检索结果-内蒙古大学图书馆

Joint 30th International Conference on Computational Linguistics and 14th International Conference on language Resources and Evaluation, LREC-COLING 2024

作者： Gimeno-Gómez, David Martínez-Hinarejos, Carlos D. Pattern Recognition and Human Language Technologies Research Center Universitat Politècnica de València Camino de Vera s/n València46022 Spain

ISBN: (纸本)9782493814104

Thanks to the rise of deep learning and the availability of large-scale audio-visual databases, recent advances have been achieved in Visual Speech recognition (VSR). Similar to other speech processing tasks, these end-to-end VSR systems are usually based on encoder-decoder architectures. While encoders are somewhat general, multiple decoding approaches have been explored, such as the conventional hybrid model based on Deep Neural Networks combined with Hidden Markov Models (DNN-HMM) or the Connectionist Temporal Classification (CTC) paradigm. However, there are languages and tasks in which data is scarce, and in this situation, there is not a clear comparison between different types of decoders. Therefore, we focused our study on how the conventional DNN-HMM decoder and its state-of-the-art CTC/Attention counterpart behave depending on the amount of data used for their estimation. We also analyzed to what extent our visual speech features were able to adapt to scenarios for which they were not explicitly trained, either considering a similar dataset or another collected for a different language. Results showed that the conventional paradigm reached recognition rates that improve the CTC/Attention model in data-scarcity scenarios along with a reduced training time and fewer parameters. © 2024 ELRA language Resource Association: CC BY-NC 4.0.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Limitations and Challenges of Unsupervised Cross-lingual Pre-training 15

Limitations and Challenges of Unsupervised Cross-lingual Pre...

引用

15th Conference of the Association for Machine Translation in the Americas, AMTA 2022

作者： Zaragoza, Martín Quesada Casacuberta, Francisco Research Center of Pattern Recognition and Human Language Technology Universitat Politècnica de València Valencia46022 Spain

Cross-lingual alignment methods for monolingual language representations have received notable attention in recent years. However, their use in machine translation pre-training remains scarce. This work tries to shed light on the effects of some of the factors that play a role in cross-lingual pre-training, both for cross-lingual mappings and their integration in supervised neural models. The results show that unsupervised cross-lingual methods are effective at inducing alignment even for distant languages and they benefit noticeably from subword information. However, we find that their effectiveness as pre-training models in machine translation is severely limited due to their cross-lingual signal being easily distorted by the principal network during training. Moreover, the learned bilingual projection is too restrictive to allow said network to learn properly when the embedding weights are frozen. © AMTA 2022 - 15th Conference of the Association for Machine Translation in the Americas, Proceedings.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Conspiracy vs Critical Thinking Using an Ensemble of Transformers with Data Augmentation Techniques 25

Conspiracy vs Critical Thinking Using an Ensemble of Transfo...

引用

25th Working Notes of the Conference and Labs of the Evaluation Forum, CLEF 2024

作者： Tulbure, Angelo Maximilian Ardanuy, Mariona Coll Universitat Politècnica de València València Spain Politecnico di Milano Milan Italy Pattern Recognition and Human Language Technology Research Center Universitat Politècnica de València València Spain

This paper provides an overview of our contributions to the PAN at CLEF2024 Oppositional thinking analysis shared task, which focuses on distinguishing between conspiratorial and critical thinking narratives. The competition featured two main tasks. The first task is a binary classification task that aims at determining whether a text is conspiratorial or critical. The second task is a span-level detection task, in which the goal is to detect elements of oppositional narratives in the texts. Two annotated datasets, one in English and one in Spanish, were provided, each of 5K telegram comments. Our best-performing approaches combined custom fine-tuned Transformer models with data augmentation techniques. We achieved an F1-Score of 0.8917 for English and of 0.8293 for Spanish for task 1, and a span-F1 score of 0.6279 for English and 0.6129 for Spanish for task 2. Our task 2 approach achieved the best results in the shared task for both English and Spanish. © 2024 Copyright for this paper by its authors.

关键词： binary classification conspiracy theories critical thinking data augmentation ensembling models oppositional thinking PAN 2024 token classification

来源：评论

学校读者我要写书评

暂无评论

Py4MER: A CTC-Based Mathematical Expression recognition System 11th

Py4MER: A CTC-Based Mathematical Expression Recognition Syst...

