Related papers: Semi-Supervised Bilingual Lexicon Induction with T…
Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance…
We explore a novel approach to semi-supervised learning. This approach is contrary to the common approach in that the unlabeled examples serve to "muffle," rather than enhance, the guidance provided by the labeled examples. We provide…
This study discusses the effect of semi-supervised learning in combination with pretrained language models for data-to-text generation. It is not known whether semi-supervised learning is still helpful when a large-scale language model is…
Unpaired text and audio injection have emerged as dominant methods for improving ASR performance in the absence of a large labeled corpus. However, little guidance exists on deploying these methods to improve production ASR systems that are…
In this paper, we propose a novel active learning approach integrated with an improved semi-supervised learning framework to reduce the cost of manual annotation and enhance model performance. Our proposed approach effectively leverages…
We introduce a novel framework, called Interface Laplace learning, for graph-based semi-supervised learning. Motivated by the observation that an interface should exist between different classes where the function value is non-smooth, we…
The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-model (LM) pretraining, how we can make the best use of U is…
Although data is abundant, data labeling is expensive. Semi-supervised learning methods combine a few labeled samples with a large corpus of unlabeled data to effectively train models. This paper introduces our proposed method LiDAM, a…
Cross-lingual representation learning transfers knowledge from resource-rich data to resource-scarce ones to improve the semantic understanding abilities of different languages. However, previous works rely on shallow unsupervised data…
Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine translation. The key idea is guiding LLMs to generate translation with human-like feedback. However, existing self-reflection…
Semi-supervised learning, which leverages both annotated and unannotated data, is an efficient approach for medical image segmentation, where obtaining annotations for the whole dataset is time-consuming and costly. Traditional…
Transliterating related languages that use different scripts into a common script is effective for improving crosslingual transfer in downstream tasks. However, this methodology often makes pretraining a model from scratch unavoidable, as…
Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language. Recent developments which construct these embeddings…
Unsupervised representation learning aims at finding methods that learn representations from data without annotation-based signals. Abstaining from annotations not only leads to economic benefits but may - and to some extent already does -…
The ability of robots to manipulate objects relies heavily on their aptitude for visual perception. In domains characterized by cluttered scenes and high object variability, most methods call for vast labeled datasets, laboriously…
Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and…
Establishing dense correspondences across semantically similar images remains a challenging task due to the significant intra-class variations and background clutters. Traditionally, a supervised learning was used for training the models,…
Despite the remarkable performance of supervised medical image segmentation models, relying on a large amount of labeled data is impractical in real-world situations. Semi-supervised learning approaches aim to alleviate this challenge using…
The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…
The lack of labeled data is a major obstacle to learning high-quality sentence embeddings. Recently, self-supervised contrastive learning (SCL) is regarded as a promising way to address this problem. However, the existing works mainly rely…