1 |
Effective healthcare worker-patient communication in Hong Kong accident and emergency departments
|
|
|
|
In: Hong Kong Journal of Emergency Medicine (HKJEM) (2022)
|
|
BASE
|
|
Show details
|
|
3 |
AVQVC: One-shot Voice Conversion by Vector Quantization with applying contrastive learning ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
CREER: A Large-Scale Corpus for Relation Extraction and Entity Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Examining English Ability-Grouping Practices by Aligning CEFR Levels with University-Level General English Courses in Taiwan
|
|
|
|
In: Sustainability; Volume 14; Issue 8; Pages: 4629 (2022)
|
|
BASE
|
|
Show details
|
|
11 |
A Survey of Automatic Source Code Summarization
|
|
|
|
In: Symmetry; Volume 14; Issue 3; Pages: 471 (2022)
|
|
BASE
|
|
Show details
|
|
12 |
Improving Recruitment for a Newborn Screening Pilot Study with Adaptations in Response to the COVID-19 Pandemic
|
|
|
|
In: International Journal of Neonatal Screening; Volume 8; Issue 2; Pages: 23 (2022)
|
|
BASE
|
|
Show details
|
|
13 |
Primary Pupils’ Multimodal Representations in Worksheets—Text Work in Science Education
|
|
|
|
In: Education Sciences; Volume 12; Issue 3; Pages: 221 (2022)
|
|
BASE
|
|
Show details
|
|
16 |
Disambiguation of morpho-syntactic features of African American English -- the case of habitual be ...
|
|
|
|
Abstract:
Recent research has highlighted that natural language processing (NLP) systems exhibit a bias against African American speakers. The bias errors are often caused by poor representation of linguistic features unique to African American English (AAE), due to the relatively low probability of occurrence of many such features in training data. We present a workflow to overcome such bias in the case of habitual "be". Habitual "be" is isomorphic, and therefore ambiguous, with other forms of "be" found in both AAE and other varieties of English. This creates a clear challenge for bias in NLP technologies. To overcome the scarcity, we employ a combination of rule-based filters and data augmentation that generate a corpus balanced between habitual and non-habitual instances. With this balanced corpus, we train unbiased machine learning classifiers, as demonstrated on a corpus of AAE transcribed texts, achieving .65 F$_1$ score disambiguating habitual "be". ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2204.12421 https://arxiv.org/abs/2204.12421
|
|
BASE
|
|
Hide details
|
|
17 |
Chinese Word Segmentation with Heterogeneous Graph Neural Network ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
(18)F-FDG PET/CT and PET/MRI fusion imaging for neuroendocrine carcinoma of the tongue: A case report
|
|
|
|
In: Radiol Case Rep (2022)
|
|
BASE
|
|
Show details
|
|
|
|