检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Liu, Xiao Huang, Heyan Shi, Ge Wang, Bo School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Key Laboratory of Intelligent Information Processing and Information Security Ministry of Industry and Information Technology China Southeast Academy of Information Technology Beijing Institute of Technology China Faculty of Information Technology Beijing University of Technology China

We consider event extraction in a generative manner with template-based conditional generation. Although there is a rising trend of casting the task of event extraction as a sequence generation problem with prompts, these generation-based methods have two significant challenges, including using suboptimal prompts and static event type information. In this paper, we propose a generative template-based event extraction method with dynamic prefix (GTEE-DYNPREF) by integrating context information with type-specific prefixes to learn a context-specific prefix for each context. Experimental results show that our model achieves competitive results with the state-of-the-art classification-based model ONEIE on ACE 2005 and achieves the best performances on ERE. Additionally, our model is proven to be portable to new types of events effectively. Copyright © 2022, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Task-Aware Mean Teacher Method for Large Scale Weakly Labeled Semi-Supervised Sound Event Detection

Task-Aware Mean Teacher Method for Large Scale Weakly Labele...

引用

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

作者： Jie Yan Yan Song Li-Rong Dai Ian McLoughlin National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China Hefei China School of Computing University of Kent Medway UK

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

Weakly labeled semi-supervised learning methods have recently drawn increasing attention from the research community for sound event detection tasks. Due to the weakness of the labelling, neural networks are often designed to perform sound event detection (SED) and audio tagging (AT) at the same time. In this paper, we propose a task-aware mean teacher method using a convolutional recurrent neural network (CRNN) with multi-branch structure to solve the SED and AT tasks differently. Specifically, a branch with coarse-level temporal resolution is designed for the AT task, while a branch with fine-level temporal resolution is designed for the SED task. The mean teacher based semi-supervised learning method is first adopted to improve the performance of the coarse-level AT branch by exploiting unlabeled data. Then the coarse-level AT branch is introduced as a teacher to guide the aggregated AT output of the fine-level SED branch, yielding an improvement in the SED performance. To further improve the AT and SED performance, information from multiple layers is exploited in the form of a multi-resolution feature. Experimental results on Task4 of the DCASE2018 challenge demonstrate the superiority of the proposed method, achieving 37.7% F1-score, which outperforms the winning system's 32.4%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Cognitive Diagnostic Model Based on BP Neural Network

Research on Cognitive Diagnostic Model Based on BP Neural Ne...

引用

作者： Jin Chen Jianghao Lin XinGuang Li Laboratory for Language Engineering and Computing International College Guangdong University of Foreign Studies Laboratory for Language Engineering and Computing Guangdong University of Foreign Studies

This paper proposed a cognitive diagnostic model based on BP neural network and maximum likelihood function, with an ultimate goal of realizing the cognitive diagnostic computerized adaptive test. The model was verified through the actual data from 1029 British middle school students who participated in the English reading test of the Program for International Student Assessment(PISA). The experimental results show that both the model's mode accuracy rate and the average attribute accuracy rate are relatively ideal. Moreover, the model, which is of flexibility, can be effectively applied to cognitive diagnosis in small-scale classrooms.

