1 |
Review on multichannel emotion perception in ASD (Zhang et al., 2022) ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Review on multichannel emotion perception in ASD (Zhang et al., 2022) ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Integrating Encyclopedic Knowledge into Neural Language Models
|
|
|
|
BASE
|
|
Show details
|
|
4 |
BI-RADS Reading of Non-Mass Lesions on DCE-MRI and Differential Diagnosis Performed by Radiomics and Deep Learning.
|
|
|
|
BASE
|
|
Show details
|
|
5 |
BI-RADS Reading of Non-Mass Lesions on DCE-MRI and Differential Diagnosis Performed by Radiomics and Deep Learning.
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Gender, emotion, and channel in emotion processing (Lin et al., 2021) ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Gender differences in emotion Stroop tasks (Lin et al., 2021) ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Gender differences in emotion Stroop tasks (Lin et al., 2021) ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Gender, emotion, and channel in emotion processing (Lin et al., 2021) ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
BI-RADS Reading of Non-Mass Lesions on DCE-MRI and Differential Diagnosis Performed by Radiomics and Deep Learning
|
|
|
|
In: Front Oncol (2021)
|
|
BASE
|
|
Show details
|
|
13 |
A New Data Normalization Method to Improve Dialogue Generation by Minimizing Long Tail Effect ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
FASTMATCH: Accelerating the Inference of BERT-based Text Matching ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control
|
|
|
|
In: MIT web domain (2020)
|
|
Abstract:
Selective rationalization has become a common mechanism to ensure that predictive models reveal how they use any available features. The selection may be soft or hard, and identifies a subset of input features relevant for prediction. The setup can be viewed as a cooperate game between the selector (aka rationale generator) and the predictor making use of only the selected features. The co-operative setting may, however, be compromised for two reasons. First, the generator typically has no direct access to the outcome it aims to justify, resulting in poor performance. Second, there's typically no control exerted on the information left outside the selection. We revise the overall co-operative framework to address these challenges. We introduce an introspective model which explicitly predicts and incorporates the outcome into the selection process. Moreover, we explicitly control the rationale complement via an adversary so as not to leave any useful information out of the selection. We show that the two complementary mechanisms maintain both high predictive accuracy and lead to comprehensive rationales.
|
|
URL: https://hdl.handle.net/1721.1/128926
|
|
BASE
|
|
Hide details
|
|
18 |
Sentence Context Differentially Modulates Contributions of Fundamental Frequency Contours to Word Recognition in Chinese-Speaking Children With and Without Dyslexia
|
|
|
|
In: Front Psychol (2020)
|
|
BASE
|
|
Show details
|
|
19 |
Bimodal Benefits for Lexical Tone Recognition: An Investigation on Mandarin-speaking Preschoolers with a Cochlear Implant and a Contralateral Hearing Aid
|
|
|
|
In: Brain Sci (2020)
|
|
BASE
|
|
Show details
|
|
20 |
A unified sequence-to-sequence front-end model for Mandarin text-to-speech synthesis ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|