Related papers: UniPSDA: Unsupervised Pseudo Semantic Data Augment…

This paper explores augmenting monolingual data for knowledge distillation in neural machine translation. Source language monolingual text can be incorporated as a forward translation. Interestingly, we find the best way to incorporate…

Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks. However, to obtain better performance, former methods have higher demands for pseudo-data of the previous tasks. The performance…

Unsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic segmentation in particular, it helps deploy on real "target domain" data models that are…

Although word-level prosody modeling in neural text-to-speech (TTS) has been investigated in recent research for diverse speech synthesis, it is still challenging to control speech synthesis manually without a specific reference. This is…

In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…

Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or…

Exploiting cross-lingual resources is an effective way to compensate for data scarcity of low resource languages. Recently, a novel multilingual model fusion technique has been proposed where a model is trained to learn cross-lingual…

Cross-lingual word embeddings aim to capture common linguistic regularities of different languages, which benefit various downstream tasks ranging from machine translation to transfer learning. Recently, it has been shown that these…

Paraphrasing exemplifies the ability to abstract semantic content from surface forms. Recent work on automatic paraphrasing is dominated by methods leveraging Machine Translation (MT) as an intermediate step. This contrasts with humans, who…

Multilingual pre-trained language models (MPLMs) not only can handle tasks in different languages but also exhibit surprising zero-shot cross-lingual transferability. However, MPLMs usually are not able to achieve comparable supervised…

Recent work in cross-lingual semantic parsing has successfully applied machine translation to localize parsers to new languages. However, these advances assume access to high-quality machine translation systems and word alignment tools. We…

Named entity recognition (NER) is a fundamental component in many applications, such as Web Search and Voice Assistants. Although deep neural networks greatly improve the performance of NER, due to the requirement of large amounts of…

Unsupervised Neural Machine Translation (UNMT) focuses on improving NMT results under the assumption there is no human translated parallel data, yet little work has been done so far in highlighting its advantages compared to supervised…

Cross-lingual knowledge transfer is critical for building high-performing multilingual language models for languages with insufficient training data. When target language data is scarce, the knowledge required for many downstream tasks…

Unsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs. However, it can only translate between a single language pair and cannot produce translation results for multiple language…

Unsupervised domain adaptation for semantic segmentation (DASS) aims to transfer knowledge from a label-rich source domain to a target domain with no labels. Two key approaches in DASS are (1) vision-only approaches using masking or…

Joint representation learning of words and entities benefits many NLP tasks, but has not been well explored in cross-lingual settings. In this paper, we propose a novel method for joint representation learning of cross-lingual words and…

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and…

Dense retrievers have made significant strides in text retrieval and open-domain question answering. However, most of these achievements have relied heavily on extensive human-annotated supervision. In this study, we aim to develop…

Computing universal distributed representations of sentences is a fundamental task in natural language processing. We propose ConsSent, a simple yet surprisingly powerful unsupervised method to learn such representations by enforcing…