1 |
Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Fostering Teachers’ Multicultural Competence for Chinese Ethnic Minority Education: An Analysis of Teacher Education Programmes, Syllabuses and Teacher Educator Perceptions
|
|
|
|
In: Front Psychol (2022)
|
|
BASE
|
|
Show details
|
|
4 |
國小一年級新住民學生注音符號教學之行動研究 ; Action Research on Teaching First-Grade New Immigrant Students Mandarin Phonetic Symbols
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Locate then Segment: A Strong Pipeline for Referring Image Segmentation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
A Dataset and Baselines for Multilingual Reply Suggestion ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
StructuralLM: Structural Pre-training for Form Understanding ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Mendelian randomization suggests that head circumference, but not birth weight and length, associates with intelligence
|
|
|
|
In: Brain Behav (2021)
|
|
BASE
|
|
Show details
|
|
12 |
Exploration of simulation-based medical education for undergraduate students
|
|
|
|
In: Medicine (Baltimore) (2021)
|
|
BASE
|
|
Show details
|
|
13 |
Causal relationships between genetically determined metabolites and human intelligence: a Mendelian randomization study
|
|
|
|
In: Mol Brain (2021)
|
|
BASE
|
|
Show details
|
|
18 |
"The Boating Store Had Its Best Sail Ever": Pronunciation-attentive Contextualized Pun Recognition ...
|
|
|
|
Abstract:
Humor plays an important role in human languages and it is essential to model humor when building intelligence systems. Among different forms of humor, puns perform wordplay for humorous effects by employing words with double entendre and high phonetic similarity. However, identifying and modeling puns are challenging as puns usually involved implicit semantic or phonological tricks. In this paper, we propose Pronunciation-attentive Contextualized Pun Recognition (PCPR) to perceive human humor, detect if a sentence contains puns and locate them in the sentence. PCPR derives contextualized representation for each word in a sentence by capturing the association between the surrounding context and its corresponding phonetic symbols. Extensive experiments are conducted on two benchmark datasets. Results demonstrate that the proposed approach significantly outperforms the state-of-the-art methods in pun detection and location tasks. In-depth analyses verify the effectiveness and robustness of PCPR. ... : 10 pages, 4 figures, 7 tables, accepted by ACL 2020 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2004.14457 https://arxiv.org/abs/2004.14457
|
|
BASE
|
|
Hide details
|
|
19 |
VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|