DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5...26
Hits 1 – 20 of 511

1
Interference in processing of Czech intraclausal garden-path structures - yes/no questions ...
Chromý, Jan. - : Open Science Framework, 2022
BASE
Show details
2
Agreement attraction in English and Czech: A direct experimental comparison ...
Lacina, Radim. - : Open Science Framework, 2022
BASE
Show details
3
Investigating the Effect of Context on Sentence Comprehension ...
Chen, Sihan. - : Open Science Framework, 2022
BASE
Show details
4
Interference in processing of Czech intraclausal garden-path structures - open-ended questions ...
Chromý, Jan. - : Open Science Framework, 2022
BASE
Show details
5
Measuring and Comparing Social Bias in Static and Contextual Word Embeddings
Mora, Alan Cueva. - : Technological University Dublin, 2022
In: Dissertations (2022)
Abstract: Word embeddings have been considered one of the biggest breakthroughs of deep learning for natural language processing. They are learned numerical vector representations of words where similar words have similar representations. Contextual word embeddings are the promising second-generation of word embeddings assigning a representation to a word based on its context. This can result in different representations for the same word depending on the context (e.g. river bank and commercial bank). There is evidence of social bias (human-like implicit biases based on gender, race, and other social constructs) in word embeddings. While detecting bias in static (classical or non-contextual) word embeddings is a well-researched topic, there has been limited work in detecting bias in contextual word embeddings, mostly focussed on using the Word Embedding Association Test (WEAT). This paper explores measuring social bias (gender, ethnicity, and religion) in contextual word embeddings using a number of fairness metrics, including the Relative Norm Distance (RND), the Relative Negative Sentiment Bias (RNSB) and the already mentioned WEAT. It extends the Word Embeddings Fairness Evaluation (WEFE) framework to facilitate measuring social biases in contextual embeddings and compares these with biases in static word embeddings. The results show when ranking performance over a number of fairness metrics that contextual word embedding pre-trained models BERT and RoBERTa have more social bias than static word embedding pre-trained models GloVe and Word2Vec.
Keyword: Computer Engineering; Computer Sciences; Contextual Word Embeddings; Fairness Evaluation; Natural Language Processing; Sentence Embeddings; Social Bias; Word Embeddings
URL: https://arrow.tudublin.ie/scschcomdis/250
https://arrow.tudublin.ie/cgi/viewcontent.cgi?article=1267&context=scschcomdis
BASE
Hide details
6
Effect of Lexical-Semantic Cues during Real-Time Sentence Processing in Aphasia
In: Brain Sciences; Volume 12; Issue 3; Pages: 312 (2022)
BASE
Show details
7
Use of Parsing Heuristics in the Comprehension of Passive Sentences: Evidence from Dyslexia and Individual Differences
In: Brain Sciences; Volume 12; Issue 2; Pages: 209 (2022)
BASE
Show details
8
A perceptual study of language chunking in Estonian
In: Open Linguistics, Vol 8, Iss 1, Pp 1-26 (2022) (2022)
BASE
Show details
9
Verb-second as a reconstruction phenomenon : evidence from grammar and processing
Leibniz-Zentrum Allgemeine Sprachwissenschaft
Show details
10
The Role of Prosodic Phrasing on the Acceptability of Agreement Attraction in English
Royer, Adam Joseph. - : eScholarship, University of California, 2021
BASE
Show details
11
How sentence processing sheds light on mixed language creation
In: New Perspectives on Mixed Languages. From Core to Fringe ; https://halshs.archives-ouvertes.fr/halshs-02442565 ; Eeva Sippola; Maria Mazzoli. New Perspectives on Mixed Languages. From Core to Fringe, De Gruyter, In press, 978-1-5015-1125-7 ; https://www.degruyter.com/view/product/511911 (2021)
BASE
Show details
12
Dialect effects on morphosyntactic agreement interpretation ...
Maher, Zachary. - : Open Science Framework, 2021
BASE
Show details
13
Adjectival polarity and the processing of scalar inferences
In: Glossa: a journal of general linguistics; Vol 6, No 1 (2021); 32 ; 2397-1835 (2021)
BASE
Show details
14
When missing NPs make double center-embedding sentences acceptable
In: Glossa: a journal of general linguistics; Vol 6, No 1 (2021); 37 ; 2397-1835 (2021)
BASE
Show details
15
Gender attraction in sentence comprehension
In: Glossa: a journal of general linguistics; Vol 6, No 1 (2021); 20 ; 2397-1835 (2021)
BASE
Show details
16
Processing of intraclausal garden-path structures in Czech - yes/no questions (11/2021) ...
Chromý, Jan. - : Open Science Framework, 2021
BASE
Show details
17
Plausibility and recall of information of transitive sentences in Czech: open-ended questions experiment (December 2021) ...
Chromý, Jan. - : Open Science Framework, 2021
BASE
Show details
18
Cognitive control adaptation and syntactic ambiguity ...
Kaan, Edith. - : Open Science Framework, 2021
BASE
Show details
19
Visual Gating ...
Schlenter, Judith. - : Open Science Framework, 2021
BASE
Show details
20
Processing of intraclausal garden-path structures in Czech - open-ended questions ...
Chromý, Jan. - : Open Science Framework, 2021
BASE
Show details

Page: 1 2 3 4 5...26

Catalogues
6
0
8
0
0
0
1
Bibliographies
37
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
473
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern