William Merrill

Publication Activity (10 Years)

Years Active: 2001-2024
Publications (10 Years): 46

Top Topics

Hierarchical Structure

Finite Automata

Expressive Power

Top Venues

Trans. Assoc. Comput. Linguistics

Publications

William Merrill, Zhaofeng Wu, Norihito Naka, Yoon Kim, Tal Linzen
Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment. ACL (Findings) (2024)
Dirk Groeneveld, Iz Beltagy, Pete Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Harsh Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, Shane Arora, David Atkinson, Russell Authur, Khyathi Raghavi Chandu, Arman Cohan, Jennifer Dumas, Yanai Elazar, Yuling Gu, Jack Hessel, Tushar Khot, William Merrill, Jacob Morrison, Niklas Muennighoff, Aakanksha Naik, Crystal Nam, Matthew E. Peters, Valentina Pyatkin, Abhilasha Ravichander, Dustin Schwenk, Saurabh Shah, Will Smith, Emma Strubell, Nishant Subramani, Mitchell Wortsman, Pradeep Dasigi, Nathan Lambert, Kyle Richardson, Luke Zettlemoyer, Jesse Dodge, Kyle Lo, Luca Soldaini, Noah A. Smith, Hannaneh Hajishirzi
OLMo: Accelerating the Science of Language Models. CoRR (2024)
Lena Strobl, William Merrill, Gail Weiss, David Chiang, Dana Angluin
What Formal Languages Can Transformers Express? A Survey. Trans. Assoc. Comput. Linguistics 12 (2024)
William Merrill, Zhaofeng Wu, Norihito Naka, Yoon Kim, Tal Linzen
Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment. CoRR (2024)
William Merrill, Jackson Petty, Ashish Sabharwal
The Illusion of State in State-Space Models. CoRR (2024)
William Merrill, Ashish Sabharwal
The Expressive Power of Transformers with Chain of Thought. ICLR (2024)
William Merrill, Noah A. Smith, Yanai Elazar
Evaluating n-Gram Novelty of Language Models Using Rusty-DAWG. CoRR (2024)
Jacob Pfau, William Merrill, Samuel R. Bowman
Let's Think Dot by Dot: Hidden Computation in Transformer Language Models. CoRR (2024)
William Merrill, Ashish Sabharwal
The Parallelism Tradeoff: Limitations of Log-Precision Transformers. Trans. Assoc. Comput. Linguistics 11 (2023)
Muru Zhang, Ofir Press, William Merrill, Alisa Liu, Noah A. Smith
How Language Model Hallucinations Can Snowball. CoRR (2023)
William Merrill
Formal languages and neural models for learning on sequences. ICGI (2023)
Zhaofeng Wu, William Merrill, Hao Peng, Iz Beltagy, Noah A. Smith
Transparency Helps Reveal When Language Models Learn Meaning. Trans. Assoc. Comput. Linguistics 11 (2023)
William Merrill, Ashish Sabharwal
The Expressive Power of Transformers with Chain of Thought. CoRR (2023)
William Merrill, Nikolaos Tsilivis, Aman Shukla
A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks. CoRR (2023)
William Merrill, Ashish Sabharwal
A Logic for Expressing Log-Precision Transformers. NeurIPS (2023)
William Merrill
Formal Languages and the NLP Black Box. DLT (2023)
Lena Strobl, William Merrill, Gail Weiss, David Chiang, Dana Angluin
Transformers as Recognizers of Formal Languages: A Survey on Expressivity. CoRR (2023)
Zhaofeng Wu, William Merrill, Hao Peng, Iz Beltagy, Noah A. Smith
Transparency Helps Reveal When Language Models Learn Meaning. CoRR (2022)
William Merrill, Alex Warstadt, Tal Linzen
Entailment Semantics Can Be Extracted from an Ideal Language Model. CoNLL (2022)
William Merrill, Nikolaos Tsilivis
Extracting Finite Automata from RNNs Using State Merging. CoRR (2022)
William Merrill, Ashish Sabharwal
Log-Precision Transformers are Constant-Depth Uniform Threshold Circuits. CoRR (2022)
Sanjay Subramanian, William Merrill, Trevor Darrell, Matt Gardner, Sameer Singh, Anna Rohrbach
ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension. ACL (1) (2022)
William Merrill, Alex Warstadt, Tal Linzen
Entailment Semantics Can Be Extracted from an Ideal Language Model. CoRR (2022)
William Merrill, Ashish Sabharwal
Transformers Implement First-Order Logic with Majority Quantifiers. CoRR (2022)
William Merrill, Ashish Sabharwal, Noah A. Smith
Saturated Transformers are Constant-Depth Threshold Circuits. Trans. Assoc. Comput. Linguistics 10 (2022)