引用

11th Iberian Conference on pattern recognition and Image Analysis, IbPRIA 2023

作者： Anitei, Dan Sánchez, Joan Andreu Benedí, José Miguel Pattern Recognition and Human Language Technologies Research Center Universitat Politècnica València Valencia Spain Valencian Graduate School and Research Network of Artificial Intelligence Camí de Vera s/n Valencia46022 Spain

ISBN: (纸本)9783031366154

Mathematical expression recognition is a research field that aims to develop algorithms and systems capable of interpreting mathematical content. The recognition of MEs requires handling two-dimensional symbol relationships such as sub/superscripts, matrices and nested fractions, among others. The prevalent technology for addressing these challenges are based on encoder-decoder architectures with attention models. In this paper we propose the Py4MER system, based on Convolutional Recurrent Neural Network (CRNN) models, for the recognition and transcription of MEs into LaTeX mark-up sequences. This model is proposed as an alternative to encoder-decoder approaches, as CRNN models trained through Connectionist Temporal Classification (CTC) implicitly model the dependencies between symbols and do not suffer from under/over parsing of the input image, generating more consistent mark-up. The proposed model is evaluated on the Im2Latex-100k data set based on both textual and image-level metrics, showing a remarkable improvement from other CTC-based approaches. recognition results are analyzed for different ME lengths and ME structures. Furthermore, a study based on the edit distance is performed, showing a considerable improvement in precision when up to 5 edit operations are considered. Finally, we show that CTC-based CRNN models can adapt to non left-to-right ordering of ME elements, warranting more research for this approach. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

How Much Does Tokenization Affect Neural Machine Translation? 1

引用

20th International Conference on Computational Linguistics and Intelligent Text Processing, CICLing 2019

作者： Domingo, Miguel García-Martínez, Mercedes Helle, Alexandre Casacuberta, Francisco Herranz, Manuel Pattern Recognition and Human Language Technology Research Center Universitat Politècnica de València Camino de Vera s/n Valencia46022 Spain Pangeanic/B.I Europa PangeaMT Technologies Division Valencia Spain

ISBN: (数字)9783031243370

ISBN: (纸本)9783031243363

Tokenization or segmentation is a wide concept that covers simple processes such as separating punctuation from words, or more sophisticated processes such as applying morphological knowledge. Neural Machine Translation (NMT) requires a limited-size vocabulary for computational cost and enough examples to estimate word embeddings. Separating punctuation and splitting tokens into words or subwords has proven to be helpful to reduce vocabulary and increase the number of examples of each word, improving the translation quality. Tokenization is more challenging when dealing with languages with no separator between words. In order to assess the impact of the tokenization in the quality of the final translation on NMT, we experimented on five tokenizers over ten language pairs. We reached the conclusion that the tokenization significantly affects the final translation quality and that the best tokenizer differs for different language pairs. © 2023, Springer Nature Switzerland AG.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Tailored Design of Audio-Visual Speech recognition Models using Branchformers

arXiv

引用

arXiv 2024年

作者： Gimeno-Gómez, David Martínez-Hinarejos, Carlos D. Pattern Recognition and Human Language Technology research center Universitat Politècnica de València Camino de Vera s/n València46022 Spain

Recent advances in Audio-Visual Speech recognition (AVSR) have led to unprecedented achievements in the field, improving the robustness of this type of system in adverse, noisy environments. In most cases, this task has been addressed through the design of models composed of two independent encoders, each dedicated to a specific modality. However, while recent works have explored unified audio-visual encoders, determining the optimal cross-modal architecture remains an ongoing challenge. Furthermore, such approaches often rely on models comprising vast amounts of parameters and high computational cost training processes. In this paper, we aim to bridge this research gap by introducing a novel audio-visual framework. Our proposed method constitutes, to the best of our knowledge, the first attempt to harness the flexibility and interpretability offered by encoder architectures, such as the Branchformer, in the design of parameter-efficient AVSR systems. To be more precise, the proposed framework consists of two steps: first, estimating audio- and video-only systems, and then designing a tailored audiovisual unified encoder based on the layer-level branch scores provided by the modality-specific models. Extensive experiments on English and Spanish AVSR benchmarks covering multiple data conditions and scenarios demonstrated the effectiveness of our proposed method. Even when trained on a moderate scale of data, our models achieve competitive word error rates (WER) of approximately 2.5% for English and surpass existing approaches for Spanish, establishing a new benchmark with an average WER of around 9.1%. These results reflect how our tailored AVSR system is able to reach state-of-the-art recognition rates while significantly reducing the model complexity w.r.t. the prevalent approach in the field. Code and pre-trained models are available at https://***/david-gimeno/tailored-avsr. © 2024, CC BY-NC-ND.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

