检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Yu, Peiying Chen, Guoxin Wang, Jingjing Natural Language Processing Lab Soochow University China Institute of Computing Technology Chinese Academy of Sciences China

Despite the remarkable capabilities of large language models (LLMs) in various reasoning tasks, they still struggle with table reasoning tasks, particularly in maintaining consistency throughout multi-step reasoning processes. While existing approaches have explored various decomposition strategies, they often lack effective mechanisms to identify and correct errors in intermediate reasoning steps, leading to cascading error propagation. To address these issues, we propose Table-Critic, a novel multi-agent framework that facilitates collaborative criticism and iterative refinement of the reasoning process until convergence to correct solutions. Our framework consists of four specialized agents: a Judge for error identification, a Critic for comprehensive critiques, a Refiner for process improvement, and a Curator for pattern distillation. To effectively deal with diverse and unpredictable error types, we introduce a self-evolving template tree that systematically accumulates critique knowledge through experience-driven learning and guides future reflections. Extensive experiments have demonstrated that Table-Critic achieves substantial improvements over existing methods, achieving superior accuracy and error correction rates while maintaining computational efficiency and lower solution degradation rate. Copyright © 2025, The Authors. All rights reserved.

关键词： Intelligent agents

来源：评论

学校读者我要写书评

暂无评论

Generalized Attention Flow: Feature Attribution for Transformer Models via Maximum Flow

arXiv

引用

arXiv 2025年

作者： Azarkhalili, Behrooz Libbrecht, Maxwell Computing Science Department Simon Fraser University Canada Life Language Processing Lab University of California Berkeley United States

This paper introduces Generalized Attention Flow (GAF), a novel feature attribution method for Transformer-based models to address the limitations of current approaches. By extending Attention Flow and replacing attention weights with the generalized Information Tensor, GAF integrates attention weights, their gradients, the maximum flow problem, and the barrier method to enhance the performance of feature attributions. The proposed method exhibits key theoretical properties and mitigates the shortcomings of prior techniques that rely solely on simple aggregation of attention weights. Our comprehensive benchmarking on sequence classification tasks demonstrates that a specific variant of GAF consistently outperforms state-of-the-art feature attribution methods in most evaluation settings, providing a more reliable interpretation of Transformer model outputs. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Technological acceptance of non-native speakers on language learning mobile application using augmented reality

引用

Multimedia Tools and Applications 2025年 1-32页

作者： Suwadi, Nur Asylah Lam, Meng Chun Majid, Nazatul Aini Abd Jalaluddin, Nor Hashimah Aisyah, Aznur Kasdan, Junaini Hussain, Afifuddin Husairi Ahmad, Azlan Ma’arof, Daing Zairi Mixed Reality and Pervasive Computing Lab Center for Artificial Intelligence Technology Faculty of Information Science & Technology Universiti Kebangsaan Malaysia Bangi43600 Malaysia Center for Research in Language and Linguistics Faculty of Social Sciences and Humanities Universiti Kebangsaan Malaysia Bangi43600 Malaysia Universiti Kebangsaan Malaysia Bangi43600 Malaysia Pusat Citra Universiti Universiti Kebangsaan Malaysia Bangi43600 Malaysia

Although mobile applications have been widely used, there is limited research on the acceptance of mobile-based applications for language learning among foreign learners. Hence, we propose an extended version of the Technology Acceptance Model (TAM) that analyzes the key aspects affecting the acceptance of the mobile application by foreign learners. The extended TAM includes external constructs such as augmented reality (AR), content quality, design quality, and interactivity to consider both system and individual levels. Eighty international students from various countries studying Malay were given a TAM questionnaire online. Results revealed positive effects, and notably, the external constructs of AR, content quality, and interactivity are prerequisite factors in extending the TAM. The findings revealed that interactivity is the most significant external construct of Perceived Ease of Use (PEOU), followed by Perceived Usefulness (PU), which exhibits a significant contribution to the user’s attitude. Therefore, these results could guide how educator and higher education centers should approach the incorporation of these technologies in classrooms. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Socially Sustainable HRI for Underrepresented Communities: Case Study of language Learning of Arab Children in Israel 25

Socially Sustainable HRI for Underrepresented Communities: C...

引用

ACM/IEEE International Conference on Human-Robot Interaction (HRI)

作者： Einat Gonen Amna Abu-Mukh Goren Gordon Department of Hebrew language and Semitic languages Tel-Aviv University Tel-Aviv Israel Curiosity Lab Department of Industrial Engineering Tel-Aviv University Tel-Aviv Israel Department of Informatics Luddy School of Informatics Computing and Engineering Indiana University Bloomington IN USA

ISBN: (数字)9798350378931

ISBN: (纸本)9798350378948

Social robots have predominantly been deployed in resource-rich environments and managed by technical research teams. We propose a socially sustainable framework for deploying social robots in underrepresented, under-resourced communities. This approach emphasizes population-specific social impact, affordable robotic platforms, and “programming“ and operation by local community members. We present a holistic and sociallyecological case study of a unique population: Arabic elementary school children in Israel who face specific linguistic challenges. Learning Hebrew as a second language is crucial for their future, but teaching resources are limited. We developed a unique curriculum designed to teach bilingual morphological awareness in a fun and engaging way, implementing it through social robotic platforms. These platforms were selected based on social sustainability criteria, including affordability, lack of required programming skills by educators, and ease of deployment in schools. In two long-term, in-the-wild studies conducted at two different elementary schools (N=135, N=87), we utilized first Patricc and then Valera, both open-source, 3D-printed robots. These robots were “programmed“ by a non-technical educator and operated by local teachers. After six activities conducted over several weeks, our results show significant positive learning gains in both Arabic and Hebrew morphological awareness. We discuss the implications of our socially sustainable framework for using social robots in underrepresented and under-resourced communities.

关键词： Social robots Education Linguistics Sustainable development Programming profession Faces

来源：评论

学校读者我要写书评

暂无评论

A General Framework to Evaluate Methods for Assessing Dimensions of Lexical Semantic Change Using LLM-Generated Synthetic Data

arXiv

引用

arXiv 2025年

作者： Baes, Naomi Merx, Raphaël Haslam, Nick Vylomova, Ekaterina Dubossarsky, Haim Melbourne School of Psychological Sciences The University of Melbourne Australia School of Computing and Information Systems The University of Melbourne Australia School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom The Alan Turing Institute London United Kingdom Language Technology Lab University of Cambridge United Kingdom

Lexical Semantic Change (LSC) offers insights into cultural and social dynamics. Yet, the validity of methods for measuring kinds of LSC has yet to be established due to the absence of historical benchmark datasets. To address this gap, we develop a novel three-stage evaluation framework that involves: 1) creating a scalable, domain-general methodology for generating synthetic datasets that simulate theory-driven LSC across time, leveraging In-Context Learning and a lexical database;2) using these datasets to evaluate the effectiveness of various methods;and 3) assessing their suitability for specific dimensions and domains. We apply this framework to simulate changes across key dimensions of LSC (SIB: Sentiment, Intensity, and Breadth) using examples from psychology, and evaluate the sensitivity of selected methods to detect these artificially induced changes. Our findings support the utility of the synthetic data approach, validate the efficacy of tailored methods for detecting synthetic changes in SIB, and reveal that a state-of-the-art LSC model faces challenges in detecting affective dimensions of LSC. This framework provides a valuable tool for dimension- and domain-specific benchmarking and evaluation of LSC methods, with particular benefits for the social sciences. © 2025, CC BY-NC-SA.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Automatic treebank conversion via informed decoding-A case study on Chinese treebanks

引用

ACM Transactions on Asian language Information Processing 2011年第3期10卷 1–24页

作者： Zhu, Muhua Zhu, Jingbo Xiao, Tong Key Laboratory of Medical Image Computing Natural Language Processing Lab Northeastern University Shenyang 110819 China

Treebanks are valuable resources for syntactic parsing. For some languages such as Chinese, we can obtain multiple constituency treebanks which are developed by different organizations. However, due to discrepancies of underlying annotation standards, such treebanks in general cannot be used together through direct data combination. To enlarge training data for syntactic parsing, we focus in this article on the challenge of unifying standards of disparate treebanks by automatically converting one treebank (source treebank) to fit a different standard which is exhibited by another treebank (target treebank). We propose to convert a treebank in two sequential steps which correspond to the part-of-speech level and syntactic structure level (including tree structures and grammar labels), respectively. Approaches used in both levels can be unified as an informed decoding procedure, where information derived from original annotation in a source treebank is used to guide the conversion conducted by a POS tagger (or a parser in the syntactic structure level) trained on a target treebank. We take two Chinese treebanks as a case study, and experiments on these two treebanks show significant improvements in conversion accuracy over baseline systems, especially in situations where a target treebank is small in size. © 2011 ACM.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

language modeling for syntax-based machine translation using tree substitution grammars: A case study on Chinese-english translation

引用

ACM Transactions on Asian language Information Processing 2011年第4期10卷 18.1-18.29页

作者： Xiao, Tong Zhu, Jingbo Zhu, Muhua Northeastern University Key Laboratory of Medical Image Computing Natural Language Processing Lab Shenyang 110004 China

