Home
Catalogue search
Refine your search:
Keyword
Creator / Publisher:
Kelleher, John D. (42)
Mac Namee, Brian (10)
Dobnik, Simon (7)
SFI Research Centres Programme (6)
Costello, Fintan (5)
Klubicka, Filip (5)
Schütte, Niels (5)
Maldonado, Alfredo (4)
van Genabith, Josef (4)
Ross, Robert (3)
more
Year
Medium
Type
BLLDB-Access
Search in the Catalogues and Directories
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
Sort by
creator [A → Z]
'
creator [Z → A]
'
publishing year ↑ (asc)
'
publishing year ↓ (desc)
'
title [A → Z]
'
title [Z → A]
'
Simple Search
Page:
1
2
3
Hits 1 – 20 of 42
1
Shapley Idioms: Analysing BERT Sentence Embeddings for General Idiom Token Identification
Nedumpozhimana, Vasudevan
;
Klubička, Filip
;
Kelleher, John D.
In: Front Artif Intell (2022)
BASE
Show details
2
Language-Driven Region Pointer Advancement for Controllable Image Captioning ...
Lindh, Annika
;
Ross, Robert J.
;
Kelleher, John D.
. - : arXiv, 2020
BASE
Show details
3
Semantic Relatedness and Taxonomic Word Embeddings ...
Kacmajor, Magdalena
;
Kelleher, John D.
;
Klubicka, Filip
. - : arXiv, 2020
BASE
Show details
4
English WordNet Taxonomic Random Walk Pseudo-Corpora
Klubicka, Filip
;
Maldonado, Alfredo
;
Mahalunkar, Abhijit
...
In: Conference papers (2020)
BASE
Show details
5
Language-Driven Region Pointer Advancement for Controllable Image Captioning
Lindh, Annika
;
Ross, Robert
;
Kelleher, John D.
In: Conference papers (2020)
BASE
Show details
6
Local Alignment of Frame of Reference Assignment in English and Swedish Dialogue
Dobnik, Simon
;
Kelleher, John D.
;
Howes, Christine
In: Conference papers (2020)
BASE
Show details
7
Synthetic, Yet Natural: Properties of WordNet Random Walk Corpora and the impact of rare words on embedding performance
Klubicka, Filip
;
Mahalunkar, Abhijit
;
Maldonado, Alfredo
...
In: Conference papers (2019)
BASE
Show details
8
Size Matters: The Impact of Training Size in Taxonomically-Enriched Word Embeddings
Maldonado, Alfredo
;
Klubicka, Filip
;
Kelleher, John D.
In: Articles (2019)
BASE
Show details
9
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
10
What is not where: the challenge of integrating spatial representations into deep learning architectures ...
Kelleher, John D.
;
Dobnik, Simon
. - : arXiv, 2018
BASE
Show details
11
Is it worth it? Budget-related evaluation metrics for model selection ...
Klubička, Filip
;
Salton, Giancarlo D.
;
Kelleher, John D.
. - : arXiv, 2018
BASE
Show details
12
Is it worth it? Budget-related evaluation metrics for model selection
Klubicka, Filip
;
Salton, Giancarlo
;
Kelleher, John D.
In: Conference papers (2018)
Abstract:
Projects that set out to create a linguistic resource often do so by using a machine learning model that pre-annotates or filters the content that goes through to a human annotator, before going into the final version of the resource. However, available budgets are often limited, and the amount of data that is available exceeds the amount of annotation that can be done. Thus, in order to optimize the benefit from the invested human work, we argue that the decision on which predictive model one should employ depends not only on generalized evaluation metrics, such as accuracy and F-score, but also on the gain metric. The rationale is that, the model with the highest F-score may not necessarily have the best separation and sequencing of predicted classes, thus leading to the investment of more time and/or money on annotating false positives, yielding zero improvement of the linguistic resource. We exemplify our point with a case study, using real data from a task of building a verb-noun idiom dictionary. We show that in our scenario, given the choice of three systems with varying F-scores, the system with the highest F-score does not yield the highest profits. In other words, we show that the cost-benefit trade off can be more favorable if a system with a lower F-score is employed.
Keyword:
budget
;
Computational Engineering
;
Digital Humanities
;
F-score
;
gain
;
idiom dictionary
;
idiom identification
;
linguistic resource creation
;
model evaluation
;
Other Computer Engineering
URL:
https://arrow.tudublin.ie/cgi/viewcontent.cgi?article=1234&context=scschcomcon
https://arrow.tudublin.ie/scschcomcon/227
BASE
Hide details
13
Exploring the Functional and Geometric Bias of Spatial Relations Using Neural Language Models
Dobnik, Simon
;
Ghanimifard, Mehdi
;
Kelleher, John D.
In: Conference papers (2018)
BASE
Show details
14
Back to the Future: Logic and Machine Learning
Kelleher, John D.
;
Dobnik, Simon
In: Conference papers (2017)
BASE
Show details
15
Robot Perception Errors and Human Resolution Strategies in Situated Human-Robot Dialogue
Kelleher, John D.
;
Mac Namee, Brian
;
Schütte, Niels
In: Articles (2017)
BASE
Show details
16
Assessing the Usefulness of Different Feature Sets for Predicting the Comprehension Difficulty of Text
Mac Namee, Brian
;
Kelleher, John D.
;
Fitzpatrick, Noel
In: Conference papers (2017)
BASE
Show details
17
Towards a Computational Model of Frame of Reference Alignment in Swedish Dialogue
Dobnik, Simon
;
Howes, Christine
;
Kelleher, John D.
...
In: Conference papers (2016)
BASE
Show details
18
A Model for Attention-Driven Judgements in Type Theory with Records
Dobnik, Simon
;
Kelleher, John D.
In: Conference papers (2016)
BASE
Show details
19
Fundamentals of Machine Learning for Neural Machine Translation
Kelleher, John D.
In: Conference papers (2016)
BASE
Show details
20
Perception Based Misunderstandings in Human-Computer Dialogues
Schütte, Niels
;
Kelleher, John D.
;
Mac Namee, Brian
In: Articles (2014)
BASE
Show details
Page:
1
2
3
Mobile view
All
Catalogues
UB Frankfurt Linguistik
0
IDS Mannheim
0
OLC Linguistik
0
UB Frankfurt Retrokatalog
0
DNB Subject Category Language
0
Institut für Empirische Sprachwissenschaft
0
Leibniz-Centre General Linguistics (ZAS)
0
Bibliographies
BLLDB
0
BDSL
0
IDS Bibliografie zur deutschen Grammatik
0
IDS Bibliografie zur Gesprächsforschung
0
IDS Konnektoren im Deutschen
0
IDS Präpositionen im Deutschen
0
IDS OBELEX meta
0
MPI-SHH Linguistics Collection
0
MPI for Psycholinguistics
0
Linked Open Data catalogues
Annohub
0
Online resources
Link directory
0
Journal directory
0
Database directory
0
Dictionary directory
0
Open access documents
BASE
42
Linguistik-Repository
0
IDS Publikationsserver
0
Online dissertations
0
Language Description Heritage
0
© 2013 - 2024 Lin|gu|is|tik
|
Imprint
|
Privacy Policy
|
Datenschutzeinstellungen ändern