1 |
GL-CLeF: A Global-Local Contrastive Learning Framework for Cross-lingual Spoken Language Understanding ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Improving Pre-trained Language Models with Syntactic Dependency Prediction Task for Chinese Semantic Error Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
ExpMRC: explainability evaluation for machine reading comprehension
|
|
|
|
In: Heliyon (2022)
|
|
BASE
|
|
Show details
|
|
4 |
Multilingual multi-aspect explainability analyses on machine reading comprehension models
|
|
|
|
In: iScience (2022)
|
|
BASE
|
|
Show details
|
|
5 |
Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training ...
|
|
|
|
Abstract:
Compared to monolingual models, cross-lingual models usually require a more expressive vocabulary to represent all languages adequately. We find that many languages are under-represented in recent cross-lingual language models due to the limited vocabulary capacity. To this end, we propose an algorithm VoCap to determine the desired vocabulary capacity of each language. However, increasing the vocabulary size significantly slows down the pre-training speed. In order to address the issues, we propose k-NN-based target sampling to accelerate the expensive softmax. Our experiments show that the multilingual vocabulary learned with VoCap benefits cross-lingual language model pre-training. Moreover, k-NN-based target sampling mitigates the side-effects of increasing the vocabulary size while achieving comparable performance and faster pre-training speed. The code and the pretrained multilingual vocabularies are available at https://github.com/bozheng-hit/VoCapXLM. ... : EMNLP 2021 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2109.07306 https://dx.doi.org/10.48550/arxiv.2109.07306
|
|
BASE
|
|
Hide details
|
|
7 |
Bilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
A Closer Look into the Robustness of Neural Dependency Parsers Using Better Adversarial Examples ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
N-LTP: An Open-source Neural Language Technology Platform for Chinese ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|