Data augmentation techniques have been widely used to improve machine learning performance as they enhance the generalization capability of models. In this work, to generate high quality synthetic data for low-resource tagging tasks, we propose a novel augmentation method with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings. For the supervised settings, we conduct extensive experiments on named entity recognition (NER), part of speech (POS) tagging and end-to-end target based sentiment analysis (E2E-TBSA) tasks. For the semi-supervised settings, we evaluate our method on the NER task under the conditions of given unlabeled data only and unlabeled data plus a knowledge base. The results show that our method can consistently outperform the baselines, particularly when the given gold training data are less. 1 * Equal contribution. Bosheng Ding and Linlin Liu are under the Joint PhD Program between Alibaba and Nanyang Technological University.
Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a downstream task. As such, it adds only a few trainable parameters per new task, allowing a high degree of parameter sharing. Prior studies have shown that adapter-based tuning often achieves comparable results to finetuning. However, existing work only focuses on the parameter-efficient aspect of adapterbased tuning while lacking further investigation on its effectiveness. In this paper, we study the latter. We first show that adapterbased tuning better mitigates forgetting issues than fine-tuning since it yields representations with less deviation from those generated by the initial PrLM. We then empirically compare the two tuning methods on several downstream NLP tasks and settings. We demonstrate that 1) adapter-based tuning outperforms fine-tuning on low-resource and cross-lingual tasks; 2) it is more robust to overfitting and less sensitive to changes in learning rates.
The development of hydrogen sensors is of paramount importance for timely leak detection and remains a crucial unmet need. Palladium‐based materials, well known as hydrogen sensors, still suffer from poisoning and deactivation. Here, a hybrid hydrogen sensor consisting of a Pd nanocluster (NC) film, a metal–organic framework (MOF), and a polymer, are proposed. The polymer coating, as a protection layer, endows the sensor with excellent H2 selectivity and CO‐poisoning resistance. The MOF serves as an interface layer between the Pd NC film and the polymer layer, which alters the nature of the interaction with hydrogen and leads to significant sensing performance improvements, owing to the interfacial electronic coupling between Pd NCs and the MOF. The strategy overcomes the shortcomings of retarded response speed and degraded sensitivity induced by the polymer coating of a Pd NC film–polymer hybrid system. This is the first exhibition of a hydrogen‐sensing enhancement mechanism achieved by engineering the electronic coupling between Pd and a MOF. The work establishes a deep understanding of the hydrogen‐sensing enhancement mechanism at the nanoscale and provides a feasible strategy to engineer next‐generation gas‐sensing nanodevices with superior sensing figures of merit via hybrid material systems.
Named Entity Recognition (NER) for lowresource languages is a both practical and challenging research problem. This paper addresses zero-shot transfer for cross-lingual NER, especially when the amount of sourcelanguage training data is also limited. The paper first proposes a simple but effective labeled sequence translation method to translate source-language training data to target languages and avoids problems such as word order change and entity span determination. With the source-language data as well as the translated data, a generation-based multilingual data augmentation method is introduced to further increase diversity by generating synthetic labeled data in multiple languages. These augmented data enable the language model based NER models to generalize better with both the language-specific features from the target-language synthetic data and the language-independent features from multilingual synthetic data. An extensive set of experiments were conducted to demonstrate encouraging cross-lingual transfer performance of the new research on a wide variety of target languages. 1 * Equal contribution, order decided by coin flip. Linlin Liu and Bosheng Ding are under the Joint PhD Program between Alibaba and Nanyang Technological University.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.