DE eng

Search in the Catalogues and Directories

Hits 1 – 13 of 13

1
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment ...
BASE
Show details
2
Few-shot Language Coordination by Modeling Theory of Mind ...
BASE
Show details
3
An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games ...
BASE
Show details
4
Grounding 'Grounding' in NLP ...
BASE
Show details
5
Dependency Induction Through the Lens of Visual Perception ...
Su, Ruisi; Rijhwani, Shruti; Zhu, Hao. - : arXiv, 2021
BASE
Show details
6
Dependency Induction Through the Lens of Visual Perception ...
Abstract: Most previous work on grammar induction focuses on learning phrasal or dependency structure purely from text. However, because the signal provided by text alone is limited, recently introduced visually grounded syntax models make use of multimodal information leading to improved performance in constituency grammar induction. However, as compared to dependency grammars, constituency grammars do not provide a straight- forward way to incorporate visual information without enforcing language-specific heuristics. In this paper, we propose an unsupervised grammar induction model that leverages word concreteness and a structural vision-based heuristic to jointly learn constituency-structure and dependency-structure grammars. Our experiments find that concreteness is a strong indicator for learning dependency grammars, im- proving the direct attachment score (DAS) by over 50% as compared to state-of-the-art models trained on pure text. Next, we propose an extension of our model that leverages both word concreteness ...
Keyword: Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
URL: https://dx.doi.org/10.48448/7j5q-9w68
https://underline.io/lecture/39855-dependency-induction-through-the-lens-of-visual-perception
BASE
Hide details
7
Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games ...
BASE
Show details
8
Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games ...
BASE
Show details
9
Experience Grounds Language ...
BASE
Show details
10
The Return of Lexical Dependencies: Neural Lexicalized PCFGs ...
BASE
Show details
11
Shifting the Baseline: Single Modality Performance on Visual Navigation & QA ...
BASE
Show details
12
Natural Language Inference from Multiple Premises ...
BASE
Show details
13
Unsupervised grammar induction with Combinatory Categorial Grammars
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
13
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern