Articles

This paper describes the ROCLING-2023 shared task for Chinese multi-genre named entity recognition in the healthcare domain, including task description, data preparation, performance metrics, and evaluation results. Among eight registered teams, six participating teams submitted a total of 16 runs. This shared task demonstrates current NLP techniques for dealing with …...

AbstractThis paper is a brief summary of the First WMT Shared Task on Sign Language Translation (WMT-SLT22), a project partly funded by EAMT. The focus of this shared task is automatic translation between signed and spoken languages. Details can be found on our website (https://www.wmt-slt.com/) or in the findings paper …...

AbstractThis paper proposes a novel approach to French patent classification leveraging data-centric strategies. We compare different approaches for the two deepest levels of the IPC hierarchy: the IPC group and subgroups. Our experiments show that while simple ensemble strategies work for shallower levels, deeper levels require more sophisticated techniques such …...

This study focuses on the adaptation and training of the Whisper model using the provided data and text annotations from the FSR-2023 Hakka Speech Recognition Challenge. The Whisper model is based on the Transformer architecture with a self- attention mechanism. Its diverse data and weakly labeled multitask training make it …...

Deep learning-based automatic speech recognition (ASR) design has been grow- ing in popularity. Besides the ASR model depends on the reliable speech representa- tion offered by the self-supervised learn- ing (SSL) model, Whisper is also a pow- erful model that makes use of the knowl- edge from large-scale labeled datasets …...

This paper is a preliminary study on Hakka speech recognition using the end-to-end Branchformer framework provided by the ESPnet. Two types of recognition targets were tested: character and Hakka pinyin. The experimental result showed that the Branchformer for the Hakka speech recog- nition pre-trained with the large Man- darin speech …...

This paper introduces the architecture and training approach of the Taiwan AI Labs Hakka automatic speech recognition (ASR) system for the Formosa Speech Recognition Challenge 2023 (FSR2023). Overall, this Hakka ASR system consists of an acoustic model trained based on the HuBERT (Hsu et al., 2021) model and a 5-gram …...

In this study, we present a novel ap- proach to enhancing the performance of our Hakka Automatic Speech Recognition (ASR) model through the strategic use of Text-to-Speech (TTS) amplification tech- niques. Our investigation explores the inte- gration of diverse speakers to expand our training dataset, leading to a notable re- …...

Language preservation has become increasingly urgent with globalization and rapid technological advancement. Minority languages, such as Hakka, are particularly vulnerable. This study aims to expedite the research and development of Hakka speech recognition by integrating Open AI's Whisper model with online Hakka speech resources. This study developed an efficient speech …...

In this research, we utilized the training dataset from the ROCLING 2023 Chinese Multi-genre Named Entity Recognition in the Healthcare Domain, which comprises the Chi- nese HealthNER Corpus (Lee and Lu, 2021) and the ROCLING 2022 CHNER Dataset (Lee et al., 2022), along with the test set (Lee et al., …...

This report provides a concise overview of the proposed North system, which aims to achieve automatic word/syllable recognition for Tai- wanese Hakka (Sixian). The report outlines three key components of the system: the acqui- sition, composition, and utilization of the train- ing data; the architecture of the model; and the …...

Medical Named Entity Recognition (NER) stands as a pivotal technique within the realm of medicine, cate sequence labeling.encompassing intri- Profound medi- cal knowledge acumen and accurate de- marcation of entity boundaries constitute the principal challenges of this task. In contrast to the English context, Chinese medical NER poses even greater …...

In this study, the speech recognition sys- tem will be introduced, used by NSYSU- MITLab, for Formosa Speech Recogni- tion Challenge 2023. We use the pre- trained model wav2vec2.0 as the frontend module in both the Enhanced Branch- former system and the Dynamic convolu- tion Enhanced Branchformer system. The Dynamic …...

AbstractNeural language models play an increasingly central role for language processing, given their success for a range of NLP tasks. In this study, we compare some canonical strategies in language modeling for low-resource scenarios, evaluating all models by their (finetuned) performance on a POS-tagging downstream task. We work with five …...

Named entity recognition (NER) is a sub- task in the field of information extraction in natural language processing (NLP). Its main goal is to recognize named entities in text and classify them into predefined categories. In the medical field, NER technology is used to automatically iden- tify medical-related entities, such …...

Chinese healthcare NER is an essential task in natural language processing to automatically identify healthcare entities such as symptoms, chemicals, diseases, and treatments for machine reading and understanding. Previous studies used Bi-directional Long Short-Term Memory (BiLSTM) and Conditional Random Fields (CRF) to solve NER tasks. This paper uses the RoBERTa-large …...

The demand for sequence segmentation and tagging has recently extended to different professional fields. The most commonly used model in conventional solutions is Bidirectional Long Short-Term Memory-Conditional Random Fields (Bi- LSTM-CRF), which combines deep learning and supervised learning. As the importance of unsupervised learning has become equal to that of …...

In this research, we comprehensively ana- lyze the potential biases inherent in Large Language Model, utilizing meticulously cu- rated input data to ascertain the extent to which such data sway machine-generated responses to yield prejudiced outcomes. Notwithstanding recent strides in mitigat- ing bias in LLM-based NLP, our findings underscore the …...

Lexical complexity is crucial for reading comprehension. In the past, research work of lexical complexity prediction mainly focuses on differentiating the complexity difference between two words. Moreover, most of the previous lexical complexity prediction approaches only consider traditional lexically relevant features. In this paper, we propose a novel supervised approach …...

In this study, we delve into the efficacy of the Tree-of-Thought Prompting technique as a mechanism to address linguistic challenges and augment the reasoning capabilities of expansive language models. Specifically, we scrutinize the reasoning prowess of the Generative Pre-trained Transformer (GPT) model, which has garnered significant at- tention within the …...