Zhengxuan Wu | DeepAI

DeepAI AI Chat

Featured Co-authors

Jure Leskovec
142 publications
Douwe Kiela
70 publications
Christopher Potts
57 publications
Jing Huang
55 publications
Roi Reichart
53 publications
Noah D. Goodman
52 publications
Michael S. Bernstein
28 publications
Kyle Mahowald
18 publications
Desmond C. Ong
18 publications
Alex Tamkin
17 publications
Atticus Geiger
16 publications

∙ 09/19/2023

Rigorously Assessing Natural Language Explanations of Neurons

Natural language is an appealing medium for explaining how large languag...

0 Jing Huang, et al. ∙

∙ 05/15/2023

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca

Obtaining human-interpretable explanations of large, general-purpose lan...

0 Zhengxuan Wu, et al. ∙

∙ 03/05/2023

Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations

Causal abstraction is a promising theoretical framework for explainable ...

0 Atticus Geiger, 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. ∙

∙ 09/28/2022

Causal Proxy Models for Concept-Based Model Explanations

Explainability methods for NLP systems encounter a version of the fundam...

19 Zhengxuan Wu, et al. ∙

∙ 06/30/2022

ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time

Humans have the remarkable ability to recognize and acquire novel visual...

5 Tailin Wu, et al. ∙

∙ 05/27/2022

CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior

The increasing size and complexity of modern ML systems has improved the...

4 Eldar David Abraham, et al. ∙

∙ 02/24/2022

Oolong: Investigating What Makes Crosslingual Transfer Hard with Controlled Studies

Little is known about what makes cross-lingual transfer hard, since fact...

9 Zhengxuan Wu, et al. ∙

∙ 12/05/2021

Causal Distillation for Language Models

Distillation efforts have led to language models that are more compact a...

0 Zhengxuan Wu, et al. ∙

∙ 12/01/2021

Inducing Causal Structure for Interpretable Neural Networks

In many areas, we have well-founded insights about causal structure that...

0 Atticus Geiger, et al. ∙

∙ 09/18/2021

ReaSCAN: Compositional Reasoning in Language Grounding

The ability to compositionally map language to referents, relations, and...

0 Zhengxuan Wu, et al. ∙

∙ 04/17/2021

Identifying the Limits of Cross-Domain Knowledge Transfer for Pretrained Models

There is growing evidence that pretrained language models improve task-s...

2 Zhengxuan Wu, et al. ∙

∙ 01/27/2021

Not Now, Ask Later: Users Weaken Their Behavior Change Regimen Over Time, But Expect To Re-Strengthen It Imminently

How effectively do we adhere to nudges and interventions that help us co...

0 Geza Kovacs, et al. ∙

∙ 01/01/2021

On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification

BERT, as one of the pretrianed language models, attracts the most attent...

0 Zhengxuan Wu, et al. ∙

∙ 12/30/2020

DynaSent: A Dynamic Benchmark for Sentiment Analysis

We introduce DynaSent ('Dynamic Sentiment'), a new English-language benc...

5 Christopher Potts, et al. ∙

∙ 10/15/2020

Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) and Targeted ASBA (TABSA) allow f...

0 Zhengxuan Wu, et al. ∙

∙ 10/10/2020

Structured Self-Attention Weights Encode Semantics in Sentiment Analysis

Neural attention, especially the self-attention made popular by the Tran...

0 Zhengxuan Wu, et al. ∙

∙ 10/09/2020

Pragmatically Informative Color Generation by Grounding Contextual Modifiers

Grounding language in contextual information is crucial for fine-grained...

0 Zhengxuan Wu, et al. ∙

∙ 11/22/2019

Modeling emotion in complex stories: the Stanford Emotional Narratives Dataset

Human emotions unfold over time, and more affective computing research h...

0 Desmond C. Ong, et al. ∙

∙ 08/15/2019

Disentangling Latent Emotions of Word Embeddings on Complex Emotional Narratives

Word embedding models such as GloVe are widely used in natural language ...

0 Zhengxuan Wu, et al. ∙

∙ 07/08/2019

Attending to Emotional Narratives

Attention mechanisms in deep neural networks have achieved excellent per...

0 Zhengxuan Wu, et al. ∙

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