检索结果-内蒙古大学图书馆

International Conference on Control Communication & Computing India (ICCC)

作者： Raj, Rekha C. T. Raj, Reghu P. C. Govt Engn Coll Dept Comp Sci & Engn Sreekrishnapuram 678633 Kerala India

ISBN: (纸本)9781467373494

Text chunking consists of dividing a text into syntactically correlated parts of words. Given the words and their morphosyntactic class, a chunker will decide which words can be grouped as chunks. Malayalam is a free word order language and has relatively unrestricted phrase structures that make the problem of chunking quite challenging. This paper aims to develop a text chunker for Malayalam using memory-based learning (MBL) approach. memory-based learning is a machine learning methodology based on the idea that the direct reuse of examples using analogical reasoning is more suited for solving language processing problems than the application of rules extracted from those examples. The chunker was trained using the tool memory-based Tagger (MBT) with words and their POS tags as features. The chunker demonstrated an accuracy of 97.14%.

关键词： Malayalam Chunking Shallow parsing POS Tagging memory based learning memory based Natural Language Processing Natural Language Processing Machine learning

来源：评论

学校读者我要写书评

暂无评论

Self-supervised on-line cumulative learning from video streams

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2020年 197卷 102983-102983页

作者： Pernici, Federico Bruni, Matteo Del Bimbo, Alberto Univ Firenze Media Integrat & Commun Ctr Dept Informat Engn MICC Florence Italy

We present a novel online self-supervised method for face identity learning from video streams. The method exploits deep face feature descriptors together with a memory based learning mechanism that takes advantage of the temporal coherence of visual data. Specifically, we introduce a discriminative descriptor matching solution based on Reverse Nearest Neighbor and a memory based cumulative learning strategy that discards redundant descriptors while time progresses. This allows building a comprehensive and cumulative representation of all the past visual information observed so far. It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications like multiple face identification and tracking from unconstrained video streams. Experimental results show that the proposed method achieves comparable results in the task of multiple face tracking and better performance in face identification with offline approaches exploiting future information.

关键词： Incremental learning Cumulative learning memory based learning Multiple Object Tracking Face Recognition Lifelong learning Long Term Object Tracking

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Named Entity Recognition for Telugu 17

A Comparative Study of Named Entity Recognition for Telugu

引用

9th Annual Meeting of the Forum-for-Information-Retrieval-Evaluation (FIRE)

作者： Gorla, SaiKiranmai Murthy, N. L. Bhanu Malapati, Aruna Birla Inst Technol & Sci Pilani Hyderabad Campus Hyderabad Telangana India

ISBN: (纸本)9781450363822

In this paper, we apply three classification learning algorithms to Telugu Named Entity Recognition (NER) task and we present a comparative study between these three learning algorithms on Telugu dataset (NER for South and South-East Asian Languages (NERSSEAL) Competition). The empirical results show that Support Vector Machine achieves the best F-measure of 54.78% on the dataset.

关键词： Named Entity Recognition Named Entity Telugu memory based learning Support Vector Machine Conditional random Field

来源：评论

学校读者我要写书评

暂无评论

Sandhi Splitter for Malayalam Using MBLP Approach

引用

Procedia Technology 2016年 24卷 1522-1527页

作者： M. Nisha P.C. Reghu Raj Mtech Scholar Department of Computer Science and Engineering Government Engineering College Sreekrishnapuram Palakkad Kerala Assistant Professor Department of Computer Science and Engineering Government Engineering College Sreekrishnapuram Palakkad Kerala

The morphological richness and the agglutinative nature of Malayalam make it necessary to retrieve the root word from its inflected form in most of the NLP tasks. This paper presents an approach to identify the suffixes of Malayalam words using MBLP approach. The idea here is to use memory based Language Processing (MBLP) algorithm for Malayalam suffix identification. MBLP is an approach to language processing based on exemplar storage during learning and analogical reasoning during processing. Sandhi splitting is essential for morphological analysis, document indexing and topic modeling. Suffix separation improves the quality of machine translated text. Training instances created from words are manually annotated for their segmentation and the system is trained using TiMBL (Tilberg memory based Learner). The paper presents memory-based model of Malayalam suffix identification and its generalization accuracy.

关键词： Malayalam Morphology memory based learning memory based Language Processing

来源：评论

学校读者我要写书评

暂无评论

memory-based in situ learning for unmanned vehicles

引用

COMPUTER 2006年第12期39卷 62-+页

作者： McDowell, Patrick Bourgeois, Brian S. Sofge, Donald A. Iyengar, S. S. USN Res Lab Position Navigat & Timing Team Stennis Space Ctr MS 39529 USA USN Res Lab Ctr Appl Res Artificial Intelligence Washington DC 20375 USA Indian Inst Sci Bangalore 560012 Karnataka India Louisiana State Univ Baton Rouge LA 70803 USA

Researchers are using a sensor-input-based metric to develop a team of robots that would have the capability to learn their roles and improve strategies so that they can meet their overall goals in dynamic unstructure... 详细信息