William Merrill, Yoav Goldberg, Roy Schwartz, Noah A. Smith
Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand? Trans. Assoc. Comput. Linguistics 9 (2021)
William Merrill, Yoav Goldberg, Roy Schwartz, Noah A. Smith
Provable Limitations of Acquiring Meaning from Ungrounded Form: What will Future Language Models Understand? CoRR (2021)
Matt Gardner, William Merrill, Jesse Dodge, Matthew E. Peters, Alexis Ross, Sameer Singh, Noah A. Smith
Competency Problems: On Finding and Removing Artifacts in Language Data. EMNLP (1) (2021)
William Merrill
Formal Language Theory Meets Modern NLP. CoRR (2021)
William Merrill, Yoav Goldberg, Roy Schwartz, Noah A. Smith
On the Power of Saturated Transformers: A View from Circuit Complexity. CoRR (2021)
Matt Gardner, William Merrill, Jesse Dodge, Matthew E. Peters, Alexis Ross, Sameer Singh, Noah A. Smith
Competency Problems: On Finding and Removing Artifacts in Language Data. CoRR (2021)
William Merrill, Vivek Ramanujan, Yoav Goldberg, Roy Schwartz, Noah A. Smith
Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent. EMNLP (1) (2021)
William Merrill
On the Linguistic Capacity of Real-Time Counter Automata. CoRR (2020)
William Merrill, Vivek Ramanujan, Yoav Goldberg, Roy Schwartz, Noah A. Smith
Parameter Norm Growth During Training of Transformers. CoRR (2020)
William Merrill, Gail Weiss, Yoav Goldberg, Roy Schwartz, Noah A. Smith, Eran Yahav
A Formal Hierarchy of RNN Architectures. ACL (2020)
Lucy Lu Wang, Kyle Lo, Yoganand Chandrasekhar, Russell Reas, Jiangjiang Yang, Darrin Eide, Kathryn Funk, Rodney Kinney, Ziyang Liu, William Merrill, Paul Mooney, Dewey A. Murdick, Devvret Rishi, Jerry Sheehan, Zhihong Shen, Brandon Stilson, Alex D. Wade, Kuansan Wang, Chris Wilhelm, Boya Xie, Douglas Raymond, Daniel S. Weld, Oren Etzioni, Sebastian Kohlmeier
CORD-19: The Covid-19 Open Research Dataset. CoRR (2020)
William Merrill, Gail Weiss, Yoav Goldberg, Roy Schwartz, Noah A. Smith, Eran Yahav
A Formal Hierarchy of RNN Architectures. CoRR (2020)
William Merrill, Gigi Felice Stark, Robert Frank
Detecting Syntactic Change Using a Neural Part-of-Speech Tagger. LChange@ACL (2019)
William Merrill, Gigi Felice Stark, Robert Frank
Detecting Syntactic Change Using a Neural Part-of-Speech Tagger. CoRR (2019)
William Merrill, Lenny Khazan, Noah Amsel, Yiding Hao, Simon Mendelsohn, Robert Frank
Finding Syntactic Representations in Neural Stacks. CoRR (2019)
William Merrill, Lenny Khazan, Noah Amsel, Yiding Hao, Simon Mendelsohn, Robert Frank
Finding Hierarchical Structure in Neural Stacks Using Unsupervised Parsing. BlackboxNLP@ACL (2019)
William Merrill
Sequential Neural Networks as Automata. CoRR (2019)
Yiding Hao, William Merrill, Dana Angluin, Robert Frank, Noah Amsel, Andrew Benz, Simon Mendelsohn
Context-Free Transductions with Neural Stacks. BlackboxNLP@EMNLP (2018)
Yiding Hao, William Merrill, Dana Angluin, Robert Frank, Noah Amsel, Andrew Benz, Simon Mendelsohn
Context-Free Transductions with Neural Stacks. CoRR (2018)
Jungo Kasai, Robert Frank, Pauli Xu, William Merrill, Owen Rambow
End-to-End Graph-Based TAG Parsing with Neural Networks. NAACL-HLT (2018)
Jungo Kasai, Robert Frank, Pauli Xu, William Merrill, Owen Rambow
End-to-end Graph-based TAG Parsing with Neural Networks. CoRR (2018)
William Merrill
Where is the return on investment in wireless sensor networks? IEEE Wirel. Commun. 17 (1) (2010)
William Merrill, Lewis Girod, Brian Schiffer, Dustin McIntire, Guillaume Rava, Katayoun Sohrabi, Fredric Newberg, Jeremy Elson, William J. Kaiser
Dynamic Networking and Smart Sensing Enable Next-Generation Landmines. IEEE Pervasive Comput. 3 (4) (2004)
Katayoun Sohrabi, William Merrill, Jeremy Elson, Lewis Girod, Fredric Newberg, William J. Kaiser
Methods for Scalable Self-Assembly of Ad Hoc Wireless Sensor Networks. IEEE Trans. Mob. Comput. 3 (4) (2004)
William Merrill
Preserving and Protecting the Freedom to Learn Online. WebNet (2001)