5 |
Compositional Networks Enable Systematic Generalization for Grounded Language Understanding
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Measuring Social Biases in Grounded Vision and Language Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Compositional Networks Enable Systematic Generalization for Grounded Language Understanding ...
|
|
|
|
Abstract:
Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abilities when presented with novel sentences, systematic variation uncovers the limitations in the language-understanding abilities of networks. We demonstrate that these limitations can be overcome by addressing the generalization challenges in the gSCAN dataset, which explicitly measures how well an agent is able to interpret novel linguistic commands grounded in vision, e.g., novel pairings of adjectives and nouns. The key principle we employ is compositionality: that the compositional structure of networks should reflect the compositional structure of the problem domain they address, while allowing other parameters to be learned end-to-end. We build a general-purpose mechanism that enables agents to generalize their language understanding to compositional domains. Crucially, our network has ...
|
|
URL: https://underline.io/lecture/38607-compositional-networks-enable-systematic-generalization-for-grounded-language-understanding https://dx.doi.org/10.48448/9s57-wf82
|
|
BASE
|
|
Hide details
|
|
9 |
Assessing Language Proficiency from Eye Movements in Reading
|
|
|
|
In: Association for Computational Linguistics (2021)
|
|
BASE
|
|
Show details
|
|
10 |
Measuring Social Biases in Grounded Vision and Language Embeddings
|
|
Ross, Candace; Barbu, Andrei; Katz, Boris. - : Center for Brains, Minds and Machines (CBMM), Annual Conference of the North American Chapter of the Association for Computational Linguistics (HLT/NAACL), 2021
|
|
BASE
|
|
Show details
|
|
13 |
Learning a natural-language to LTL executable semantic parser for grounded robotics
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Compositional Networks Enable Systematic Generalization for Grounded Language Understanding ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Learning a natural-language to LTL executable semantic parser for grounded robotics ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Measuring Social Biases in Grounded Vision and Language Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas
|
|
|
|
BASE
|
|
Show details
|
|
|
|