检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Pappas, Dimitris Malakasiotis, Prodromos Androutsopoulos, Ion Department of Informatics Athens University of Economics and Business Greece Institute for Language and Speech Processing Research Center Athena Greece Institute of Informatics and Telecommunications NCSR Demokritos Greece

We study the effect of seven data augmentation (da) methods in factoid question answering, focusing on the biomedical domain, where obtaining training instances is particularly difficult. We experiment with data from the bioasq challenge, which we augment with training instances obtained from an artificial biomedical machine reading comprehension dataset, or via back-translation, information retrieval, word substitution based on word2vec embeddings or masked language modeling, question generation, or extending the given passage with additional context. We show that da can lead to very significant performance gains, even when using large pretrained Transformers, contributing to a broader discussion of if/when da benefits large pretrained models. One of the simplest da methods, word2vec-based word substitution, performed best and is recommended. We release our artificial training instances and code. © 2022, CC BY.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Krikri: Advancing Open Large language Models for Greek

arXiv

引用

arXiv 2025年

作者： Roussis, Dimitris Voukoutis, Leon Paraskevopoulos, Georgios Sofianopoulos, Sokratis Prokopidis, Prokopis Papavasileiou, Vassilis Katsamanis, Athanasios Piperidis, Stelios Katsouros, Vassilis Institute for Speech and Language Processing Athena Research Center Artemidos 6 & Epidavrou Athens Greece

We introduce Llama-Krikri-8B, a cutting-edge Large language Model tailored for the Greek language, built on Meta’s Llama 3.1-8B. Llama-Krikri-8B has been extensively trained on high-quality Greek data to ensure superior adaptation to linguistic nuances. With 8 billion parameters, it offers advanced capabilities while maintaining efficient computational performance. Llama-Krikri-8B supports both Modern Greek and English, and is also equipped to handle polytonic text and Ancient Greek. The chat version of Llama-Krikri-8B features a multi-stage post-training pipeline, utilizing both human and synthetic instruction and preference data, by applying techniques such as MAGPIE. In addition, for evaluation, we propose three novel public benchmarks for Greek. Our evaluation on existing as well as the proposed benchmarks shows notable improvements over comparable Greek and multilingual LLMs in both natural language understanding and generation as well as code generation. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RobuSER: A Robustness Benchmark for speech Emotion Recognition

RobuSER: A Robustness Benchmark for Speech Emotion Recogniti...

引用

International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII

作者： Antonia Petrogianni Lefteris Kapelonis Nikolaos Antoniou Sofia Eleftheriou Petros Mitseas Dimitris Sgouropoulos Athanasios Katsamanis Theodoros Giannakopoulos Shrikanth Narayanan Behavioral Signal Technologies Athens Greece Behavioral Signal Technologies Institute for Language and Speech Processing Athena R.C Athens Greece Behavioral Signal Technologies Institute of Informatics and Telecommunications NCSR Demokritos Athens Greece Behavioral Signal Technologies SAIL University of Southern California Los Angeles USA

ISBN: (数字)9798331516437

ISBN: (纸本)9798331516444

The recent surge in deep learning has improved speech Emotion Recognition (SER) model performance; however, ensuring robustness across diverse scenarios beyond the training dataset remains a problem. This challenge becomes pronounced in real-world situations characterized by noisy conditions, where model adaptability to unclean data is crucial. Despite ongoing efforts to develop noise-robust models, the lack of standardized evaluation protocols hampers fair comparisons among different models. This paper tackles this issue by introducing Robuser, a benchmarking procedure designed specifically for evaluating the robustness of SER models under noise. Robuser is a comprehensive open-source benchmark that can be applied to any speech dataset, focusing on diverse corruption types in two pivotal dimensions: additive background noise and various signal distortion corruptions, each in varying levels of severity. Furthermore, through the evaluation of a state-of-the-art SER model against this benchmark, we offer quantitative insights into the impact of the different corruption types and severity levels on performance. The baseline model reveals a notable performance degradation of up to 22.77% in Unweighted Accuracy (UA) and 20.32% in Weighted Accuracy (WA) on corrupted IEMOCAP, underscoring the substantial room for improvement in this domain. Our code is openly available at the following URL: https://***/BehavioralSignalTechnologies/ser_***

