Page: 1 2 3 4 5 6 7 8... 174
61 |
Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners ...
|
|
|
|
BASE
|
|
Show details
|
|
62 |
What is a 'mechanism'? A distinction between two sub-types of mechanistic explanations ...
|
|
|
|
BASE
|
|
Show details
|
|
64 |
Modeling Sense Structure in Word Usage Graphs with the Weighted Stochastic Block Model ...
|
|
|
|
BASE
|
|
Show details
|
|
65 |
Judgement of political statements are influenced by speaker identity ...
|
|
|
|
BASE
|
|
Show details
|
|
67 |
How do the semantic properties of visual explanations guide causal inference? ...
|
|
|
|
BASE
|
|
Show details
|
|
68 |
Statistical properties of the speed-accuracy trade-off (SAT) paradigm in sentence processing ...
|
|
|
|
BASE
|
|
Show details
|
|
69 |
CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals ...
|
|
|
|
Abstract:
Read paper: https://www.aclanthology.org/2021.acl-long.291 Abstract: Most previous studies integrate cognitive language processing signals (e.g., eye-tracking or EEG data) into neural models of natural language processing (NLP) just by directly concatenating word embeddings with cognitive features, ignoring the gap between the two modalities (i.e., textual vs. cognitive) and noise in cognitive features. In this paper, we propose a CogAlign approach to these issues, which learns to align textual neural representations to cognitive features. In CogAlign, we use a shared encoder equipped with a modality discriminator to alternatively encode textual and cognitive inputs to capture their differences and commonalities. Additionally, a text-aware attention mechanism is proposed to detect task-related information and to avoid using noise in cognitive features. Experimental results on three NLP tasks, namely named entity recognition, sentiment analysis and relation extraction, show that CogAlign achieves significant ...
|
|
Keyword:
Cognitive Linguistics; Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
|
|
URL: https://underline.io/lecture/25643-cogalign-learning-to-align-textual-neural-representations-to-cognitive-language-processing-signals https://dx.doi.org/10.48448/pn9t-2v24
|
|
BASE
|
|
Hide details
|
|
70 |
Providing explanations shifts preschoolers’ metaphor preferences ...
|
|
|
|
BASE
|
|
Show details
|
|
71 |
Statistical properties of the speed-accuracy trade-off (SAT) paradigm in sentence processing ...
|
|
|
|
BASE
|
|
Show details
|
|
73 |
Hand constraint affects semantic processing of hand-manipulable objects: An fNIRS study ...
|
|
|
|
BASE
|
|
Show details
|
|
74 |
Verb learning in young children: Are types of comparisons important? ...
|
|
|
|
BASE
|
|
Show details
|
|
75 |
Hand constraint affects semantic processing of hand-manipulable objects: An fNIRS study ...
|
|
|
|
BASE
|
|
Show details
|
|
76 |
Verb learning in young children: Are types of comparisons important? ...
|
|
|
|
BASE
|
|
Show details
|
|
77 |
How do the semantic properties of visual explanations guide causal inference? ...
|
|
|
|
BASE
|
|
Show details
|
|
78 |
What is a 'mechanism'? A distinction between two sub-types of mechanistic explanations ...
|
|
|
|
BASE
|
|
Show details
|
|
79 |
A Computational Model of Comprehension in Manga Style Visual Narratives ...
|
|
|
|
BASE
|
|
Show details
|
|
80 |
Recovering Quantitative Models of Human Information Processing with Differentiable Architecture Search ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8... 174
|
|