Filters








381,110 Hits in 5.7 sec

An Effective Feature-Weighting Model for Question Classification

Peng Huang, Jiajun Bu, Chun Chen, Guang Qiu
2007 2007 International Conference on Computational Intelligence and Security (CIS 2007)  
The main characteristic of this model is assigning more reasonable weight to features: these weights can be used to differentiate features each other according to their contribution to question classification  ...  Question classification is one of the most important subtasks in Question Answering systems. Now question taxonomy is getting larger and more fine-grained for better answer generation.  ...  Conclusions In this paper we have proposed an effective featureweighting model for question classification.  ... 
doi:10.1109/cis.2007.12 dblp:conf/cis/HuangBCQ07 fatcat:vzttwb2ylbcenlwkivnyxh27r4

An effective category classification method based on a language model for question category recommendation on a cQA service

Kyoungman Bae, Youngjoong Ko
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
In this paper, we propose a novel effective word weighting method based on a language model for automatic category classification in the cQA service.  ...  The word weighting method must estimate the appropriate weight of a word to improve the category (or topic) classification.  ...  We assume that words with negative weights are bad features for category classification.  ... 
doi:10.1145/2396761.2398614 dblp:conf/cikm/BaeK12 fatcat:dw6gdr2mijgmvjjsp7lsrsbnae

A semantic approach for question classification using WordNet and Wikipedia

Santosh Kumar Ray, Shailendra Singh, B.P. Joshi
2010 Pattern Recognition Letters  
Identifying the relevant approach for question classification for a specific domain is one of the foremost tasks.  ...  To overcome these issues, we employ a question classifier using Register Linear (RL) models for a specific domain.  ...  problem for the question classes in an effective manner.  ... 
doi:10.1016/j.patrec.2010.06.012 fatcat:mym5j5pthzgx5akqzpotye47bi

Identifying Optimal Baseline Variant of Unsupervised Term Weighting in Question Classification Based on Bloom Taxonomy

Anbuselvan Sangodiah, Tham Jee San, Yong Tien Fui, Lim Ean Heng, Ramesh Kumar Ayyasamy, Norazira A Jalil
2022 The MENDEL Soft Computing journal : International Conference on Soft Computing MENDEL  
Feature selection, feature extraction and term weighting are common ways to improve the accuracy of question classification.  ...  Therefore, the normalized TF-IDF3 variant is important for benchmarking purposes, which can be used to compare with other term weighting t [...]  ...  In another research (3), an exam classification framework is proposed by using different feature types.  ... 
doaj:c5afcd8c7d34495e8cdc61310341c840 fatcat:xxth35bxi5afvfqngcfmcw3og4

A Densely Connected GRU Neural Network Based on Coattention Mechanism for Chinese Rice-Related Question Similarity Matching

Haoriqin Wang, Huaji Zhu, Huarui Wu, Xiaomin Wang, Xiao Han, Tongyu Xu
2021 Agronomy  
To alleviate the problem of feature vector size increasing due to dense splicing, an autoencoder was used after dense concatenation.  ...  Compared with seven other kinds of question similarity matching models, we present a new state-of-the-art method with our rice-related question dataset.  ...  Figure 4 shows the classification effect of models 1-7 on the rice-related question dataset at different GRU levels.  ... 
doi:10.3390/agronomy11071307 fatcat:qag5pszb5fh35m5whxvimlrjhu

Dependency Based Embeddings for Sentence Classification Tasks

Alexandros Komninos, Suresh Manandhar
2016 Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
We explore the effectiveness of the different types of word embeddings for word similarity and sentence classification tasks.  ...  We compare different word embeddings from a standard window based skipgram model, a skipgram model trained using dependency context features and a novel skipgram variant that utilizes additional information  ...  Conclusions We compare a window based, a dependency based and an extended dependency based skipgram model in word similarity and sentence classification tasks of question classification, binary sentiment  ... 
doi:10.18653/v1/n16-1175 dblp:conf/naacl/KomninosM16 fatcat:ptipx7awinfxbj3j4dm5nc6b3a

Multiple interaction learning with question-type prior knowledge for constraining answer search space in visual question answering [article]

Tuong Do, Binh X. Nguyen, Huy Tran, Erman Tjiputra, Quang D. Tran, Thanh-Toan Do
2020 arXiv   pre-print
reliable cue to reason about answers for questions asked in input images.  ...  In this paper, we propose a novel VQA model that utilizes the question-type prior information to improve VQA by leveraging the multiple interactions between different joint modality methods based on their  ...  features and learn attention weights to weight for visual and/or linguistic features.  ... 
arXiv:2009.11118v1 fatcat:t7ta6gjvxvdgjmg3xkytgpqfvi

Identifying Cognitive Impairment Using Sentence Representation Vectors

Bahman Mirheidari, Yilin Pan, Daniel Blackburn, Ronan O'Malley, Heidi Christensen
2021 Conference of the International Speech Communication Association  
The in-house dataset contains the audio recordings of an intelligent virtual agent (IVA) who asks the participants several conversational questions prompts in addition to giving a picture description prompt  ...  We use a sliding window and averaging approach for pre-processing text for BERT to extract features for classifying three diagnostic categories relating to cognitive impairment: neurodegenerative dis-order  ...  Using the features we determine a subset of questions that are more useful for the classification (question selection process).  ... 
doi:10.21437/interspeech.2021-915 dblp:conf/interspeech/MirheidariPBOC21 fatcat:4a7orre5bjgl3jz2xfom4cp2ru

