Question Classification Method Research Articles

Development of Logic-Based Question Classification Methods to Measure the Ability to Ask Questions Essential for Setting Research Questions

Development of Logic-Based Question Classification Methods to Measure the Ability to Ask Questions Essential for Setting Research Questions

Classification of crop disease-pest questions based on BERT-BiGRU-CapsNet with attention pooling.

Crop disease-pest question classification is an essential part of pest knowledge intelligent question answering system. A crop disease-pest question classification method is proposed on the basis of bidirectional encoder representations from transformers (BERT), bidirectional gated unit (BiGRU), capsule network (CapsNet), and BERT-BiGRU-CapsNet with attention pooling (BBGCAP). In BBGCAP, the unstructured text data are preprocessed vectorically using BERT, BiGRU is used to extract the deep features of the text, attention pooling is used to assign the corresponding weights to the extracted deep information, and CapsNet is used to route the right alternative. BBGCAP is a synthetic model by integrating the advantages of BERT, BiGRU, CapsNet, and attention pooling. The experimental results on the cucumber-pest question database show that the proposed method is superior to the methods based on traditional template matching, support vector machines (SVM), and convolutional neural network-long short-term memory (LSTM), and the accuracy rates of precision, recall, and F1 are all above 902.15%. This method provides technical support for intelligent question answering system of crop disease-pests.

OEQA: Knowledge- and Intention-Driven Intelligent Ocean Engineering Question-Answering Framework

The constantly updating big data in the ocean engineering domain has challenged the traditional manner of manually extracting knowledge, thereby underscoring the current absence of a knowledge graph framework in such a special field. This paper proposes a knowledge graph framework to fill the gap in the knowledge management application of the ocean engineering field. Subsequently, we propose an intelligent question-answering framework named OEQA based on an ocean engineering-oriented knowledge graph. Firstly, we define the ontology of ocean engineering and adopt a top-down approach to construct a knowledge graph. Secondly, we collect and analyze the data from databases, websites, and textual reports. Based on these collected data, we implement named entity recognition on the unstructured data and extract corresponding relations between entities. Thirdly, we propose an intent-recognizing-based user question classification method, and according to the classification result, construct and fill corresponding query templates by keyword matching. Finally, we use T5-Pegasus to generate natural answers based on the answer entities queried from the knowledge graph. Experimental results show that the accuracy in finding answers is 89.6%. OEQA achieves in the natural answer generation in the ocean engineering domain significant improvements in relevance (1.0912%), accuracy (4.2817%), and practicability (3.1071%) in comparison to ChatGPT.

Preciser comparison: Augmented multi-layer dynamic contrastive strategy for text2text question classification

Text2text question classification (TQC), as a particular application case of question classification (QC), is of great practical value. Traditional QC methods usually label categories of questions using one or multiple keywords provided by users. In contrast, in TQC, each question in natural language is automatically categorized into pre-designed standard question classes, which are coded in the form of short text. Because of this unique characteristic, TQC relies on a specifically designed framework and should be trained and validated based on customized experimental datasets. Previous TQC-related work mainly utilized textual similarity-matching methods. However, no effective pairwise learning paradigm has been proposed in TQC to model correlations between input text and classes; and the influence of distance metrics and loss function in TQC has not been investigated. In this work, we propose a novel and comprehensive strategy, Augmented Dynamic Multi-layer Contrastive (ADMC), to resolve the challenge of TQC. Our framework consists of (1) an optional data augmentation module, (2) one stage for dynamic negative sampling, and (3) one stage for precise matching. The comprehensive TQC framework with ADMC strategy in this work resolves data imbalance and explores distance metrics learning via multiple augmentation options and dynamic negative sampling based on multi-layer contrastive learning. To compensate for the shortage of public datasets for this task, we collected two real-world datasets and adaptively expanded three existing public datasets, which will be available after data masking. The results show that our ADMC outperformed other baseline methods investigated in this paper. The codes are available at https://github.com/WJULYW/ADMC.

