DE eng

Search in the Catalogues and Directories

Page: 1 2 3
Hits 1 – 20 of 56

1
EMBEDDIA tools output example corpus of Estonian, Croatian and Latvian news articles 1.0
Freienthal, Linda; Pelicon, Andraž; Martinc, Matej. - : Ekspress Meedia Group, 2022. : Styria Media Group, 2022
BASE
Show details
2
Not All Comments Are Equal: Insights into Comment Moderation from a Topic-aware Model ...
BASE
Show details
3
Not All Comments Are Equal: Insights into Comment Moderation from a Topic-aware Model ...
BASE
Show details
4
Ekspress news article archive (in Estonian and Russian) 1.0
Purver, Matthew; Pollak, Senja; Freienthal, Linda. - : Ekspress Meedia Group, 2021
BASE
Show details
5
Latvian user comment dataset 1.0
Shekhar, Ravi; Purver, Matthew; Pollak, Senja. - : Ekspress Meedia Group, 2021
BASE
Show details
6
24sata news comment dataset 1.0
Shekhar, Ravi; Pranjic, Marko; Pollak, Senja. - : Styria Media Group, 2021
BASE
Show details
7
24sata news article archive 1.0
Purver, Matthew; Shekhar, Ravi; Pranjić, Marko. - : Styria Media Group, 2021
BASE
Show details
8
Latvian Delfi article archive (in Latvian and Russian) 1.0
Pollak, Senja; Purver, Matthew; Shekhar, Ravi. - : Ekspress Meedia Group, 2021
BASE
Show details
9
Evaluation of contextual embeddings on less-resourced languages ...
BASE
Show details
10
A Longitudinal Multi-modal Dataset for Dementia Monitoring and Diagnosis ...
BASE
Show details
11
Not All Comments are Equal: Insights into Comment Moderation from a Topic-Aware Model ...
BASE
Show details
12
Not All Comments are Equal: Insights into Comment Moderation from a Topic-Aware Model ...
BASE
Show details
13
Not all comments are equal: Insights into comment moderation from a topic-aware model ...
BASE
Show details
14
Not All Comments are Equal: Insights into Comment Moderation from a Topic-Aware Model ...
BASE
Show details
15
Not all comments are equal: Insights into comment moderation from a topic-aware model ...
BASE
Show details
16
Linguistic Creativity III ...
BASE
Show details
17
Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer's Dementia recognition from spontaneous speech ...
BASE
Show details
18
Towards Robustness of Text-to-SQL Models against Synonym Substitution ...
Abstract: Recently, there has been significant progress in studying neural networks to translate text descriptions into SQL queries. Despite achieving good performance on some public benchmarks, existing text-to-SQL models typically rely on the lexical matching between words in natural language (NL) questions and tokens in table schemas, which may render the models vulnerable to attacks that break the schema linking mechanism. In this work, we investigate the robustness of text-to-SQL models to synonym substitution. In particular, we introduce Spider-Syn, a human-curated dataset based on the Spider benchmark for text-to-SQL translation. NL questions in Spider-Syn are modified from Spider, by replacing their schema-related words with manually selected synonyms that reflect real-world question paraphrases. We observe that the accuracy dramatically drops by eliminating such explicit correspondence between NL questions and table schemas, even if the synonyms are not adversarially selected to conduct worst-case adversarial ... : To appear in ACL 2021 ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://arxiv.org/abs/2106.01065
https://dx.doi.org/10.48550/arxiv.2106.01065
BASE
Hide details
19
Alzheimer's Dementia Recognition Using Acoustic, Lexical, Disfluency and Speech Pause Features Robust to Noisy Inputs ...
BASE
Show details
20
Investigating cross-lingual training for offensive language detection
In: PeerJ Comput Sci (2021)
BASE
Show details

Page: 1 2 3

Catalogues
1
0
3
0
1
0
1
Bibliographies
8
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
45
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern