1 |
Is Information Density Uniform in Task-Oriented Dialogues? ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Analysing Human Strategies of Information Transmission as a Function of Discourse Context ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Syntactic Persistence in Language Models: Priming as a Window into Abstract Language Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Words are the Window to the Soul: Language-based User Representations for Fake News Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Analysing Lexical Semantic Change with Contextualised Word Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Disentangling dialects: a neural approach to Indo-Aryan historical phonology and subgrouping
|
|
|
|
In: Cathcart, Chundra; Rama, Taraka (2020). Disentangling dialects: a neural approach to Indo-Aryan historical phonology and subgrouping. In: Fernández, Raquel; Linzen, Tal. Proceedings of the 24th Conference on Computational Natural Language Learning. Online: Association for Computational Linguistics, 620-630. (2020)
|
|
BASE
|
|
Show details
|
|
12 |
Identifying robust markers of Parkinson's disease in typing behaviour using a CNN-LSTM network.
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Evaluating the Representational Hub of Language and Vision Models ...
|
|
|
|
Abstract:
The multimodal models used in the emerging field at the intersection of computational linguistics and computer vision implement the bottom-up processing of the `Hub and Spoke' architecture proposed in cognitive science to represent how the brain processes and combines multi-sensory inputs. In particular, the Hub is implemented as a neural network encoder. We investigate the effect on this encoder of various vision-and-language tasks proposed in the literature: visual question answering, visual reference resolution, and visually grounded dialogue. To measure the quality of the representations learned by the encoder, we use two kinds of analyses. First, we evaluate the encoder pre-trained on the different vision-and-language tasks on an existing diagnostic task designed to assess multimodal semantic understanding. Second, we carry out a battery of analyses aimed at studying how the encoder merges and exploits the two modalities. ... : Accepted to IWCS 2019 ...
|
|
Keyword:
Computation and Language cs.CL; Computer Vision and Pattern Recognition cs.CV; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1904.06038 https://arxiv.org/abs/1904.06038
|
|
BASE
|
|
Hide details
|
|
14 |
Is the Red Square Big? MALeViC: Modeling Adjectives Leveraging Visual Contexts ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
MALeViC: Modeling Adjectives Leveraging Visual Contexts ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
MALeViC: Modeling Adjectives Leveraging Visual Contexts ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
La adquisición del lenguaje de tres a seis años y sus posibles trastornos
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|