1 |
Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension ...
|
|
|
|
Abstract:
Multilingual pre-trained models are able to zero-shot transfer knowledge from rich-resource to low-resource languages in machine reading comprehension (MRC). However, inherent linguistic discrepancies in different languages could make answer spans predicted by zero-shot transfer violate syntactic constraints of the target language. In this paper, we propose a novel multilingual MRC framework equipped with a Siamese Semantic Disentanglement Model (SSDM) to disassociate semantics from syntax in representations learned by multilingual pre-trained models. To explicitly transfer only semantic knowledge to the target language, we propose two groups of losses tailored for semantic and syntactic encoding and disentanglement. Experimental results on three multilingual MRC datasets (i.e., XQuAD, MLQA, and TyDi QA) demonstrate the effectiveness of our proposed approach over models based on mBERT and XLM-100. Code is available at:https://github.com/wulinjuan/SSDM_MRC. ... : Accepted to ACL 2022 (main conference) ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2204.00996 https://arxiv.org/abs/2204.00996
|
|
BASE
|
|
Hide details
|
|
2 |
CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Bridging between Cognitive Processing Signals and Linguistic Features via a Unified Attentional Network ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Chinese WPLC: A Chinese Dataset for Evaluating Pretrained Language Models on Word Prediction Given Long-Range Context ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Modeling Homophone Noise for Robust Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Merging External Bilingual Pairs into Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Fusing Recency into Neural Machine Translation with an Inter-Sentence Gate Model ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
BattRAE: Bidimensional Attention-Based Recursive Autoencoders for Learning Bilingual Phrase Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Combining documentation and research: ongoing work on an endangered language
|
|
|
|
In: Proceedings of IALP 2012 (2012 International Conference on Asian Language Processing) ; IALP 2012 (2012 International Conference on Asian Language Processing) ; https://halshs.archives-ouvertes.fr/halshs-00731261 ; IALP 2012 (2012 International Conference on Asian Language Processing), 2012, Hanoi, Vietnam. pp.169-172 (2012)
|
|
BASE
|
|
Show details
|
|
20 |
Combining documentation and research: ongoing work on an endangered language
|
|
|
|
In: Proceedings of IALP 2012 (2012 International Conference on Asian Language Processing) ; IALP 2012 (2012 International Conference on Asian Language Processing) ; https://halshs.archives-ouvertes.fr/halshs-00731261 ; IALP 2012 (2012 International Conference on Asian Language Processing), 2012, Hanoi, Vietnam. pp.169-172 (2012)
|
|
BASE
|
|
Show details
|
|
|
|