Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension
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.
Code (1)
Tasks
Cross-Lingual TransferDisentanglementMachine Reading ComprehensionReading ComprehensionZero-Shot Cross-Lingual TransferMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Motion-Guided Semantic Alignment with Negative Prompts for Zero-Shot Video Action Recognition
Zero-shot action recognition is challenging due to the semantic gap between seen and unseen classes. We present a novel framework that enhances CLIP with disentangled embeddings and semantic-guided interaction. A Motion …
Zero-Shot Action RecognitionDisentangling Semantic-to-visual Confusion for Zero-shot Learning
Using generative models to synthesize visual features from semantic distribution is one of the most popular solutions to ZSL image classification in recent years. The triplet loss (TL) is popularly used to generate reali…
Generative Adversarial Networkimage-classificationImage ClassificationTriplet+1ARC: Leveraging Compositional Representations for Cross-Problem Learning on VRPs
Vehicle Routing Problems (VRPs) with diverse real-world attributes have driven recent interest in cross-problem learning approaches that efficiently generalize across problem variants. We propose ARC (Attribute Represent…
Zero-shot GeneralizationConditional MoCoGAN for Zero-Shot Video Generation
We propose a conditional generative adversarial network (GAN) model for zero-shot video generation. In this study, we have explored zero-shot conditional generation setting. In other words, we generate unseen videos from…
Generative Adversarial NetworkImage GenerationVideo GenerationDisentangled Ontology Embedding for Zero-shot Learning
Knowledge Graph (KG) and its variant of ontology have been widely used for knowledge representation, and have shown to be quite effective in augmenting Zero-shot Learning (ZSL). However, existing ZSL methods that utilize…
image-classificationImage ClassificationOntology EmbeddingZero-Shot Image Classification+1