关键词： BP Neural Network Cognitive Diagnostic Model CD-CAT

来源：评论

学校读者我要写书评

暂无评论

Overview of the Tenth Dialog System Technology Challenge: DSTC10

引用

IEEE/ACM Transactions on Audio Speech and language Processing 2024年 32卷 765-778页

作者： Yoshino, Koichiro Chen, Yun-Nung Crook, Paul Kottur, Satwik Li, Jinchao Hedayatnia, Behnam Moon, Seungwhan Fei, Zhengcong Li, Zekang Zhang, Jinchao Feng, Yang Zhou, Jie Kim, Seokhwan Liu, Yang Jin, Di Papangelis, Alexandros Gopalakrishnan, Karthik Hakkani-Tur, Dilek Damavandi, Babak Geramifard, Alborz Hori, Chiori Shah, Ankit Zhang, Chen Li, Haizhou Sedoc, Joao D'haro, Luis F. Banchs, Rafael Rudnicky, Alexander Guardian Robot Project R-IH RIKEN 2-2-2 Hikaridai Seika Shoraku619-0288 Japan Information Science Nara Institute of Science and Technology Ikoma630-0101 Japan Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Inc. Palo AltoCA95054 United States Alexa AI *** Inc. SunnyvaleCA94089 United States Meta Seattle RedmondWA98052 United States Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Tencent AI Lab Beijing Beijing China Kexueyuan South Road Zhongguancun Beijing100190 China Beijing 100190 China Alexa AI *** Inc. SunnyvaleCA United States 1120 Enterprise way Sunnyvale94089 United States *** Inc. SeattleWA United States Menlo Park CA United States Audio and Speech Group Mitsubishi Electric Research Laboratories CambridgeMA02139-1955 United States Carnegie Mellon University Department of Language and Information Technologies or just Carnegie Mellon University Pittsburgh United States National University of Singapore Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Shenzhen Research Institute of Big Data School of Data Science Chinese University of Hong Kong Shenzhen518172 China New York University New YorkNY United States ETSI de Telecomunicacion - Speech Technology and Machine Learning Group Universidad Politecnica de Madrid Ciudad Universitaria Madrid28040 Spain Nanyang Technological University Singapore Singapore Carnegie Mellon University PittsburghPA United States

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situated Interactive Multimodal dialogs, 4. Reasoning for Audio Visual Scene-Aware Dialog, and 5. Automatic Evaluation and Moderation of Open-domainDialogue Systems. This article describes the task definition, provided datasets, baselines, and evaluation setup for each track. We also summarize the results of the submitted systems to highlight the general trends of the state-of-the-art technologies for the tasks. © 2023 The Authors.

关键词： Job analysis

来源：评论

学校读者我要写书评

暂无评论

A scoring system of oral english-Chinese translation based on frame semantic analysis 6

A scoring system of oral english-Chinese translation based o...

引用

6th International Conference on Systems and Informatics, ICSAI 2019

作者： Li, Xinguang Long, Xiaolan Long, Yan Liang, Chuhua Laboratory of Language Engineering and Computing Guangdong University of Foreign Studies Guangzhou China School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou China

ISBN: (纸本)9781728152561

In recent years, there has been an increasing interest in speech evaluation. However, most of the automatic evaluation systems focus on evaluating the quality of retelling questions and reading questions. In our best knowledge, research evaluating the quality of English-Chinese oral translation questions have not been found. This paper proposed an automatic method for scoring English-Chinese oral translation. This method leveraged three indicators, including key words, general idea of sentences and fluency, as the basis of scoring. The key words indicator was evaluated by the synonym analysis at the lexical level to evaluate while the general idea of sentences indicator was evaluated by the framework semantic analysis at the sentence level. Then, fluency indicator was scored by the speed of the speech. The experimental results demonstrated that using Mel-frequency cepstral coefficients (MFCC) and the Hidden Markov Model (HMM) algorithm to identify the key words, the system achieved average recognition rate in answering keywords of 97.3%. There is a good possibility that the proposed method may be effective for key word recognition. © 2019 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Transfer Building of Multiword Expression Resource from Indonesian to Malay

Transfer Building of Multiword Expression Resource from Indo...

引用

International Conference on Asian language Processing (IALP)

作者： Wuying Liu Lin Wang Laboratory of Language Engineering and Computing Guangdong University of Foreign Studies Guangzhou China Xianda College of Economics and Humanities Shanghai International Studies University Shanghai China

ISBN: (数字)9781728176895

ISBN: (纸本)9781728176901

The scarcity of corpus makes multiword expression (MWE) extraction very difficult for some low-resource languages. The homology and similarity between languages bring a new opportunity about morphological transfer learning from rich-resource languages to low-resource languages. This paper addresses the issue of MWE extraction for relatively low-resource Malay, and proposes a novel transfer building algorithm from rich-resource Indonesian. The experimental results verify the effectiveness of our algorithm to extract Malay MWEs from Indonesian corpus, and also prove a strong computability of morphological transfer learning from Indonesian to Malay owing to the homology and similarity of the same Malay-Polynesian language branch of the Austronesian language family.

关键词： Feature extraction Internet Encyclopedias Electronic publishing Data mining Buildings Standards

来源：评论

学校读者我要写书评

暂无评论

Robust Deep Learning Framework for Predicting Respiratory Anomalies and Diseases 42

Robust Deep Learning Framework for Predicting Respiratory An...

引用

42nd Annual International Conferences of the IEEE engineering in Medicine and Biology Society, EMBC 2020

作者： Pham, Lam McLoughlin, Ian Phan, Huy Tran, Minh Nguyen, Truc Palaniappan, Ramaswamy University of Kent School of Computing Medway Kent United Kingdom University of Science and Technology of China National Engineering Laboratory for Speech and Language Information Processing Hefei China Queen Mary University School of Electronic Engineering and Computer Science London United Kingdom University of Oxford Nuffield Department of Anaesthesia United Kingdom Graz University of Technology Signal Processing and Speech Communication Lab Austria

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119908

This paper presents a robust deep learning framework developed to detect respiratory diseases from recordings of respiratory sounds. The complete detection process firstly involves front end feature extraction where recordings are transformed into spectrograms that convey both spectral and temporal information. Then a back-end deep learning model classifies the features into classes of respiratory disease or anomaly. Experiments, conducted over the ICBHI benchmark dataset of respiratory sounds, evaluate the ability of the framework to classify sounds. Two main contributions are made in this paper. Firstly, we provide an extensive analysis of how factors such as respiratory cycle length, time resolution, and network architecture, affect final prediction accuracy. Secondly, a novel deep learning based framework is proposed for detection of respiratory diseases and shown to perform extremely well compared to state of the art methods. © 2020 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

language-ontology-based russian-chinese basic sentence bank construction 10th

Language-ontology-based russian-chinese basic sentence bank ...

引用

10th International Symposium on Intelligence Computation and Applications, ISICA 2018

作者： Yao, Aigang Liu, Wuying Laboratory of Language Engineering and Computing Guangdong University of Foreign Studies GuangzhouGuangdong510420 China School of Information Science and Technology Jiujiang University JiujiangJiangxi332005 China

ISBN: (纸本)9789811364723

language ontology is one of the research hotspots in artificial intelligence, knowledge engineering and natural language processing. This paper discusses what kind of language ontology is needed for natural language processing and how to construct such language ontology, and tries to establish a Russian-Chinese bank of basic sentences for natural language processing based on language ontology. The final implementation of the language resource engineering shows the effectiveness of our novel construction approach. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Evolution analysis of information retrieval based on co-word network 3

Evolution analysis of information retrieval based on co-word...

引用

3rd IEEE International Conference on Electronic Information Technology and Computer engineering, EITCE 2019

作者： Zhang, Xinmeng Li, Xinguang Jiang, Shengyi Li, Xia Xie, Bolin Laboratory of Language Engineering and Computing Guangdong University of Foreign Studies Guangzhou Guangdong China Non-universal Language Intelligent Processing Laboratory Guangdong University of Foreign Studies Guangzhou Guangdong China School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou Guangdong China

ISBN: (纸本)9781728135847

With the development of natural language processing and artificial intelligence, remarkable progress has been made in the field of information retrieval In this paper, we selected papers on information retrieval from web of Science in the past ten years, and constructed a Co-word network based on the co-occurrence relationship of keywords in the same paper. By analyzing the evolution of the Co-word network community, the core evolution and the number of keyword status, we discussed the evolution of research focus in the field of information retrieval in the past ten years. The results show that natural language processing, medical information retrieval, image retrieval and social media retrieval are the focus of information retrieval research in recent years. © 2019 IEEE.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Identifying the Motives of Using Weibo from Digital Traces 20

Identifying the Motives of Using Weibo from Digital Traces

引用

Proceedings of the 4th International Conference on Natural language Processing and Information Retrieval

作者： Bi Li Boyu Chen Yan Wu Juan Wang Xueming Yan Yahui Yang Laboratory for Language Engineering and Computing Guangdong University of Foreign Studies Guangzhou China and School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou China School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou China Department of Applied Psychology Guangdong University of Foreign Studies Guangzhou China

ISBN: (纸本)9781450377607

Billions of users around the world are using social networking sites (SNS) to express everyday thoughts and feelings. Investigating motives of using SNS is attracting scholarly attention. The common way to assess users' motives is analyzing data from self-report questionnaires. The current research aims to identifying undergraduate students' motives of using Weibo from digital traces, in an effort to alleviate the distortion in self-report data. The term frequency-inverse document frequency (Tf-idf) was employed to obtain key terms and their weights in digital traces crawled from Weibo. Top frequent terms, based on Tf-idf, indicate that entertainment, information seeking and sharing, and alleviating life stress are among the major motives of using Weibo. This study underscores the feasibility and importance of directly detecting motives of using SNS from digital traces.

关键词： Digital traces

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：