Different Approaches for Multi-Class Classification using Machine Learning Techniques

Web content increasing in every sector has become challenging task to find the useful information. Question Answering system in agriculture domain help farmers to provide the accurate answer. Farmer asking the queries relevant to pomegranate fruit in which question classification plays an important role for various questions asked by farmer to categorize or to identifY the type of question Different question classification methods have been proposed to provide solutions for classification of question. In this research, we are considering the different pomegranate questions that can be asked by farmer to classify the questions correctly using different machine learning methods. A proposed framework for question classification having multiple classes i.e.name, descriptive, location, numeric and entity: other which enables machine learning algorithms to categorize the type of question. This paper compares various machine learning algorithms and result shows K-Nearest Neighbor, SYM & Decision tree performed well with good accuracy.

Deep Transfer Learning for Question Classification Based on Semantic Information Features of Category Labels.

Question classification is an important component of the question answering system (QA system), which is designed to restrict the answer types and accurately locate the answers. Therefore, the classification results of the questions affect the quality and performance of the QA system. Most question classification methods in the past have relied on a large amount of manually labeled training data. However, in real situations, especially in new domains, it is very difficult to obtain a large amount of labeled data. Transfer learning is an effective approach to solve the problem with the scarcity of annotated data in new domains. We compare the effects of different deep transfer learning methods on cross-domain question classification. On the basis of the ALBERT fine-tuning model, we extract the category labels of the source domain, the question text, and the predicted category labels of the target domain as input to extract the category labels. Additionally, the semantic information of the category labels is extracted to achieve cross-domain question classification. Furthermore, WordNet is used to expand the question, which further improves the classification accuracy of the target domain. Experimental results show that the above methods can further improve the classification accuracy in new domains based on deep transfer learning.

Embedding arabic questions by feature-level fusion of word representations for questions classification: It is worth doing?

Questions classification remains one of the most critical phases of Question Answering Systems. It aims to reduce the answers search space by assigning a predefined class label to each question. Recently, contextualized word representations methods based on deep learning approach have achieved state of the art performance in various fields of Natural Language Processing. However, few works have applied these representations to classify Arabic questions. In this research, we propose an Arabic question classification method based on a sentence transformers-based representation. Besides, we investigate the fusion of various word representations including Bidirectional Encoder Representations from Transformers (BERT), Embeddings from Language Models (ELMo), and word embeddings enriched by subwords information (W2V). Our contribution is threefold. First, our method handles out of vocabulary words. Second, we apply the BERT representation to extract the most valuable features from words and then construct better question representation. Third, we study the impact of fusing various word embeddings on Arabic question classification. To evaluate the proposed models, we perform stratified 5-folds cross-validation on a dataset containing 3173 questions labeled with Arabic and Li & Roth taxonomies. The experimental results show that all our models surpassed previous works related to Arabic question classification task. In the Arabic taxonomy case, we scored the maximum accuracy of 94.20% with our AraBERT-based model. As for Li & Roth taxonomy, the model based on the concatenation of AraBERT and W2V scored the highest overall accuracy of 93.51%.

Classification of Arabic healthcare questions based on word embeddings learned from massive consultations: a deep learning approach

Automated question classification is a fundamental component of automated question-answering systems, which plays a critical role in promoting medical and healthcare services. Developing an automated question classification system depends heavily on natural language processing and data mining techniques. Question classification methods based on classical machine learning techniques face limitations in capturing the hidden relationships of features, as well as, handling complex languages and very large-scale datasets. Therefore, this paper proposes a deep learning approach for question classification, since deep learning methods have the powerful capability to extract implicit, hidden relationships and automatically generate dense representations of features. The proposed question classification model depends on unidirectional and bidirectional long short-term memory networks (LSTM and BiLSTM), which essentially developed to handle the Arabic language in the field of healthcare. The features are represented and created using a domain-specific word embedding model (Word2Vec) that is constructed by training around 1.5 million medical consultations from Altibbi company. Altibbi is a telemedicine company that is used as a case study and a source for curating and collecting the data. The proposed deep learning approach is a multi-class classification algorithm that automatically labels and maps the questions into 15 categories of medical specialities. The proposed deep learning model is evaluated using several evaluation metrics, including accuracy, precision, recall, and F1-score. Markedly, the proposed model achieved a superb classification capacity in terms of classification accuracy rate, which gained 87.2%.

