DE eng

Search in the Catalogues and Directories

Page: 1 2 3
Hits 1 – 20 of 43

1
Shapley Idioms: Analysing BERT Sentence Embeddings for General Idiom Token Identification
In: Front Artif Intell (2022)
BASE
Show details
2
Language-Driven Region Pointer Advancement for Controllable Image Captioning ...
BASE
Show details
3
Semantic Relatedness and Taxonomic Word Embeddings ...
BASE
Show details
4
English WordNet Taxonomic Random Walk Pseudo-Corpora
In: Conference papers (2020)
BASE
Show details
5
Language-Driven Region Pointer Advancement for Controllable Image Captioning
In: Conference papers (2020)
BASE
Show details
6
Local Alignment of Frame of Reference Assignment in English and Swedish Dialogue
In: Conference papers (2020)
BASE
Show details
7
Capturing and measuring thematic relatedness [<Journal>]
DNB Subject Category Language
Show details
8
Synthetic, Yet Natural: Properties of WordNet Random Walk Corpora and the impact of rare words on embedding performance
In: Conference papers (2019)
Abstract: Creating word embeddings that reflect semantic relationships encoded in lexical knowledge resources is an open challenge. One approach is to use a random walk over a knowledge graph to generate a pseudo-corpus and use this corpus to train embeddings. However, the effect of the shape of the knowledge graph on the generated pseudo-corpora, and on the resulting word embeddings, has not been studied. To explore this, we use English WordNet, constrained to the taxonomic (tree-like) portion of the graph, as a case study. We investigate the properties of the generated pseudo-corpora, and their impact on the resulting embeddings. We find that the distributions in the psuedo-corpora exhibit properties found in natural corpora, such as Zipf’s and Heaps’ law, and also ob- serve that the proportion of rare words in a pseudo-corpus affects the performance of its embeddings on word similarity.
Keyword: Artificial Intelligence and Robotics; Computational Linguistics; corpus; evaluation; Numerical Analysis and Scientific Computing; random walk; representations; Software Engineering; taxonomy; word embeddings; word similarity; WordNet
URL: https://arrow.tudublin.ie/scschcomcon/271
https://arrow.tudublin.ie/cgi/viewcontent.cgi?article=1283&context=scschcomcon
BASE
Hide details
9
Size Matters: The Impact of Training Size in Taxonomically-Enriched Word Embeddings
In: Articles (2019)
BASE
Show details
10
Modular Mechanistic Networks: On Bridging Mechanistic and Phenomenological Models with Deep Neural Networks in Natural Language Processing ...
Dobnik, Simon; Kelleher, John D.. - : arXiv, 2018
BASE
Show details
11
What is not where: the challenge of integrating spatial representations into deep learning architectures ...
Kelleher, John D.; Dobnik, Simon. - : arXiv, 2018
BASE
Show details
12
Is it worth it? Budget-related evaluation metrics for model selection ...
BASE
Show details
13
Is it worth it? Budget-related evaluation metrics for model selection
In: Conference papers (2018)
BASE
Show details
14
Exploring the Functional and Geometric Bias of Spatial Relations Using Neural Language Models
In: Conference papers (2018)
BASE
Show details
15
Back to the Future: Logic and Machine Learning
In: Conference papers (2017)
BASE
Show details
16
Robot Perception Errors and Human Resolution Strategies in Situated Human-Robot Dialogue
In: Articles (2017)
BASE
Show details
17
Assessing the Usefulness of Different Feature Sets for Predicting the Comprehension Difficulty of Text
In: Conference papers (2017)
BASE
Show details
18
Towards a Computational Model of Frame of Reference Alignment in Swedish Dialogue
In: Conference papers (2016)
BASE
Show details
19
A Model for Attention-Driven Judgements in Type Theory with Records
In: Conference papers (2016)
BASE
Show details
20
Fundamentals of Machine Learning for Neural Machine Translation
In: Conference papers (2016)
BASE
Show details

Page: 1 2 3

Catalogues
0
0
0
0
1
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
42
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern