相关论文: Model and Data Transfer for Cross-Lingual Sequence…

Named entity recognition (NER) suffers from the scarcity of annotated training data, especially for low-resource languages without labeled data. Cross-lingual NER has been proposed to alleviate this issue by transferring knowledge from…

This paper describes our submission of the WMT 2020 Shared Task on Sentence Level Direct Assessment, Quality Estimation (QE). In this study, we empirically reveal the \textit{mismatching issue} when directly adopting BERTScore to QE.…

Pretrained language models have shown success in various areas of natural language processing, including reading comprehension tasks. However, when applying machine learning methods to new domains, labeled data may not always be available.…

There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of these models with restricted data. Whisper, a speech…

Multi-label zero-shot classification aims to predict multiple unseen class labels for an input image. It is more challenging than its single-label counterpart. On one hand, the unconstrained number of labels assigned to each image makes the…

Current multimodal machine translation (MMT) systems rely on fully supervised data (i.e models are trained on sentences with their translations and accompanying images). However, this type of data is costly to collect, limiting the…

Labeled audio data is insufficient to build satisfying speech recognition systems for most of the languages in the world. There have been some zero-resource methods trying to perform phoneme or word-level speech recognition without labeled…

Pre-trained multilingual language models show significant performance gains for zero-shot cross-lingual model transfer on a wide range of natural language understanding (NLU) tasks. Previously, for zero-shot cross-lingual evaluation,…

Music classification and tagging is conducted through categorical supervised learning with a fixed set of labels. In principle, this cannot make predictions on unseen labels. Zero-shot learning is an approach to solve the problem by using…

Manually annotated corpora for low-resource languages are usually small in quantity (gold), or large but distantly supervised (silver). Inspired by recent progress of injecting pre-trained language model (LM) on many Natural Language…

Multilingual Large Language Models (LLMs) achieve remarkable levels of zero-shot cross-lingual transfer performance. We speculate that this is predicated on their ability to align languages without explicit supervision from parallel…

Multilingual Neural Machine Translation (NMT) models are capable of translating between multiple source and target languages. Despite various approaches to train such models, they have difficulty with zero-shot translation: translating…

We study the zero-shot transfer capabilities of text matching models on a massive scale, by self-supervised training on 140 source domains from community question answering forums in English. We investigate the model performances on nine…

Statements on social media can be analysed to identify individuals who are experiencing red flag medical symptoms, allowing early detection of the spread of disease such as influenza. Since disease does not respect cultural borders and may…

Cross-lingual semantic parsing transfers parsing capability from a high-resource language (e.g., English) to low-resource languages with scarce training data. Previous work has primarily considered silver-standard data augmentation or…

Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalise methods for unsupervised transfer from multiple input…

Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-byword matching. Such requirements and assumptions are infeasible for most languages, especially for languages…

Recently, end-to-end speech translation (ST) has gained significant attention as it avoids error propagation. However, the approach suffers from data scarcity. It heavily depends on direct ST data and is less efficient in making use of…

Many language pairs are low resource, meaning the amount and/or quality of available parallel data is not sufficient to train a neural machine translation (NMT) model which can reach an acceptable standard of accuracy. Many works have…

Recent speech technologies have led to produce high quality synthesised speech due to recent advances in neural Text to Speech (TTS). However, such TTS models depend on extensive amounts of data that can be costly to produce and is hardly…