The poor grammatical output of Machine Translation (MT) systems appeals syntax-based approaches within language modeling. However, previous studies showed that syntax-based language modeling using (Context- Free) Treebank Grammars was not very helpful in improving BLEU scores for Chinese-English machine translation. In this article we further study this issue in the context of Chinese-English syntax-based Statistical Machine Translation (SMT) where Synchronous Tree Substitution Grammars (STSGs) are utilized to model the translation process. In particular, we develop a Tree Substitution Grammar-based language model for syntax-based MT, and present three methods to efficiently integrate the proposed language model into MT decoding. In addition, we design a simple and effective method to adapt syntax-based language models for MT tasks. We demonstrate that the proposed methods are able to benefit a state-of-the-art syntax-based MT system. On the NIST Chinese-English MT evaluation corpora, we finally achieve an improvement of 0.6 BLEU points over the baseline. © 2011 ACM.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

The SRC-B speech-to-text systems for OC16 Chinese-English mix-ASR challenge 19

The SRC-B speech-to-text systems for OC16 Chinese-English mi...

引用

19th Annual Conference of the Oriental Chapter of International Committee for Coordination and Standardization of Speech Databases and Assessment Techniques, O-COCOSDA 2016

作者： Chen, Mingming Xu, Xiaoyun Yu, Xiaojie Zhu, Xuan Language Computing Lab Beijing Samsung Telecom RandD Center China

ISBN: (纸本)9781509035168

In the paper, we describe our Chinese-English Speech-to-Text (STT) systems for OC16 Chinese-English Mix-ASR Challenge. This challenge focuses on the transcription of Chinese-English code-mixing speech. Code-mixing speech which refers to the intra-sentential switching of two different languages in a spoken utterance proposes a very challenging task for the ASR research community. In this challenge, our setup includes systems trained using the Kaldi speech recognition toolkit. We combined the outputs from different systems using ROVER to achieve a good overall performance. The individual subsystems are built by using different front-ends (e.g., MFCC+pitch, Fbank+pitch or FMLLR features), acoustic models (CD-GMM-HMM, CD-DNN-HMM or CD-LSTM-HMM), language models (with or without interpolated using development set text), phone sets and by training on different sets of permissible training data. The ROVER combination setup produces a final hypothesis. Our best system (CD-DNN-HMM-MPE) based on Kaldi has a CER of 4.79% on the development set using interpolated LM while in combination with CD-LSTM-HMM system we get 4.98% CER on the development set. © 2016 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

AMR parsing with an incremental joint model

AMR parsing with an incremental joint model

引用

2016 Conference on Empirical Methods in Natural language Processing, EMNLP 2016

作者： Zhou, Junsheng Xu, Feiyu Uszkoreit, Hans Qu, Weiguang Li, Ran Gu, Yanhui Language Information Processing and Social Computing Lab School of Computer Science and Technology Nanjing Normal University China Language Technology Lab DFKI Germany

ISBN: (纸本)9781945626258

To alleviate the error propagation in the traditional pipelined models for Abstract Meaning Representation (AMR) parsing, we formulate AMR parsing as a joint task that performs the two subtasks: concept identification and relation identification simultaneously. To this end, we first develop a novel component-wise beam search algorithm for relation identification in an incremental fashion, and then incorporate the decoder into a unified framework based on multiple-beam search, which allows for the bi-directional information flow between the two subtasks in a single incremental model. Experiments on the public datasets demonstrate that our joint model significantly outperforms the previous pipelined counterparts, and also achieves better or comparable performance than other approaches to AMR parsing, without utilizing external semantic resources. © 2016 Association for Computational Linguistics

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Beyond possession existence: Duration and co-possession 58

Beyond possession existence: Duration and co-possession

引用

58th Annual Meeting of the Association for Computational Linguistics, ACL 2020

作者： Chinnappa, Dhivya Murugan, Srikala Blanco, Eduardo Center for Cognitive Computing Thomson Reuters Human Intelligence and Language Technologies Lab University of North Texas

ISBN: (纸本)9781952148255

This paper introduces two tasks: determining (a) the duration of possession relations and (b) co-possessions, i.e., whether multiple possessors possess a possessee at the same time. We present new annotations on top of corpora annotating possession existence, and experimental results. Regarding possession duration, we derive the time spans we work with empirically from annotations indicating lower and upper bounds. Regarding co-possessions, we use a binary label. Cohen's kappa coefficients indicate substantial agreement, and experimental results show that text is more useful than the image for solving these tasks. © 2020 Association for Computational Linguistics

关键词：

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：