PseudoLabels
Related Papers
Self-Adaptation for Unsupervised Domain Adaptation
AbstractLack of labelled data in the target domain for training is a common problem in domain adaptation. To overcome this problem, we propose a novel unsupervised domain adaptation method that …...
Maastricht University’s Multilingual Speech Translation System for IWSLT 2021
AbstractThis paper describes Maastricht University’s participation in the IWSLT 2021 multilingual speech translation track. The task in this track is to build multilingual speech translation systems in supervised and zero-shot …...
MetaTS: Meta Teacher-Student Network for Multilingual Sequence Labeling with Minimal Supervision
AbstractSequence labeling aims to predict a fine-grained sequence of labels for the text. However, such formulation hinders the effectiveness of supervised methods due to the lack of token-level annotated data. …...
Semi-Supervised Text Classification with Balanced Deep Representation Distributions
AbstractSemi-Supervised Text Classification (SSTC) mainly works under the spirit of self-training. They initialize the deep classifier by training over labeled texts; and then alternatively predict unlabeled texts as their pseudo-labels …...
Cluster-aware Pseudo-Labeling for Supervised Open Relation Extraction
AbstractSupervised open relation extraction aims to discover novel relations by leveraging supervised data of pre-defined relations. However, most existing methods do not achieve effective knowledge transfer from pre-defined relations to …...
Enhancing Task-Specific Distillation in Small Data Regimes through Language Generation
AbstractLarge-scale pretrained language models have led to significant improvements in Natural Language Processing. Unfortunately, they come at the cost of high computational and storage requirements that complicate their deployment on …...
Intent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive Clustering
AbstractIntent Detection is a crucial component of Dialogue Systems wherein the objective is to classify a user utterance into one of multiple pre-defined intents. A pre-requisite for developing an effective …...
QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation
AbstractQuestion answering (QA) has recently shown impressive results for answering questions from customized domains. Yet, a common challenge is to adapt QA models to an unseen target domain. In this …...
ComSearch: Equation Searching with Combinatorial Strategy for Solving Math Word Problems with Weak Supervision
AbstractPrevious studies have introduced a weakly-supervised paradigm for solving math word problems requiring only the answer value annotation. While these methods search for correct value equation candidates as pseudo labels, …...
Simple and Effective Unsupervised Speech Translation
AbstractThe 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 …...
Uncertainty Guided Label Denoising for Document-level Distant Relation Extraction
AbstractDocument-level relation extraction (DocRE) aims to infer complex semantic relations among entities in a document. Distant supervision (DS) is able to generate massive auto-labeled data, which can improve DocRE performance. …...