Initializing Convolutional Filters with Semantic Features for Text Classification

Shen Li, Zhe Zhao, Tao Liu, Renfen Hu, Xiaoyong Du
2017 Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing  
This paper presents a novel weight initialization method to improve the CNNs for text classification.  ...  Instead of randomly initializing the convolutional filters, we encode semantic features into them, which helps the model focus on learning useful features at the beginning of the training.  ...  Naive Bayes (NB) weighting is an effective technique for determining the words' importance (Martineau and Finin, 2009; Wang and Manning, 2012) .  ... 
doi:10.18653/v1/d17-1201 dblp:conf/emnlp/LiZLHD17 fatcat:ju2qekiutfhffbsxwdu42gvmay

The Research of Convolutional Neural Network Based on Integrated Classification in Question Classification

Lihua Zhen, Xiaoqi Sun, Tongguang Ni
2021 Scientific Programming  
On the study of existing CNN research, an improved CNN model based on Bagging integrated classification ("W2V + B-CNN" for short) is proposed and applied to question classification.  ...  However, as an indispensable part of the QAS, the role of question classification is an understood thing in the system.  ...  a better question classification effect.  ... 
doi:10.1155/2021/4176059 fatcat:wvvpfali3jb43lbaymfeuvamfi

A combination fingerprint classifier

A. Senior
2001 IEEE Transactions on Pattern Analysis and Machine Intelligence  
AbstractÐFingerprint classification is an important indexing method for any large scale fingerprint recognition system or database as a method for reducing the number of fingerprints that need to be searched  ...  This paper describes novel methods of classification using hidden Markov models (HMMs) and decision trees to recognize the ridge structure of the print, without needing to detect singular points.  ...  The procedure has been adopted here for fingerprint classification and involves an initial feature extraction phase, followed by question building which creates informative questions assisting in classification  ... 
doi:10.1109/34.954606 fatcat:54qjuujj6nee3pywe33wg2fn4i

MuVAM: A Multi-View Attention-based Model for Medical Visual Question Answering [article]

Haiwei Pan, Shuning He, Kejia Zhang, Bo Qu, Chunling Chen, Kun Shi
2021 arXiv   pre-print
Since most current medical VQA models focus on visual content, ignoring the importance of text, this paper proposes a multi-view attention-based model(MuVAM) for medical visual question answering which  ...  Firstly, different methods are utilized to extract the features of the image and the question for the two modalities of vision and text.  ...  As an example is shown in Fig. (3) , for the question "Is there an acute bleed present?", this is obviously a closedended question, and the correct answer is "Yes".  ... 
arXiv:2107.03216v1 fatcat:4yqcxspwjrdphl6x22naqvh2aq

Question Text Classification Method of Tourism Based on Deep Learning Model

Wanli Luo, Lei Zhang, Mohammad R Khosravi
2022 Wireless Communications and Mobile Computing  
, this paper proposes a text classification method of tourism questions based on deep learning model.  ...  Aiming at the problems that machine learning and single structure deep learning model cannot effectively grasp the text emotional information in text processing, resulting in poor classification effect  ...  Acknowledgments We wish to express their appreciation to the reviewers for their helpful suggestions which greatly improved the presentation of this paper.  ... 
doi:10.1155/2022/4330701 fatcat:y7p3xc4dgrblffhbnbhguqohcu

MODEL ADAPTATION FOR DIALOG ACT TAGGING

Gokhan Tur, Umit Guz, Dilek Hakkani-Tur
2006 2006 IEEE Spoken Language Technology Workshop  
In this paper, we analyze the effect of model adaptation for dialog act tagging. The goal of adaptation is to improve the performance of the tagger using out-of-domain data or models.  ...  Dialog act tagging aims to provide a basis for further discourse analysis and understanding in conversational speech.  ...  We thank Andreas Stolcke and Elizabeth Shriberg for many helpful discussions.  ... 
doi:10.1109/slt.2006.326825 dblp:conf/slt/TurGH06 fatcat:jig4l3jn7vflnjfmkfttmtraky

Ensemble of feature sets and classification algorithms for sentiment classification

Rui Xia, Chengqing Zong, Shoushan Li
2011 Information Sciences  
In this paper, we make a comparative study of the effectiveness of ensemble technique for sentiment classification.  ...  First, two types of feature sets are designed for sentiment classification, namely the part-of-speech based feature sets and the word-relation based feature sets.  ...  The ensemble technique, which combines the outputs of several base classification models to form an integrated output, has become an effective classification method for many domains [13, 17] .  ... 
doi:10.1016/j.ins.2010.11.023 fatcat:z4mxmo4hufggdhkzwgn7fu46ue
« Previous Showing results 1 — 15 out of 381,110 results