towards Anticipatory Analytics: Forecasting Instability Across Countries from Dynamic Knowledge GraphsSuraj Maharjan, Prasha Shrestha, Katherine Porterfield, Dustin Arendt and Svitlana Volkova.
  4. Forecasting Influenza-like Illness Dynamics for Military Populations Using Neural Networks and Social MediaEllyn Ayton, Katherine Poterfield, Svitlana Volkova and Court Corley.
  5. Serendipity in Book Passage Recommendation with Neural and LDA Topic ModelingJoshua Mathias.
  6. Multiple Document Representations from News Alerts for Automated Bio-surveillance Event DetectionAaron Tuor, Lauren Charles and Fnu Anubhav.
  7. Continuous Learning in a Hierarchical Multiscale Neural NetworkThomas Wolf, Julien Chaumond and Clement Delangue.
  8. E-MATCH – Event Matching by Analysis of Text CharacteristicsAnne Kao, Stephen Poteet, Lesley Quach, Rodney Tjoelker and David Augustine.
  9. Building Knowledge Bases for Precision Cancer MedicineJake Lever, Eric Y. Zhao, Jasleen Grewal, Luka Culibrk, Melika Bonakdar, Kilannin Krysiak, Arpad Danos, Obi Griffith, Malachi Griffith, Martin R. Jones and Steven J.M. Jones.

Afternoon Talks 2 (17:15-18:15)

17:15 Adverbial Clausal Modifiers in the LinGO Grammar MatrixKristen Howell and Olga Zamaraeva.

17:35 SimpleQuestions Nearly Solved: A New Upperbound and Baseline ApproachMichael Petrochuk and Luke Zettlemoyer.

17:55 Neural Relation Extraction Model with Selectively Incorporated Concept EmbeddingsYi Luan, Mari Ostendorf and Hannaneh Hajishirzi.

Closing Remarks (18:15)

Poster, Talk, and Camera-Ready Notes

  • The space for posters is 4.5' tall by 3.5' wide.
  • Long talks are 20 minutes (15 for presentation + 5 Q/A)
  • Short talks are 12 minutes (10 for presentation + 2 Q/A)
  • We will be as flexible as possible with camera-ready papers. Please ask if you have questions, but here are the general guidelines:
    • Extended abstracts: 2-page + refrences, please submit a final version, revised to reflect the reviewers' comments.
    • Already published papers: please send a link to the publication or your paper.

Submission and Reviewing Procedures

Submissions are now closed.

Program Committee

  • Ashkan Alinejad, Simon Fraser University
  • Sauleh Eetemadi, Microsoft Research
  • Christian Federmann, Microsoft Research
  • Michael Gamon, Microsoft Research
  • Ryan Georgi, University of Washington
  • Anne Kao, The Boeing Company.
  • Will Lewis, Microsoft Research
  • Gina-Anne Levow, University of Washington
  • Anahita Mansouri, Simon Fraser University
  • Arul Menezes, Microsoft Research
  • Christian Monson, Amazon Inc.
  • Gabriel Murray, University of Fraser Valley
  • Fred Popowich, Simon Fraser University
  • Chris Quirk, University of Washington
  • Brian Roark, Google Research
  • Masoud Rouhizadeh, Johns Hopkins University
  • Anoop Sarkar, Simon Fraser University
  • Maryam Siahbani, University of Fraser Valley
  • Noah Smith, University of Washington
  • Michael Tjalve, University of Washington
  • Luke Zettlemoyer, University of Washington

Previous NW-NLP Workshops