Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Ellie Pavlick

Ellie Pavlick

Does Vision-and-Language Pretraining Improve Lexical Grounding?


Sep 21, 2021
Tian Yun, Chen Sun, Ellie Pavlick

Figure 1 for Does Vision-and-Language Pretraining Improve Lexical Grounding?
Figure 2 for Does Vision-and-Language Pretraining Improve Lexical Grounding?
Figure 3 for Does Vision-and-Language Pretraining Improve Lexical Grounding?
Figure 4 for Does Vision-and-Language Pretraining Improve Lexical Grounding?
* Camera ready for Findings of EMNLP 2021 
  Access Paper or Ask Questions

Frequency Effects on Syntactic Rule Learning in Transformers


Sep 14, 2021
Jason Wei, Dan Garrette, Tal Linzen, Ellie Pavlick

Figure 1 for Frequency Effects on Syntactic Rule Learning in Transformers
Figure 2 for Frequency Effects on Syntactic Rule Learning in Transformers
Figure 3 for Frequency Effects on Syntactic Rule Learning in Transformers
Figure 4 for Frequency Effects on Syntactic Rule Learning in Transformers
* Camera ready for EMNLP 2021 
  Access Paper or Ask Questions

Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color


Sep 14, 2021
Mostafa Abdou, Artur Kulmizev, Daniel Hershcovich, Stella Frank, Ellie Pavlick, Anders Søgaard

Figure 1 for Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
Figure 2 for Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
Figure 3 for Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
Figure 4 for Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
* CoNLL 2021 
  Access Paper or Ask Questions

Do Prompt-Based Models Really Understand the Meaning of their Prompts?


Sep 02, 2021
Albert Webson, Ellie Pavlick

Figure 1 for Do Prompt-Based Models Really Understand the Meaning of their Prompts?
Figure 2 for Do Prompt-Based Models Really Understand the Meaning of their Prompts?
Figure 3 for Do Prompt-Based Models Really Understand the Meaning of their Prompts?
Figure 4 for Do Prompt-Based Models Really Understand the Meaning of their Prompts?
* Code available at https://github.com/awebson/prompt_semantics 
  Access Paper or Ask Questions

The MultiBERTs: BERT Reproductions for Robustness Analysis


Jun 30, 2021
Thibault Sellam, Steve Yadlowsky, Jason Wei, Naomi Saphra, Alexander D'Amour, Tal Linzen, Jasmijn Bastings, Iulia Turc, Jacob Eisenstein, Dipanjan Das, Ian Tenney, Ellie Pavlick

Figure 1 for The MultiBERTs: BERT Reproductions for Robustness Analysis
Figure 2 for The MultiBERTs: BERT Reproductions for Robustness Analysis
Figure 3 for The MultiBERTs: BERT Reproductions for Robustness Analysis
Figure 4 for The MultiBERTs: BERT Reproductions for Robustness Analysis
* Checkpoints and example analyses: http://goo.gle/multiberts 
  Access Paper or Ask Questions

Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering


Jan 02, 2021
Najoung Kim, Ellie Pavlick, Burcu Karagol Ayan, Deepak Ramachandran

Figure 1 for Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering
Figure 2 for Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering
Figure 3 for Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering
Figure 4 for Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering
* Preprint 
  Access Paper or Ask Questions

Spatial Language Understanding for Object Search in Partially Observed Cityscale Environments


Dec 04, 2020
Kaiyu Zheng, Deniz Bayazit, Rebecca Mathew, Ellie Pavlick, Stefanie Tellex

Figure 1 for Spatial Language Understanding for Object Search in Partially Observed Cityscale Environments
Figure 2 for Spatial Language Understanding for Object Search in Partially Observed Cityscale Environments
Figure 3 for Spatial Language Understanding for Object Search in Partially Observed Cityscale Environments
Figure 4 for Spatial Language Understanding for Object Search in Partially Observed Cityscale Environments
* 7 pages, 7 figures, 1 table. Preprint. Under review 
  Access Paper or Ask Questions

