2 |
On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Genre as Weak Supervision for Cross-lingual Dependency Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
DaN+: Danish Nested Named Entities and Lexical Normalization ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding ...
|
|
van der Goot, Rob; Sharaf, Ibrahim; Imankulova, Aizhan; Üstün, Ahmet; Stepanović, Marija; Ramponi, Alan; Khairunnisa, Siti Oryza; Komachi, Mamoru; Plank, Barbara. - : arXiv, 2021
|
|
Abstract:
The lack of publicly available evaluation data for low-resource languages limits progress in Spoken Language Understanding (SLU). As key tasks like intent classification and slot filling require abundant training data, it is desirable to reuse existing data in high-resource languages to develop models for low-resource scenarios. We introduce xSID, a new benchmark for cross-lingual Slot and Intent Detection in 13 languages from 6 language families, including a very low-resource dialect. To tackle the challenge, we propose a joint learning approach, with English SLU training data and non-English auxiliary tasks from raw text, syntax and translation for transfer. We study two setups which differ by type and language coverage of the pre-trained embeddings. Our results show that jointly learning the main tasks with masked language modeling is effective for slots, while machine translation transfer works best for intent classification. ... : To appear in the proceedings of NAACL 2021 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2105.07316 https://dx.doi.org/10.48550/arxiv.2105.07316
|
|
BASE
|
|
Hide details
|
|
6 |
Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Universal Dependencies 2.2
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-01930733 ; 2018 (2018)
|
|
BASE
|
|
Show details
|
|
8 |
Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
The Best of Both Worlds: Lexical Resources To Improve Low-Resource Part-of-Speech Tagging ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Bleaching Text: Abstract Features for Cross-lingual Gender Prediction ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Universal Dependencies 2.1
|
|
|
|
In: https://hal.inria.fr/hal-01682188 ; 2017 (2017)
|
|
BASE
|
|
Show details
|
|
13 |
ALL-IN-1: Short Text Classification with One Model for All Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
TwiSty: a multilingual Twitter Stylometry corpus for gender and personality profiling ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
TwiSty: a multilingual Twitter Stylometry corpus for gender and personality profiling ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Keystroke dynamics as signal for shallow syntactic parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|