关键词： Underwater Vehicles learning Artificial Intelligence Remotely Operated Vehicles Robots Sensors UUV memory based learning Unmanned Underwater Vehicles Robot Teams Sensor Input based Metric Robot Sensing Systems Underwater Vehicles Animals Testing Hazards Oceans Environmental Economics Government Costs Vehicle Dynamics learning Algorithms Unmanned Vehicles Robotics

来源：评论

学校读者我要写书评

暂无评论

Vision-Motor Abstraction toward Robot Cognition

引用

16th International Conference on Neural Information Processing (ICONIP 2009)

作者： Alnajjar, Fady Hafiz, Abdul Rahman Zin, Indra Bin Mohd Murase, Kazuyuki Univ Fukui Grad Sch Engn Fukui Japan

ISBN: (纸本)9783642106828

based on indications from neuroscience and psychology, both perception and action can be internally simulated in organisms by activating sensory and/or motor areas in the brain without actual sensory input and/or without any resulting behavior. This phenomenon is usually used by the organisms to cope with missing external inputs. Applying such a phenomenon in a real robot recently has taken the attention of many researchers. Although some work has been reported on this issue, none of it has so far considered the potential of the robot's vision at the sensorimotor abstraction level, where extracting data from the environment to build the internal representation takes place. In this study, a novel vision-motor abstraction is presented into a physically robot through a memory-based learning algorithm. Experimental results indicate that our robot with its vision could develop a simple anticipation mechanism in its memory from the interacting with the environment. This mechanism could guide the robot behavior in the absence of external inputs.

关键词： Vision-motor abstraction memory based learning cognition

来源：评论

学校读者我要写书评

暂无评论

Multi-level information and automatic dialog act detection in human-human spoken dialogs

引用

SPEECH COMMUNICATION 2008年第1期50卷 1-13页

作者： Rosset, S. Tribout, D. Lamel, L. LIMSI CNRS Spoken Language Proc Grp F-91403 Orsay France

This paper reports studies on annotating and automatically detecting dialog acts in human-human spoken dialogs. The work reposes on three hypotheses: first, the succession of dialog acts is strongly constrained;second, the initial word and semantic class of word are more important for identifying dialog acts than the complete exact word sequence of an utterance;third, most of the important information is encoded in specific entities. A memory based learning approach is used to detect dialog acts. For each utterance unit, eight dialog acts are systematically annotated. Experiments have been conducted using different levels of information, with and without the use of dialog history information. In order to assess the generality of the method, the specific entity tag based model trained on a French corpus was tested on an English corpus for a similar task and on a French corpus from a different domain. A correct dialog act detection rate of about 86% is obtained for the same domain/language condition and 77% for the cross-language or cross-domain conditions., (c) 2007 Elsevier B.V. All rights reserved.

关键词： automatic dialog act detection human-human dialogs memory based learning

来源：评论

学校读者我要写书评

暂无评论

Dutch plural inflection: The exception that proves the analogy

引用

COGNITIVE PSYCHOLOGY 2007年第4期54卷 283-318页

作者： Keuleers, Emmanael Sandra, Dorniniek Daelemans, Walter Gillis, Steven Durieux, Gert Martens, Evelyn Univ Antwerp Ctr Psycholinguist B-2020 Antwerp Belgium Univ Antwerp Ctr Dutch Language & Speech Antwerp Belgium

We develop the view that inflection is driven partly by non-phonological analogy and that nonphonological information is of particular importance to the inflection of non-canonical roots, which in the view of [Marcus, G. F., Brinkmann, U., Clahsen, H., Wiese, R., & Pinker, S. (1995). German inflection: the exception that proves the rule. Cognitive Psychology, 29, 189-256.] are inflected by a symbolic rule process. We used the Dutch plural to evaluate these claims. An analysis of corpus data shows that a model using non-phonological information (orthography) produces significantly fewer errors on plurals of non-canonical Dutch nouns, in particular borrowings, than a model that includes only phonological information. Moreover, we show that a double default system, as proposed by Pinker [Pinker, S. (1999). Words and rules. London: Phoenix.], does not offer an advantage over the latter model. A second study, examining the use of orthography in an online plural production task, shows that, in Dutch, the chosen pseudoword plural is significantly affected by non-phonological information. A final simulation study confirms that these results are in line with a model of inflectional morphology that explains the inflection of non-canonical roots by non-phonological analogy instead of by a default rule process. (C) 2006 Elsevier Inc. All rights reserved.

关键词： dual mechanism model memory based learning default rules similarity analogy inflection Dutch plural non-canonical roots morphology

来源：评论

学校读者我要写书评

暂无评论

Instance metrics improvement by probabilistic support

引用

Mexican International Conference on Artificial Intelligence (MICAI 2000)

作者： Jiménez, H Morales, G Univ Autonoma Puebla Fac Ciencias Fis Matemat Puebla 72570 Mexico IPN Ctr Invest & Estudios Avanzados Mexico City DF Mexico

ISBN: (纸本)3540673547

The use of distance functions in order to determine nearest instance class at memory based learning methods may be crucial when there are no exact matchings. We add relative information over unknown feature values to improve the information extract on the training instances. An experiment was carried out for Spanish Part-Of-Speech tagging of unknown words finding a Letter performance with our modi fled function.

关键词： memory based learning inexact matching Spanish Part-Of-Speech tagging unknown words

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：