DE eng

Search in the Catalogues and Directories

Hits 1 – 11 of 11

1
In-Game Social Interactions to Facilitate ESL Students' Morphological Awareness, Language and Literacy Skills
In: Computer Science Faculty Publications and Presentations (2021)
BASE
Show details
2
Language Acquisition is Embodied, Interactive, Emotive: a Research Proposal ...
Kennington, Casey. - : arXiv, 2021
BASE
Show details
3
Enriching Language Models with Visually-grounded Word Vectors and the Lancaster Sensorimotor Norms ...
Abstract: Language models are trained only on text despite the fact that humans learn their first language in a highly interactive and multimodal environment where the first set of learned words are largely concrete, denoting physical entities and embodied states. To enrich language models with some of this missing experience, we leverage two sources of information: (1) the Lancaster Sensorimotor norms, which provide ratings (means and standard deviations) for over 40,000 English words along several dimensions of embodiment, and which capture the extent to which something is experienced across 11 different sensory modalities, and (2) vectors from coefficients of binary classifiers trained on images for the BERT vocabulary. We pre-trained the ELECTRA model and fine-tuned the RoBERTa model with these two sources of information then evaluate using the established GLUE benchmark and the Visual Dialog benchmark. We find that enriching language models with the Lancaster norms and image vectors improves results in both ...
Keyword: Computational Linguistics; Language Models; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
URL: https://dx.doi.org/10.48448/93qk-ze94
https://underline.io/lecture/39871-enriching-language-models-with-visually-grounded-word-vectors-and-the-lancaster-sensorimotor-norms
BASE
Hide details
4
KidSpell: A Child-Oriented, Rule-Based, Phonetic Spellchecker
In: Computer Science Faculty Publications and Presentations (2020)
BASE
Show details
5
Guiding the Selection of Child Spellchecker Suggestions Using Audio and Visual Cues
In: Computer Science Faculty Publications and Presentations (2020)
BASE
Show details
6
Evaluating and Improving Child-Directed Automatic Speech Recognition
In: Computer Science Faculty Publications and Presentations (2020)
BASE
Show details
7
Composing and Embedding the Words-as-Classifiers Model of Grounded Semantics ...
BASE
Show details
8
Symbol, Conversational, and Societal Grounding with a Toy Robot ...
Kennington, Casey; Plane, Sarah. - : arXiv, 2017
BASE
Show details
9
Incrementally resolving references in order to identify visually present objects in a situated dialogue setting
Kennington, Casey. - : Universität Bielefeld, 2016
BASE
Show details
10
Incremental Semantics for Dialogue Processing: Requirements, and a Comparison of Two Approaches
In: Proceedings of the 11th International Conference on Computational Semantics ; 11th International Conference on Computational Semantics ; https://hal-univ-paris.archives-ouvertes.fr/hal-01371420 ; 11th International Conference on Computational Semantics, 2015, London, United Kingdom (2015)
BASE
Show details
11
Situated incremental natural language understanding using Markov Logic Networks
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 28 (2014) 1, 240-255
OLC Linguistik
Show details

Catalogues
0
0
1
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
10
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern