检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Robin Schmitt Albert Zeyer Mohammad Zeineldeen Ralf Schlűter Hermann Ney Computer Science Department Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany AppTek GmbH Aachen Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We sometimes observe monotonically decreasing cross-attention weights in our Conformer-based global attention-based encoder-decoder (AED) models, negatively affecting performance compared to monotonically increasing attention weights. Further investigation shows that the Conformer encoder reverses the sequence in the time dimension. We analyze the initial behavior of the decoder cross-attention mechanism and find that it encourages the Conformer encoder self-attention to build a connection between the initial frames and all other informative frames. Furthermore, we show that, at some point in training, the self-attention module of the Conformer starts dominating the output over the preceding feed-forward module, which then only allows the reversed information to pass through. We propose methods and ideas of how this flipping can be avoided and investigate a novel method to obtain label-frame-position alignments by using the gradients of the label log probabilities w.r.t. the encoder input frames.

关键词： Training Signal processing Acoustics Decoding Speech processing

来源：评论

学校读者我要写书评

暂无评论

From Correctness to Comprehension: AI Agents for Personalized Error Diagnosis in Education

arXiv

引用

arXiv 2025年

作者： Zhang, Yi-Fan Li, Hang Song, Dingjie Sun, Lichao Xu, Tianlong Wen, Qingsong National Laboratory of Pattern Recognition University of Chinese Academy of Sciences China Computer Science department from Michigan State University United States CUHK-Shenzhen Natural Language Processing group China Computer Science and Engineering Lehigh University United States Squirrel Ai Learning group

Large language Models (LLMs), such as GPT-4, have demonstrated impressive mathematical reasoning capabilities, achieving near-perfect performance on benchmarks like GSM8K. However, their application in personalized education remains limited due to an overemphasis on correctness over error diagnosis and feedback generation. Current models fail to provide meaningful insights into the causes of student mistakes, limiting their utility in educational contexts. To address these challenges, we present three key contributions. First, we introduce MathCCS (Mathematical Classification and Constructive Suggestions), a multi-modal benchmark designed for systematic error analysis and tailored feedback. MathCCS includes real-world problems, expert-annotated error categories, and longitudinal student data. Evaluations of state-of-the-art models, including Qwen2-VL, LLaVA-OV, Claude-3.5-Sonnet and GPT-4o, reveal that none achieved classification accuracy above 30% or generated high-quality suggestions (average scores below 4/10), highlighting a significant gap from human-level performance. Second, we develop a sequential error analysis framework that leverages historical data to track trends and improve diagnostic precision. Finally, we propose a multi-agent collaborative framework that combines a Time Series Agent for historical analysis and an MLLM Agent for real-time refinement, enhancing error classification and feedback generation. Together, these contributions provide a robust platform for advancing personalized education, bridging the gap between current AI capabilities and the demands of real-world teaching. Copyright © 2025, The Authors. All rights reserved.

关键词： Systematic errors

来源：评论

学校读者我要写书评

暂无评论

Classification Error Bound for Low Bayes Error Conditions in Machine Learning

arXiv

引用

arXiv 2025年

作者： Yang, Zijian Eminyan, Vahe Schlüter, Ralf Ney, Hermann Machine Learning and Human Language Technology Group Lehrstuhl Informatik 6 Computer Science Department RWTH Aachen University Germany AppTek GmbH Germany

In statistical classification and machine learning, classification error is an important performance measure, which is minimized by the Bayes decision rule. In practice, the unknown true distribution is usually replaced with a model distribution estimated from the training data in the Bayes decision rule. This substitution introduces a mismatch between the Bayes error and the model-based classification error. In this work, we apply classification error bounds to study the relationship between the error mismatch and the Kullback-Leibler divergence in machine learning. Motivated by recent observations of low model-based classification errors in many machine learning tasks, bounding the Bayes error to be lower, we propose a linear approximation of the classification error bound for low Bayes error conditions. Then, the bound for class priors are discussed. Moreover, we extend the classification error bound for sequences. Using automatic speech recognition as a representative example of machine learning applications, this work analytically discusses the correlations among different performance measures with extended bounds, including cross-entropy loss, language model perplexity, and word error rate. Copyright © 2025, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Classification Error Bound for Low Bayes Error Conditions in Machine Learning

Classification Error Bound for Low Bayes Error Conditions in...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zijian Yang Vahe Eminyan Ralf Schlüter Hermann Ney Computer Science Department Machine Learning and Human Language Technology Group Lehrstuhl Informatik 6 RWTH Aachen University Germany AppTek GmbH Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

关键词： Error analysis Measurement uncertainty Linear approximation Training data Machine learning Signal processing Loss measurement Data models Bayes methods Speech processing

来源：评论

学校读者我要写书评

暂无评论

Transformer-based direct hidden Markov model for machine translation 59

Transformer-based direct hidden Markov model for machine tra...

引用

2021 Student Research Workshop, SRW 2021 at the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural language Processing, ACL-IJCNLP 2021

作者： Wang, Weiyue Yang, Zijian Gao, Yingbo Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Germany

ISBN: (纸本)9781954085558

The neural hidden Markov model has been proposed as an alternative to attention mechanism in machine translation with recurrent neural networks. However, since the introduction of the transformer models, its performance has been surpassed. This work proposes to introduce the concept of the hidden Markov model to the transformer architecture, which outperforms the transformer baseline. Interestingly, we find that the zero-order model already provides promising performance, giving it an edge compared to a model with first-order dependency, which performs similarly but is significantly slower in training and decoding. © 2021 Association for Computational Linguistics.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Extending statistical machine translation with discriminative and trigger-based lexicon models

Extending statistical machine translation with discriminativ...