Contextual Word Representation and Deep Neural Networks-based Method for Arabic Question Classification

Contextual Word Representation and Deep Neural Networks-based Method for Arabic Question Classification

Deep Refinement: capsule network with attention mechanism-based system for text classification

Most of the text in the questions of community question–answering systems does not consist of a definite mechanism for the restriction of inappropriate and insincere content. A given piece of text can be insincere if it asserts false claims or assumes something which is debatable or has a non-neutral or exaggerated tone about an individual or a group. In this paper, we propose a pipeline called Deep Refinement which utilizes some of the state-of-the-art methods for information retrieval from highly sparse data such as capsule network and attention mechanism. We have applied the Deep Refinement pipeline to classify the text primarily into two categories, namely sincere and insincere. Our novel approach ‘Deep Refinement’ provides a system for the classification of such questions in order to ensure enhanced monitoring and information quality. The database used to understand the real concept of what actually makes up sincere and insincere includes quora insincere question dataset. Our proposed question classification method outperformed previously used text classification methods, as evident from the F1 score of 0.978.

An arabic question classification method based on new taxonomy and continuous distributed representation of words

The unability of search engines to retrieve precise answer for a given question leads research teams to build question answering systems (QAS). These systems provide exact answers of questions formulated in natural languages. Question classification is a crucial task for QAS since finding the correct answer type increases the performance of this latter. The questions taxonomy plays an important role in question classification. A broad range of taxonomies are proposed; most of these are not designed for Arabic questions. The contribution of the paper is twofold. First, we build a taxonomy for open domain Arabic questions. Second, we propose an efficient method for classifying Arabic questions. The basic idea consists of two stages: first, we compute representation of questions according to continuous distributed representation of words which allows to capture syntactic and semantic relations between words. Then, we apply a machine learning approach to classify questions into seven types or categories. We carried out several experiments and compared the proposed method with different state of arts Arabic question classification methods. Experimental results show that the proposed method achieves 90% in terms of accuracy.

Semi-supervised learning for question classification in CQA

In a community question answering (CQA) system, the new questions are appeared endlessly which have no tags. And the questions must be marked as some labels. Therefore, the question classification is very important for CQA. In the traditional task of question classification, a mass of labeled questions are required. In the real world, it is effortless to obtain a large number of unlabeled question samples and the vast labeled question samples are fairly expensive to obtain. Therefore, how to utilize the unlabeled samples to improve the question classification accuracy has been the core question of the question classification. In this paper, a kind of semi-supervised question classification method based on ensemble learning is proposed. Firstly, several classifiers are combined as one, i.e. ensemble classifier. The ensemble classifier is trained firstly to utilize a small number of labeled question samples. Secondly, the trained preliminary classifier gives each of the unlabeled question samples a pseudo label. Then, the ensemble classifier is trained again to use the labeled question samples and a large number of unlabeled question samples which have pseudo labels. Finally, to verify the effectiveness of the method through the experiments on question samples of 15 classes extracted from the community question answering system. The experiments demonstrate that the method could effectively utilize a large number of unlabeled question samples to improve the question classification accuracy.