A Visuospatial Dataset for Naturalistic Verb Learning


Oct 28, 2020
Dylan Ebert, Ellie Pavlick

Figure 1 for A Visuospatial Dataset for Naturalistic Verb Learning
Figure 2 for A Visuospatial Dataset for Naturalistic Verb Learning
Figure 3 for A Visuospatial Dataset for Naturalistic Verb Learning
Figure 4 for A Visuospatial Dataset for Naturalistic Verb Learning
* 9 pages, 3 figures, starsem 2020 
  Access Paper or Ask Questions

Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces


Oct 25, 2020
Albert Webson, Zhizhong Chen, Carsten Eickhoff, Ellie Pavlick

Figure 1 for Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces
Figure 2 for Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces
Figure 3 for Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces
Figure 4 for Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces
* Published at EMNLP 2020. Recorded talk available at https://youtu.be/V2pdS6Y_8n0 . Code and data available at https://github.com/awebson/congressional_adversary 
  Access Paper or Ask Questions

Measuring and Reducing Gendered Correlations in Pre-trained Models


Oct 12, 2020
Kellie Webster, Xuezhi Wang, Ian Tenney, Alex Beutel, Emily Pitler, Ellie Pavlick, Jilin Chen, Slav Petrov

Figure 1 for Measuring and Reducing Gendered Correlations in Pre-trained Models
Figure 2 for Measuring and Reducing Gendered Correlations in Pre-trained Models
Figure 3 for Measuring and Reducing Gendered Correlations in Pre-trained Models
Figure 4 for Measuring and Reducing Gendered Correlations in Pre-trained Models

  Access Paper or Ask Questions

Self-play for Data Efficient Language Acquisition


Oct 10, 2020
Charles Lovering, Ellie Pavlick

Figure 1 for Self-play for Data Efficient Language Acquisition
Figure 2 for Self-play for Data Efficient Language Acquisition
Figure 3 for Self-play for Data Efficient Language Acquisition
Figure 4 for Self-play for Data Efficient Language Acquisition

  Access Paper or Ask Questions

Robot Object Retrieval with Contextual Natural Language Queries


Jun 23, 2020
Thao Nguyen, Nakul Gopalan, Roma Patel, Matt Corsaro, Ellie Pavlick, Stefanie Tellex

Figure 1 for Robot Object Retrieval with Contextual Natural Language Queries
Figure 2 for Robot Object Retrieval with Contextual Natural Language Queries
Figure 3 for Robot Object Retrieval with Contextual Natural Language Queries
Figure 4 for Robot Object Retrieval with Contextual Natural Language Queries

  Access Paper or Ask Questions

When does data augmentation help generalization in NLP?


Apr 30, 2020
Rohan Jha, Charles Lovering, Ellie Pavlick

Figure 1 for When does data augmentation help generalization in NLP?
Figure 2 for When does data augmentation help generalization in NLP?
Figure 3 for When does data augmentation help generalization in NLP?
Figure 4 for When does data augmentation help generalization in NLP?

  Access Paper or Ask Questions

What Happens To BERT Embeddings During Fine-tuning?


Apr 29, 2020
Amil Merchant, Elahe Rahimtoroghi, Ellie Pavlick, Ian Tenney

Figure 1 for What Happens To BERT Embeddings During Fine-tuning?
Figure 2 for What Happens To BERT Embeddings During Fine-tuning?
Figure 3 for What Happens To BERT Embeddings During Fine-tuning?
Figure 4 for What Happens To BERT Embeddings During Fine-tuning?
* 9 pages (not including references), 5 figures 
  Access Paper or Ask Questions

Planning with State Abstractions for Non-Markovian Task Specifications


May 28, 2019
Yoonseon Oh, Roma Patel, Thao Nguyen, Baichuan Huang, Ellie Pavlick, Stefanie Tellex