关键词： Uniform resource locators Training Adaptation models Emotion recognition Accuracy speech coding Noise speech recognition Benchmark testing Robustness

来源：评论

学校读者我要写书评

暂无评论

Emotion-Aware speech Popularity Prediction: A Use-Case on TED Talks

Emotion-Aware Speech Popularity Prediction: A Use-Case on TE...

引用

International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII

作者： Dimitrios Sgouropoulos Petros Mitseas Sofia Eleftheriou Theodoros Giannakopoulos Antonia Petrogianni Lefteris Kapelonis Nikolaos Antoniou Athanasios Katsamanis Shrikanth Narayanan Behavioral Signal Technologies Athens Greece Behavioral Signal Technologies Institute of Informatics and Telecommunications NCSR Demokritos Athens Greece Behavioral Signal Technologies Institute for Language and Speech Processing Athena R. C. Athens Greece Behavioral Signal Technologies SAIL University of Southern California Los Angeles USA

ISBN: (数字)9798331516437

ISBN: (纸本)9798331516444

In the context of the ever-growing influence of social media, understanding and predicting the popularity of content has become crucial for creators and marketers alike. Our research addresses this need by introducing a method to forecast the success of oral presentations, focusing on the nuanced use of paralinguistic features and insights derived from speech emotion recognition models. This innovative approach is designed to enhance verbal communication skills by providing public speakers with targeted feedback. We leverage a dataset of 2,462 TED talk videos, complete with metadata such as user comments, tags, and views, to establish a set of four objective metrics for determining presentation popularity. These metrics form the foundation of our analysis, enabling us to evaluate the efficacy of our predictive methodology. By integrating audio-based emotional cues with text-based content analysis we showcase the capability of the proposed speech analytics system to capture user assessments of presentation quality. This research highlights the role of emotional expression in speech as a component of content's appeal, advocating for a broader analytical perspective beyond just text-only analysis. It suggests new directions for improving the impact of public speaking and calls for further investigation into multimodal content analysis, aiming to deepen our understanding of audience engagement on social media and content delivery platforms.

关键词： Measurement Emotion recognition Content management Social networking (online) Focusing speech recognition Metadata speech Public speaking Videos

来源：评论

学校读者我要写书评

暂无评论

AUEB-NLP at BioASQ 8: Biomedical Document and Snippet Retrieval 11th

AUEB-NLP at BioASQ 8: Biomedical Document and Snippet Retrie...

引用

11th Conference and Labs of the Evaluation Forum, CLEF 2020

作者： Pappas, Dimitris Stavropoulos, Petros Androutsopoulos, Ion Department of Informatics Athens University of Economics and Business Greece Institute for Language and Speech Processing Research Center ‘Athena’ Greece

We present the submissions of AUEB’s NLP group to the BIOASQ 8 document and snippet retrieval tasks. We relied mostly on JPDRMM, our top performing model of BIOASQ 7, but we also tested feeding JPDRMM with word embeddings obtained by applying a graph node embedding method to a biomedical co-occurrence graph;the latter approach was competitive to using biomedical WORD2VEC embeddings in JPDRMM. We also experimented with neural methods to encode, index, and directly retrieve snippets (sentences) and indirectly documents containing the retrieved snippets, instead of relying on conventional information retrieval to pre-fetch possibly relevant documents and invoking JPDRMM to re-rank the pre-fetched documents and their snippets;conventional BM25-based pre-fetching, however, was far better. Our JPDRMM-based document and snippet retrieval methods scored at the top or near the top for all test batches of BIOASQ 8. Copyright © 2020 for this paper by its authors.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Cross-lingual Aphasia Detection using Automatic speech Recognition

arXiv

引用

arXiv 2022年

作者： Chatzoudis, Gerasimos Plitsis, Manos Stamouli, Spyridoula Dimou, Athanasia-Lida Katsamanis, Athanasios Katsouros, Vassilis Institute for Language and Speech Processing Athena Research Center Athens Greece Behavioral Signal Technologies Los AngelesCA United States National and Kapodistrian University of Athens Athens Greece