AnnoTheia: A Semi-Automatic Annotation Toolkit for Audio-Visual Speech Technologies 30

AnnoTheia: A Semi-Automatic Annotation Toolkit for Audio-Vis...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on language Resources and Evaluation, LREC-COLING 2024

作者： Acosta-Triana, José M. Gimeno-Gómez, David Martínez-Hinarejos, Carlos D. ValgrAI - Valencian Graduate School and Research Network of Artificial Intelligence Camino de Vera s/n 3Q Building València46022 Spain Pattern Recognition and Human Language Technologies Research Center Universitat Politècnica de València Camino de Vera s/n València46022 Spain

ISBN: (纸本)9782493814104

More than 7,000 known languages are spoken around the world. However, due to the lack of annotated resources, only a small fraction of them are currently covered by speech technologies. Albeit self-supervised speech representations, recent massive speech corpora collections, as well as the organization of challenges, have alleviated this inequality, most studies are mainly benchmarked on English. This situation is aggravated when tasks involving both acoustic and visual speech modalities are addressed. In order to promote research on low-resource languages for audio-visual speech technologies, we present AnnoTheia, a semi-automatic annotation toolkit that detects when a person speaks on the scene and the corresponding transcription. In addition, to show the complete process of preparing AnnoTheia for a language of interest, we also describe the adaptation of a pre-trained model for active speaker detection to Spanish, using a database not initially conceived for this type of task. The AnnoTheia toolkit, tutorials, and pre-trained models are available at https://***/joactr/AnnoTheia/. © 2024 ELRA language Resource Association: CC BY-NC 4.0.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Comparison of Conventional Hybrid and CTC/Attention Decoders for Continuous Visual Speech recognition

arXiv

引用

arXiv 2024年

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Evaluation of End-to-End Continuous Spanish Lipreading in Different Data Conditions

arXiv

引用

arXiv 2025年

Visual speech recognition remains an open research problem where different challenges must be considered by dispensing with the auditory sense, such as visual ambiguities, the inter-personal variability among speakers, and the complex modeling of silence. Nonetheless, recent remarkable results have been achieved in the field thanks to the availability of large-scale databases and the use of powerful attention mechanisms. Besides, multiple languages apart from English are nowadays a focus of interest. This paper presents noticeable advances in automatic continuous lipreading for Spanish. First, an end-to-end system based on the hybrid CTC/Attention architecture is presented. Experiments are conducted on two corpora of disparate nature, reaching state-of-the-art results that significantly improve the best performance obtained to date for both databases. In addition, a thorough ablation study is carried out, where it is studied how the different components that form the architecture influence the quality of speech recognition. Then, a rigorous error analysis is carried out to investigate the different factors that could affect the learning of the automatic system. Finally, a new Spanish lipreading benchmark is consolidated. Code and trained models are available at https://***/david-gimeno/evaluating-end2end-spanish-lipreading. © 2025, CC BY-NC-ND.

关键词： Continuous speech recognition

来源：评论

学校读者我要写书评

暂无评论

Revisiting Bag-of-Word Metrics to Assess End-To-End Text Image recognition Results

SSRN

引用

SSRN 2023年

作者： Toselli, Alejandro Héctor Vidal, Enrique Pattern Recognition and Human Language Technologies Research Center Universitat Politècnica de València Camino de Vera s/n Valencia46022 Spain

The accuracy of traditional, line-based text recognition systems depends only on how well the text in each given line image is recognized. But in recent approaches for end-to-end full-page image transcription, performance is additionally affected by line detection errors and by the order in which lines (or words in general) are provided by the (maybe implicit) layout analysis. Methods based on "bag-of-words" (BoW) have been used in the past to overcome the impact of word-order mismatch, which often leads the traditional edit-distance-based word error rate (WER) to yield pessimistic results. But BoW-based evaluation is not as popular as WER because it is presumed to provide optimistic word error estimates. We revisit the BoW idea and formally introduce evaluation metrics which are tightly and faithfully comparable with WER. We prove properties that qualify these metrics as reliably measures of order-independent word recognition accuracy, and analyse potential causes which may lead them to yield optimistic values. Finally, we report empirical results that favorably compare these metrics with the classical WER for several text recognition approaches and datasets. © 2023, The Authors. All rights reserved.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：