1 |
Analysis of Language Change in Collaborative Instruction Following ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Analysis of Language Change in Collaborative Instruction Following
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
3 |
Analysis of Language Change in Collaborative Instruction Following ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Analysis of Language Change in Collaborative Instruction Following ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Evaluating Models' Local Decision Boundaries via Contrast Sets ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
What is Learned in Visually Grounded Neural Syntax Acquisition ...
|
|
|
|
Abstract:
Visual features are a promising signal for learning bootstrap textual models. However, blackbox learning models make it difficult to isolate the specific contribution of visual components. In this analysis, we consider the case study of the Visually Grounded Neural Syntax Learner (Shi et al., 2019), a recent approach for learning syntax from a visual training signal. By constructing simplified versions of the model, we isolate the core factors that yield the model's strong performance. Contrary to what the model might be capable of learning, we find significantly less expressive versions produce similar predictions and perform just as well, or even better. We also find that a simple lexical signal of noun concreteness plays the main role in the model's predictions as opposed to more complex syntactic reasoning. ... : In ACL 2020 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2005.01678 https://arxiv.org/abs/2005.01678
|
|
BASE
|
|
Hide details
|
|
8 |
A Corpus for Reasoning About Natural Language Grounded in Photographs ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Mapping Instructions and Visual Observations to Actions with Reinforcement Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Learning to Automatically Solve Algebra Word Problems
|
|
|
|
In: MIT web domain (2014)
|
|
BASE
|
|
Show details
|
|
|
|