引用

2009 Conference on Empirical Methods in Natural language Processing, EMNLP 2009, Held in Conjunction with ACL-IJCNLP 2009

作者： Mauser, Arne Hasan, SǍa Ney, Hermann Human Language Technology and Pattern Recognition Group Department of Computer Science 6 RWTH Aachen University Germany

In this work, we propose two extensions of standard word lexicons in statistical machine translation: A discriminative word lexicon that uses sentence-level source information to predict the target words and a trigger-based lexicon model that extends IBM model 1 with a second trigger, allowing for a more fine-grained lexical choice of target words. The models capture dependencies that go beyond the scope of conventional SMT models such as phraseand language models. We show that the models improve translation quality by 1% in BLEU over a competitive baseline on a large-scale task. © 2009 ACL and AFNLP.

关键词： computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

The RWTH Aachen Speech recognition and Machine Translation System for IWSLT 2012 9

The RWTH Aachen Speech Recognition and Machine Translation S...

引用

9th International Workshop on Spoken language Translation, IWSLT 2012

作者： Peitz, Stephan Mansour, Saab Freitag, Markus Feng, Minwei Huck, Matthias Wuebker, Joern Nuhn, Malte Nußbaum-Thom, Markus Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Aachen Germany

In this paper, the automatic speech recognition (ASR) and statistical machine translation (SMT) systems of RWTH Aachen University developed for the evaluation campaign of the International Workshop on Spoken language Translation (IWSLT) 2012 are presented. We participated in the ASR (English), MT (English-French, Arabic-English, Chinese-English, German-English) and SLT (English-French) tracks. For the MT track both hierarchical and phrase-based SMT decoders are applied. A number of different techniques are evaluated in the MT and SLT tracks, including domain adaptation via data selection, translation model interpolation, phrase training for hierarchical and phrase-based systems, additional reordering model, word class language model, various Arabic and Chinese segmentation methods, postprocessing of speech recognition output with an SMT system, and system combination. By application of these methods we can show considerable improvements over the respective baseline systems. © IWSLT 2012. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

The RWTH Aachen Machine Translation System for IWSLT 2011 8

The RWTH Aachen Machine Translation System for IWSLT 2011

引用

8th International Workshop on Spoken language Translation, IWSLT 2011

作者： Wuebker, Joern Huck, Matthias Mansour, Saab Freitag, Markus Feng, Minwei Peitz, Stephan Schmidt, Christoph Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Aachen Germany

In this paper the statistical machine translation (SMT) systems of RWTH Aachen University developed for the evaluation campaign of the International Workshop on Spoken language Translation (IWSLT) 2011 is presented. We participated in the MT (English-French, Arabic-English, Chinese-English) and SLT (English-French) tracks. Both hierarchical and phrase-based SMT decoders are applied. A number of different techniques are evaluated, including domain adaptation via monolingual and bilingual data selection, phrase training, different lexical smoothing methods, additional reordering models for the hierarchical system, various Arabic and Chinese segmentation methods, punctuation prediction for speech recognition output, and system combination. By application of these methods we can show considerable improvements over the respective baseline systems. © IWSLT 2011. All rights reserved.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Sequence Labeling-based Reordering Model for Phrase-based SMT 9

Sequence Labeling-based Reordering Model for Phrase-based SM...

引用

9th International Workshop on Spoken language Translation, IWSLT 2012

作者： Feng, Minwei Peter, Jan-Thorsten Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Aachen Germany

For current statistical machine translation system, reordering is still a major problem for language pairs like Chinese-English, where the source and target language have significant word order differences. In this paper, we propose a novel reordering model based on sequence labeling techniques. Our model converts the reordering problem into a sequence labeling problem, i.e. a tagging task. For the given source sentence, we assign each source token a label which contains the reordering information for that token. We also design an unaligned word tag so that the unaligned word phenomenon is automatically implanted in the proposed model. Our reordering model is conditioned on the whole source sentence. Hence it is able to catch the long dependency in the source sentence. Although the learning on large scale task requests notably amounts of computational resources, the decoder makes use of the tagging information as soft constraints. Therefore, the training procedure of our model is computationally expensive for large task while in the test phase (during translation) our model is very efficient. We carried out experiments on five Chinese-English NIST tasks trained with BOLT data. Results show that our model improves the baseline system by 1.32 BLEU 1.53 TER on average. © IWSLT 2012. All rights reserved.

关键词： computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

Improving Continuous Sign language recognition: Speech recognition Techniques and System Design 4

Improving Continuous Sign Language Recognition: Speech Recog...

引用

4th Workshop on Speech and language Processing for Assistive Technologies, SLPAT 2013

作者： Forster, Jens Koller, Oscar Oberdorfer, Christian Gweth, Yannick Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Aachen Germany

ISBN: (纸本)9781937284930

Automatic sign language recognition (ASLR) is a special case of automatic speech recognition (ASR) and computer vision (CV) and is currently evolving from using artificial labgenerated data to using 'real-life' data. Although ASLR still struggles with feature extraction, it can benefit from techniques developed for ASR. We present a large-vocabulary ASLR system that is able to recognize sentences in continuous sign language and uses features extracted from standard single-view video cameras without using additional equipment. ASR techniques such as the multi-layer-perceptron (MLP) tandem approach, speaker adaptation, pronunciation modelling, and parallel hidden Markov models are investigated. We evaluate the influence of each system component on the recognition performance. On two publicly available large vocabulary databases representing lab-data (25 signer, 455 sign vocabulary, 19k sentence) and unconstrained 'real-life' sign language (1 signer, 266 sign vocabulary, 351 sentences) we can achieve 22.1% respectively 38.6% WER. © 2013 Association for Computational Linguistics.

关键词： Vocabulary control

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：