Picture for Alane Suhr

Alane Suhr

We're Afraid Language Models Aren't Modeling Ambiguity

Apr 27, 2023
Alisa Liu, Zhaofeng Wu, Julian Michael, Alane Suhr, Peter West, Alexander Koller, Swabha Swayamdipta, Noah A. Smith, Yejin Choi

Figure 1 for We're Afraid Language Models Aren't Modeling Ambiguity

Figure 2 for We're Afraid Language Models Aren't Modeling Ambiguity

Figure 3 for We're Afraid Language Models Aren't Modeling Ambiguity

Figure 4 for We're Afraid Language Models Aren't Modeling Ambiguity

* 9 pages, 3 figures

Access Paper or Ask Questions

Continual Learning for Instruction Following from Realtime Feedback

Dec 19, 2022
Alane Suhr, Yoav Artzi

Figure 1 for Continual Learning for Instruction Following from Realtime Feedback

Figure 2 for Continual Learning for Instruction Following from Realtime Feedback

Figure 3 for Continual Learning for Instruction Following from Realtime Feedback

Figure 4 for Continual Learning for Instruction Following from Realtime Feedback

Access Paper or Ask Questions

Abstract Visual Reasoning with Tangram Shapes

Nov 29, 2022
Anya Ji, Noriyuki Kojima, Noah Rush, Alane Suhr, Wai Keen Vong, Robert D. Hawkins, Yoav Artzi

Figure 1 for Abstract Visual Reasoning with Tangram Shapes

Figure 2 for Abstract Visual Reasoning with Tangram Shapes

Figure 3 for Abstract Visual Reasoning with Tangram Shapes

Figure 4 for Abstract Visual Reasoning with Tangram Shapes

* EMNLP 2022 long paper

Access Paper or Ask Questions

Analysis of Language Change in Collaborative Instruction Following

Sep 09, 2021
Anna Effenberger, Eva Yan, Rhia Singh, Alane Suhr, Yoav Artzi

Figure 1 for Analysis of Language Change in Collaborative Instruction Following

Figure 2 for Analysis of Language Change in Collaborative Instruction Following

Figure 3 for Analysis of Language Change in Collaborative Instruction Following

Figure 4 for Analysis of Language Change in Collaborative Instruction Following

* Findings of EMNLP 2021 Short Paper

Access Paper or Ask Questions

Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior

Aug 10, 2021
Noriyuki Kojima, Alane Suhr, Yoav Artzi

Figure 1 for Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior

Figure 2 for Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior

Figure 3 for Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior

Figure 4 for Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior

* To appear in TACL 2021. The arXiv version is a pre-MIT Press publication version

Access Paper or Ask Questions

Executing Instructions in Situated Collaborative Interactions

Oct 17, 2019
Alane Suhr, Claudia Yan, Jacob Schluger, Stanley Yu, Hadi Khader, Marwa Mouallem, Iris Zhang, Yoav Artzi

Figure 1 for Executing Instructions in Situated Collaborative Interactions

Figure 2 for Executing Instructions in Situated Collaborative Interactions

Figure 3 for Executing Instructions in Situated Collaborative Interactions

Figure 4 for Executing Instructions in Situated Collaborative Interactions

* EMNLP 2019 long paper

Access Paper or Ask Questions

NLVR2 Visual Bias Analysis

Sep 23, 2019
Alane Suhr, Yoav Artzi

Figure 1 for NLVR2 Visual Bias Analysis

Figure 2 for NLVR2 Visual Bias Analysis

Figure 3 for NLVR2 Visual Bias Analysis

Figure 4 for NLVR2 Visual Bias Analysis

* Corresponding notebook available at http://lil.nlp.cornell.edu/nlvr/NLVR2BiasAnalysis.html

Access Paper or Ask Questions