Aphasia is a common speech and language disorder, typically caused by a brain injury or a stroke, that affects millions of people worldwide. Detecting and assessing Aphasia in patients is a difficult, time-consuming process, and numerous attempts to automate it have been made, the most successful using machine learning models trained on aphasic speech data. Like in many medical applications, aphasic speech data is scarce and the problem is exacerbated in so-called "low resource" languages, which are, for this task, most languages excluding English. We attempt to leverage available data in English and achieve zero-shot aphasia detection in low-resource languages such as Greek and French, by using language-agnostic linguistic features. Current cross-lingual aphasia detection approaches rely on manually extracted transcripts. We propose an end-to-end pipeline using pre-trained Automatic speech Recognition (ASR) models that share cross-lingual speech representations and are fine-tuned for our desired low-resource languages. To further boost our ASR model's performance, we also combine it with a language model. We show that our ASR-based end-toend pipeline offers comparable results to previous setups using human-annotated transcripts. © 2022, CC BY-NC-ND.

关键词： speech recognition

来源：评论

学校读者我要写书评

暂无评论

SPECTRE: Visual speech-Informed Perceptual 3D Facial Expression Reconstruction from Videos

SPECTRE: Visual Speech-Informed Perceptual 3D Facial Express...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Panagiotis P. Filntisis George Retsinas Foivos Paraperas-Papantoniou Athanasios Katsamanis Anastasios Roussos Petros Maragos Institute of Robotics Athena Research Center Maroussi Greece School of Electrical & Computer Engineering National Technical University of Athens Greece Imperial College London UK Institute for Language and Speech Processing Athena R.C. Greece Institute of Computer Science (ICS) Foundation for Research & Technology - Hellas (FORTH) Greece College of Engineering Mathematics and Physical Sciences University of Exeter UK

The recent state of the art on monocular 3D face reconstruction from image data has made some impressive advancements, thanks to the advent of Deep Learning. However, it has mostly focused on input coming from a single RGB image, overlooking the following important factors: a) Nowadays, the vast majority of facial image data of interest do not originate from single images but rather from videos, which contain rich dynamic information. b) Furthermore, these videos typically capture individuals in some form of verbal communication (public talks, teleconferences, audiovisual human-computer interactions, interviews, monologues/dialogues in movies, etc). When existing 3D face reconstruction methods are applied in such videos, the artifacts in the reconstruction of the shape and motion of the mouth area are often severe, since they do not match well with the speech *** overcome the aforementioned limitations, we present the first method for visual speech-informed perceptual reconstruction of 3D mouth expressions. We do this by proposing a "lipreading" loss, which guides the fitting process so that the elicited perception from the 3D reconstructed talking head resembles that of the original video footage. We demonstrate that, interestingly, the lipreading loss is better suited for 3D reconstruction of mouth movements compared to traditional landmark losses, and even direct 3D supervision. Furthermore, the devised method does not rely on any text transcriptions or corresponding audio, rendering it ideal for training in unlabeled datasets. We verify the efficiency of our method through objective evaluations on three large-scale datasets, as well as subjective evaluation with two web-based user studies. Project webpage: https://***/spectre/

关键词：

来源：评论

学校读者我要写书评

暂无评论

MMLATCH: BOTTOM-UP TOP-DOWN FUSION FOR MULTIMODAL SENTIMENT ANALYSIS

arXiv

引用

arXiv 2022年

作者： Paraskevopoulos, Georgios Georgiou, Efthymios Potamianos, Alexandros National Technical University of Athens Athens Greece Institute for Language and Speech Processing Athena Research Center Athens Greece Behavioral Signal Technologies Los AngelesCA United States

