Kyle Mahowald | DeepAI

DeepAI AI Chat

Featured Co-authors

Joshua B. Tenenbaum
180 publications
William Yang Wang
166 publications
Ryan Cotterell
156 publications
Dan Jurafsky
77 publications
Christopher Potts
57 publications
Jing Huang
55 publications
Junyi Jessy Li
52 publications
Eunsol Choi
48 publications
Tiago Pimentel
40 publications
Matthew Lease
36 publications
David Harwath
35 publications

∙ 05/29/2023

A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding Spaces

We study semantic construal in grammatical constructions using large lan...

0 Gabriella Chronis, et al. ∙

∙ 05/25/2023

Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias

While existing work on studying bias in NLP focues on negative or pejora...

0 Venkata S Govindarajan, et al. ∙

∙ 05/17/2023

Elaborative Simplification as Implicit Questions Under Discussion

Automated text simplification, a technique useful for making text more a...

0 Yating Wu, et al. ∙

∙ 02/16/2023

Keep it Neutral: Using Natural Language Inference to Improve Generation

We explore incorporating natural language inference (NLI) into the text ...

0 Michail Mersinias, et al. ∙

∙ 01/29/2023

A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction

Knowledge of syntax includes knowledge of rare, idiosyncratic constructi...

0 Kyle Mahowald, et al. ∙

∙ 01/16/2023

Dissociating language and thought in large language models: a cognitive perspective

Today's large language models (LLMs) routinely generate coherent, gramma...

5 Kyle Mahowald, et al. ∙

∙ 12/19/2022

Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training

Language tasks involving character-level manipulations (e.g., spelling c...

0 Jing Huang, et al. ∙

∙ 11/01/2022

Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality

Recent visuolinguistic pre-trained models show promising progress on var...

0 Anuj Diwan, et al. ∙

∙ 06/29/2022

longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks

Developing methods to adversarially challenge NLP systems is a promising...

0 Venelin Kovatchev, et al. ∙

∙ 06/06/2022

What do tokens know about their characters and how do they know it?

Pre-trained language models (PLMs) that use subword tokenization schemes...

0 Ayush Kaushal, et al. ∙

∙ 03/11/2022

When classifying grammatical role, BERT doesn't care about word order... except when it matters

Because meaning can often be inferred from lexical semantics alone, word...

0 Isabel Papadimitriou, et al. ∙

∙ 01/30/2022

Grammatical cues are largely, but not completely, redundant with word meanings in natural language

The combinatorial power of language has historically been argued to be e...

0 Kyle Mahowald, et al. ∙

∙ 09/13/2021

A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space

In cross-lingual language models, representations for many different lan...

0 Alex Jones, et al. ∙

∙ 04/29/2021

How (Non-)Optimal is the Lexicon?

The mapping of lexical meanings to wordforms is a major feature of natur...

0 Tiago Pimentel, et al. ∙

∙ 04/17/2021

Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP

Cryptic crosswords, the dominant English-language crossword variety in t...

0 Josh Rozner, et al. ∙

∙ 01/26/2021

Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT

We investigate how Multilingual BERT (mBERT) encodes grammar by examinin...

0 Isabel Papadimitriou, et al. ∙

∙ 10/13/2020

With Little Power Comes Great Responsibility

Despite its importance to experimental design, statistical power (the pr...

5 Dallas Card, et al. ∙

∙ 10/01/2015

Response to Liu, Xu, and Liang (2015) and Ferrer-i-Cancho and Gómez-Rodríguez (2015) on Dependency Length Minimization

We address recent criticisms (Liu et al., 2015; Ferrer-i-Cancho and Góme...

0 Richard Futrell, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world