Figure 1 for Planning with State Abstractions for Non-Markovian Task Specifications
Figure 2 for Planning with State Abstractions for Non-Markovian Task Specifications
Figure 3 for Planning with State Abstractions for Non-Markovian Task Specifications
Figure 4 for Planning with State Abstractions for Non-Markovian Task Specifications

  Access Paper or Ask Questions

What do you learn from context? Probing for sentence structure in contextualized word representations


May 15, 2019
Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, R Thomas McCoy, Najoung Kim, Benjamin Van Durme, Samuel R. Bowman, Dipanjan Das, Ellie Pavlick

Figure 1 for What do you learn from context? Probing for sentence structure in contextualized word representations
Figure 2 for What do you learn from context? Probing for sentence structure in contextualized word representations
Figure 3 for What do you learn from context? Probing for sentence structure in contextualized word representations
Figure 4 for What do you learn from context? Probing for sentence structure in contextualized word representations
* ICLR 2019 camera-ready version, 17 pages including appendices 
  Access Paper or Ask Questions

BERT Rediscovers the Classical NLP Pipeline


May 15, 2019
Ian Tenney, Dipanjan Das, Ellie Pavlick

Figure 1 for BERT Rediscovers the Classical NLP Pipeline
Figure 2 for BERT Rediscovers the Classical NLP Pipeline
Figure 3 for BERT Rediscovers the Classical NLP Pipeline
Figure 4 for BERT Rediscovers the Classical NLP Pipeline
* Accepted to ACL 2019 
  Access Paper or Ask Questions

Probing What Different NLP Tasks Teach Machines about Function Word Comprehension


Apr 25, 2019
Najoung Kim, Roma Patel, Adam Poliak, Alex Wang, Patrick Xia, R. Thomas McCoy, Ian Tenney, Alexis Ross, Tal Linzen, Benjamin Van Durme, Samuel R. Bowman, Ellie Pavlick

Figure 1 for Probing What Different NLP Tasks Teach Machines about Function Word Comprehension
Figure 2 for Probing What Different NLP Tasks Teach Machines about Function Word Comprehension
Figure 3 for Probing What Different NLP Tasks Teach Machines about Function Word Comprehension
Figure 4 for Probing What Different NLP Tasks Teach Machines about Function Word Comprehension
* Accepted to *SEM 2019 
  Access Paper or Ask Questions

Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference


Feb 04, 2019
R. Thomas McCoy, Ellie Pavlick, Tal Linzen

Figure 1 for Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
Figure 2 for Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
Figure 3 for Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
Figure 4 for Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
* 8 pages plus references and appendices 
  Access Paper or Ask Questions

Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling


Dec 28, 2018
Samuel R. Bowman, Ellie Pavlick, Edouard Grave, Benjamin Van Durme, Alex Wang, Jan Hula, Patrick Xia, Raghavendra Pappagari, R. Thomas McCoy, Roma Patel, Najoung Kim, Ian Tenney, Yinghui Huang, Katherin Yu, Shuning Jin, Berlin Chen

Figure 1 for Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling
Figure 2 for Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling
Figure 3 for Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling
Figure 4 for Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling

  Access Paper or Ask Questions

Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation


Aug 29, 2018
Adam Poliak, Aparajita Haldar, Rachel Rudinger, J. Edward Hu, Ellie Pavlick, Aaron Steven White, Benjamin Van Durme

Figure 1 for Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation
Figure 2 for Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation
Figure 3 for Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation
Figure 4 for Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation
* To be presented at EMNLP 2018. 15 pages 
  Access Paper or Ask Questions

WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse


Aug 28, 2018
Manaal Faruqui, Ellie Pavlick, Ian Tenney, Dipanjan Das

Figure 1 for WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse
Figure 2 for WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse
Figure 3 for WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse
Figure 4 for WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse
* Proc. of EMNLP 2018 
  Access Paper or Ask Questions