Current deep learning approaches for multimodal fusion rely on bottom-up fusion of high and mid-level latent modality representations (late/mid fusion) or low level sensory inputs (early fusion). Models of human perception highlight the importance of top-down fusion, where high-level representations affect the way sensory inputs are perceived, i.e. cognition affects perception. These top-down interactions are not captured in current deep learning models. In this work we propose a neural architecture that captures top-down crossmodal interactions, using a feedback mechanism in the forward pass during network training. The proposed mechanism extracts high-level representations for each modality and uses these representations to mask the sensory inputs, allowing the model to perform top-down feature masking. We apply the proposed model for multimodal sentiment recognition on CMU-MOSEI. Our method shows consistent improvements over the well established MulT and over our strong late fusion baseline, achieving state-of-the-art results. © 2022, CC BY.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Unitygeoar: A Geolocation Augmented Reality Package for Unity3d

SSRN

引用

SSRN 2024年

作者： Cheliotis, Kostas Liarokapis, Fotis Kokla, Margarita Tomai, Eleni Pastra, Katerina Anastopoulou, Niki Bezerianou, Maria Darra, Athanasia Kavouras, Marinos Laboratory of Cartography School of Rural Surveying and Geoinformatics Engineering National Technical University of Athens Greece CYENS - Centre of Excellence Cyprus Institute for Language and Speech Processing ATHENA Research Center Greece Department of Geography and Regional Planning School of Rural Surveying and Geoinformatics Engineering National Technical University of Athens Greece

Research interest in Augmented Reality (AR) has been steadily increasing in the past decades. However, while we see a wide range of publications implementing AR nowadays, it is often the case that the software is not included in the publication, leading to future research having to re-introduce similar custom AR solutions. We identify one such case, that of geolocated AR, which poses a deceptively complex issue, namely that of correctly aligning a virtual view with geo-referenced material around the user. We present here UnityGeoAR, a package for the widely used game engine Unity3D, that handles geolocation, reprojection, and AR view alignment through a minimal Application Programming Interface (API), in an effort to standardize geoAR development and reduce development and implementation time for such a widely used aspect of AR. © 2024, The Authors. All rights reserved.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Modelling Collocations in OntoLex-FrAC

Modelling Collocations in OntoLex-FrAC

引用

2022 Globalex Workshop on Linked Lexicography, GWLL 2022

作者： Chiarcos, Christian Gkirtzou, Katerina Ionov, Maxim Kabashi, Besim Khan, Anas Fahad Truică, Ciprian-Octavian Applied Computational Linguistics Goethe University Frankfurt Frankfurt am Main Germany Institute for Digital Humanities University of Cologne Germany Institute of Language and Speech Processing Athena Research Center Athens Greece Computational and Corpus Linguistics Friedrich-Alexander University of Erlangen-Nuremberg Germany Istituto di Linguistica Computazionale A. Zampolli Consiglio Nazionale delle Ricerche Italy Department of Information Technology Uppsala University Sweden

ISBN: (纸本)9791095546924

Following presentations of frequency and attestations, and embeddings and distributional similarity, this paper introduces the third cornerstone of the emerging OntoLex module for Frequency, Attestation and Corpus-based Information, OntoLex-FrAC. We provide an RDF vocabulary for collocations, established as a consensus over contributions from five different institutions and numerous data sets, with the goal of eliciting feedback from reviewers, workshop audience and the scientific community in preparation of the final consolidation of the OntoLex-FrAC module, whose publication as a W3C community report is foreseen for the end of this year. The novel collocation component of OntoLex-FrAC is described in application to a lexicographic resource and corpus-based collocation scores available from the web, and finally, we demonstrate the capability and genericity of the model by showing how to retrieve and aggregate collocation information by means of SPARQL, and its export to a tabular format, so that it can be easily processed in downstream applications. © European language Resources Association (ELRA)

关键词： collocation analysis lexical resources OntoLex standards

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：