Page: 1 2 3 4 5 6 7 8 9... 150
81 |
EnvEdit: Environment Editing for Vision-and-Language Navigation ...
|
|
|
|
BASE
|
|
Show details
|
|
82 |
Homepage2Vec: Language-Agnostic Website Embedding and Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
83 |
Multilinguals at SemEval-2022 Task 11: Transformer Based Architecture for Complex NER ...
|
|
|
|
BASE
|
|
Show details
|
|
84 |
A new approach to calculating BERTScore for automatic assessment of translation quality ...
|
|
|
|
BASE
|
|
Show details
|
|
85 |
A New Generation of Perspective API: Efficient Multilingual Character-level Transformers ...
|
|
|
|
BASE
|
|
Show details
|
|
86 |
ViWOZ: A Multi-Domain Task-Oriented Dialogue Systems Dataset For Low-resource Language ...
|
|
|
|
BASE
|
|
Show details
|
|
87 |
EAG: Extract and Generate Multi-way Aligned Corpus for Complete Multi-lingual Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
88 |
Natural Language Descriptions of Deep Visual Features ...
|
|
|
|
Abstract:
Some neurons in deep networks specialize in recognizing highly specific perceptual, structural, or semantic features of inputs. In computer vision, techniques exist for identifying neurons that respond to individual concept categories like colors, textures, and object classes. But these techniques are limited in scope, labeling only a small subset of neurons and behaviors in any network. Is a richer characterization of neuron-level computation possible? We introduce a procedure (called MILAN, for mutual-information-guided linguistic annotation of neurons) that automatically labels neurons with open-ended, compositional, natural language descriptions. Given a neuron, MILAN generates a description by searching for a natural language string that maximizes pointwise mutual information with the image regions in which the neuron is active. MILAN produces fine-grained descriptions that capture categorical, relational, and logical structure in learned features. These descriptions obtain high agreement with ... : To be published as a conference paper at ICLR 2022 ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; Computer Vision and Pattern Recognition cs.CV; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://arxiv.org/abs/2201.11114 https://dx.doi.org/10.48550/arxiv.2201.11114
|
|
BASE
|
|
Hide details
|
|
89 |
Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data ...
|
|
|
|
BASE
|
|
Show details
|
|
90 |
A Feasibility Study of Answer-Agnostic Question Generation for Education ...
|
|
|
|
BASE
|
|
Show details
|
|
91 |
Language Generation for Broad-Coverage, Explainable Cognitive Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
95 |
Regional Negative Bias in Word Embeddings Predicts Racial Animus--but only via Name Frequency ...
|
|
|
|
BASE
|
|
Show details
|
|
98 |
Grounding Hindsight Instructions in Multi-Goal Reinforcement Learning for Robotics ...
|
|
|
|
BASE
|
|
Show details
|
|
99 |
Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity ...
|
|
|
|
BASE
|
|
Show details
|
|
100 |
Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9... 150
|
|