相关论文: Multilingual BERT Post-Pretraining Alignment

In this paper, we show that Multilingual BERT (M-BERT), released by Devlin et al. (2018) as a single language model pre-trained from monolingual corpora in 104 languages, is surprisingly good at zero-shot cross-lingual model transfer, in…

We propose a novel approach for cross-lingual Named Entity Recognition (NER) zero-shot transfer using parallel corpora. We built an entity alignment model on top of XLM-RoBERTa to project the entities detected on the English part of the…

This paper presents M3L-Contrast -- a novel multimodal multilingual (M3L) neural topic model for comparable data that maps texts from multiple languages and images into a shared topic space. Our model is trained jointly on texts and images…

Pre-training large-scale neural language models on raw texts has made a significant contribution to improving transfer learning in natural language processing (NLP). With the introduction of transformer-based language models, such as…

Recent work has shown the surprising ability of multi-lingual BERT to serve as a zero-shot cross-lingual transfer model for a number of language processing tasks. We combine this finding with a similarly-recently proposal on sentence-level…

We test similarity-based word alignment models (SimAlign and awesome-align) in combination with word embeddings from mBERT and XLM-R on parallel sentences in German and Romansh. Since Romansh is an unseen language, we are dealing with a…

With hundreds of multilingual embedding models available, practitioners lack clear guidance on which provide genuine cross-lingual semantic alignment versus task performance through language-specific patterns. Task-driven benchmarks (MTEB)…

Despite their remarkable ability to capture linguistic nuances across diverse languages, questions persist regarding the degree of alignment between languages in multilingual embeddings. Drawing inspiration from research on high-dimensional…

Pre-training text representations has recently been shown to significantly improve the state-of-the-art in many natural language processing tasks. The central goal of pre-training is to learn text representations that are useful for…

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

Unsupervised cross-lingual transfer involves transferring knowledge between languages without explicit supervision. Although numerous studies have been conducted to improve performance in such tasks by focusing on cross-lingual knowledge,…

We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of…

Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from…

Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…

Multilingual machine translation enables a single model to translate between different languages. Most existing multilingual machine translation systems adopt a randomly initialized Transformer backbone. In this work, inspired by the recent…

Language model pre-training has shown promising results in various downstream tasks. In this context, we introduce a cross-modal pre-trained language model, called Speech-Text BERT (ST-BERT), to tackle end-to-end spoken language…

A variety of contextualised language models have been proposed in the NLP community, which are trained on diverse corpora to produce numerous Neural Language Models (NLMs). However, different NLMs have reported different levels of…

Cross-lingual adaptation with multilingual pre-trained language models (mPTLMs) mainly consists of two lines of works: zero-shot approach and translation-based approach, which have been studied extensively on the sequence-level tasks. We…

An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of back-translations of the target-side monolingual data. Recently, iterative back-translation…

The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences. In this paper, we introduce denoising word alignment as a new cross-lingual pre-training task.…