Factor-analysis based questionnaire categorization method for reliability improvement of evaluation of working conditions in construction enterprises

This paper presents a factor-analysis based questionnaire categorization method to improve the reliability of the evaluation of working conditions without influencing the completeness of the questionnaire both in Taiwanese and Chinese construction enterprises for structural engineering applications. The proposed approach springs from the AI application and expert systems in structural engineering. Questions with a similar response pattern are grouped into or categorized as one factor. Questions that form a single factor usually have higher reliability than the entire questionnaire, especially in the case when the questionnaire is complex and inconsistent. By classifying questions based on the meanings of the words used in them and the responded scores, reliability could be increased. The principle for classification was that 90% of the questions in the same classified group must satisfy the proposed classification rule and consequently the lowest one was 92%. The results show that the question classification method could improve the reliability of the questionnaires for at least 0.7. Compared to the question deletion method using SPSS, 75% of the questions left were verified the same as the results obtained by applying the classification method.

Question classification in restricted domain using syntactic parsing-based quadratic-Bayesian model

In this paper,a new method using syntactic parsing-based quadratic-Bayesian model was proposed to perform question classification in Chinese restricted domain.In this method,firstly,the shallow syntactic parsing on Chinese question sentences was performed.Secondly,the subject-predicate structures of all parsed question sentences,as well as interrogative words and their adjunctive parts,were extracted as the features in this constructed classifier,which greatly reduced the noise information.Thirdly,an advanced quadratic-Bayesian classification model for question classification in restricted domain was constructed.The experimental results show that the proposed question classification method is feasible in restricted domain and the average classification precisions of coarse classes and fine classes reach 89.66 percent and 84.13 percent respectively.

질문대답 아카이브에서 어휘 연관성을 이용한 질문 분류

Word mismatch is the most significant problem that causes low performance in question classification, whose questions consist of only two or three words that expressed in many different ways. So, it is necessary to apply word association in question classification. In this paper, we propose question classification method using translation-based language model, which use word translation probabilities for question-question pair that is learned in the same category. In the experiment, we prove that translation probabilities of question-question pairs in the same category is more effective than question-answer pairs in total collection.

A semantic approach for question classification using WordNet and Wikipedia

Question Answering Systems, unlike search engines, are providing answers to the users’ questions in succinct form which requires the prior knowledge of the expectation of the user. Question classification module of a Question Answering System plays a very important role in determining the expectations of the user. In the literature, incorrect question classification has been cited as one of the major factors for the poor performance of the Question Answering Systems and this emphasizes on the importance of question classification module designing. In this article, we have proposed a question classification method that exploits the powerful semantic features of the WordNet and the vast knowledge repository of the Wikipedia to describe informative terms explicitly. We have trained our system over a standard set of 5500 questions (by UIUC) and then tested it over five TREC question collections. We have compared our results with some standard results reported in the literature and observed a significant improvement in the accuracy of question classification. The question classification accuracy suggests the effectiveness of the method which is promising in the field of open-domain question classification. Judging the correctness of the answer is an important issue in the field of question answering. In this article, we are extending question classification as one of the heuristics for answer validation. We are proposing a World Wide Web based solution for answer validation where answers returned by open-domain Question Answering Systems can be validated using online resources such as Wikipedia and Google. We have applied several heuristics for answer validation task and tested them against some popular web based open-domain Question Answering Systems over a collection of 500 questions collected from standard sources such as TREC, the Worldbook, and the Worldfactbook. The proposed method seems to be promising for automatic answer validation task.

Analysis of Statistical Question Classification for Fact-Based Questions

Question classification systems play an important role in question answering systems and can be used in a wide range of other domains. The goal of question classification is to accurately assign labels to questions based on expected answer type. Most approaches in the past have relied on matching questions against hand-crafted rules. However, rules require laborious effort to create and often suffer from being too specific. Statistical question classification methods overcome these issues by employing machine learning techniques. We empirically show that a statistical approach is robust and achieves good performance on three diverse data sets with little or no hand tuning. Furthermore, we examine the role different syntactic and semantic features have on performance. We find that semantic features tend to increase performance more than purely syntactic features. Finally, we analyze common causes of misclassification error and provide insight into ways they may be overcome.