Question categorization and classification using grammar based approach

This paper describes two experiments carried out in order to investigate the role of visuals in multimodal answer presentations for a medical question answering system. First, a production experiment was carried out to determine which modalities people choose to answer different types of questions. In this experiment, participants had to create (multimodal) presentations of answers to general medical questions. The collected answer presentations were coded on the presence of visual media (i.e., photos, graphics, and animations) and their function. The results indicated that participants presented the information in a multimodal way. Moreover, significant differences were found in the presentation of different answer and question types. Next, an evaluation experiment was conducted to investigate how users evaluate different types of multimodal answer presentations. In this second experiment, participants had to assess the informativity and attractiveness of answer presentations for different types of medical questions. These answer presentations, originating from the production experiment, were manipulated in their answer length (brief vs. extended) and their type of picture (illustrative vs. informative). After the participants had assessed the answer presentations, they received a post- test in which they had to indicate how much they had recalled from the presented answer presentations. The results showed that answer presentations with an informative picture were evaluated as more informative and more attractive than answer presentations with an illustrative picture. The results for the post-test tentatively indicated that learning from answer presentations with an informative picture leads to a better learning performance than learning from purely textual answer presentations.

Given a user question, the goal of a Question Answering (QA) system is to retrieve answers rather than full documents or even best-matching passages, as most Information Retrieval systems currently do. In this paper, we present BRUJA, a QA system for the management of multilingual collections. BRUJ rkstions (English, Spanish and French). The BRUJA architecture is not formed with three monolingual QA systems but instead uses English as Interlingua to make usual QA tasks such as question classifications and answer extractions. In addition, BRUJA uses Cross Language Information Retrieval (CLIR) techniques to retrieve relevant documents from a multilingual collection. On the one hand, we have more documents to find answers from but on the other hand, we are introducing noise into the system because of translations to the Interlingua (English) and the CLIR module. The question is whether the difficulty of managing three languages is worth it or whether a monolingual QA system delivers better results. We report on in-depth experimentation and demonstrate that our multilingual QA system gets better results than its monolingual counterpart whenever it uses good translation resources and, especially, CLIR techniques that are state-of-the-art.

Internet is one of the main sources for information which attracts million of users to find the answers for their questions. Finding the accurate answer of the question from giant databases or web pages is a very challenging task. Question answering systems answer the question from structured or unstructured databases. Question answering is different from the traditional ad-hoc document retrieval tasks in a way that in simple document search engine, the set of relevant documents are returned in response of the query, whereas, in the question answering systems the response of the query is the correct answer to what is asked. Finding the exact answer is more interesting and useful than getting a list of documents to look through and find the answer manually. Generally, the question classification is first phase in question answering systems. This phase reduces the answer space by pruning out the extra information that is irrelevant by finding out the expected answer type. This paper mainly focuses on Numeric type questions and also discusses briefly about the questions of type Entity and Location. Almost all the previous question classification algorithms evaluated their work by using the classes defined by Li and Roth [1]. The coarse grained class Numeric has fine grained class Other. In this paper, we target and present the mechanism to create new classes to replace the Other class in Numeric class. We present an automatic hierarchy creation method to add new class nodes using the knowledge resources and shallow language processing.

Chapter 8 - Projective Analysis of Unwitting Verbal Cues

This research was part of a larger study into student performance in senior chemistry with regard to question type and content.This paper examines student perceptions about question type and context and compares these perceptions to actual performance.How students perceive different types of questions and how it influences their self-belief and motivation were the focus of this study.Student responses to different styles or types of questions have been well researched over time.In this study Year 11 chemistry students were quizzed about their preferences to Multiple-Choice questions and Open Response question types and how the presence of each type was likely to influence their test performance.Student's perceptions were then correlated to their actual performance on sample chemistry tests.Students generally preferred MCQ questions and believed they were likely to perform better on these questions regardless of the topic.Test results did not always support this confidence.Suggestions for further research are also made.

We present an approach to develop a Question Answering (QA) system over cooking recipes that makes use of Cooking Ontology management. QA systems are designed to satisfy the user’s specific information need whereas ontology is the conceptualization of knowledge and it exhibits the hierarchical structure. The system is an Information retrieval (IR) based system where the various tasks to be handled like question classification, answer pattern recognition, indexing, final answer generation. Our proposed QA System use Apache Lucene for document retrieval. All cooking related documents are indexed using Apache Lucene. Stop words are removed from each cooking related question and formed the query words which are identified to retrieve the most relevant document using Lucene. Relevant paragraphs are selected from the retrieved documents based on the tf-idf of the matching query words along with n-gram overlap of the paragraph with the original question. This paper also presents a way to develop an ontology model in such a way that the queries can be processed with the help of the ontology knowledge base and generate the exact answer.

This paper proposes a new dataset for question classification process. Named QCoC (Question Classification of CoQA), this dataset is created based on Stanford's CoQA (A Conversational Question Answering Challenge) dataset. The total of QCoC datapoint is 116630 (total of combined question-answer pairs in CoQA training and evaluation dataset). Common question classification datasets are classifying question based on its paired answer's knowledge (the semantic of answer's context). For QCoC, classification is done differently that is per answer's feature (semantic and syntactic of answer's type). This paper discusses the question classification datasets, QA datasets, and justification of CoQA as selected base for QCoC. Then QCoC specification is discussed with class definition, classification method and result subsections. To the author's knowledge, such dataset is still nonexistent to date. This paper suggests that this type of dataset is useful in solving abstractive answers issue in Question-Answering (QA) system. While factual answers can be directly produced by regular QA system, abstractive answers need some additional components. Although it is a recognizable issue, lack of suitable dataset perhaps is the reason why such direction is not being pursued. With QCoC dataset made publicly available <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> , hopefully such direction is open for further exploration.

In recent years, the social web has been increasingly used for health information seeking, sharing, and subsequent health-related research. Women often use the Internet or social networking sites to seek information related to pregnancy in different stages. They may ask questions about birth control, trying to conceive, labor, or taking care of a newborn or baby. Classifying different types of questions about pregnancy information (e.g., before, during, and after pregnancy) can inform the design of social media and professional websites for pregnancy education and support. This research aims to investigate the attention mechanism built-in or added on top of the BERT model in classifying and annotating the pregnancy-related questions posted on a community Q&A site. We evaluated two BERT-based models and compared them against the traditional machine learning models for question classification. Most importantly, we investigated two attention mechanisms: the built-in self-attention mechanism of BERT and the additional attention layer on top of BERT for relevant term annotation. The classification performance showed that the BERT-based models worked better than the traditional models, and BERT with an additional attention layer can achieve higher overall precision than the basic BERT model. The results also showed that both attention mechanisms work differently on annotating relevant content, and they could serve as feature selection methods for text mining in general.

Search engine is a program that performs a search in the documents for finding out the response to the user’s query in form of keywords. It then provides a list of web pages comprising of those keywords. Search engines cannot differentiate between the variable documents and spams. Some search engine crawler retrieves only document title not the entire text in the document. The major objective of Question Answering system is to develop techniques that not only retrieve documents, but also provide exact answers to natural language questions. Many Question Answering systems developed are able to carry out the processing needed for attaining higher accuracy levels. However, there is no major progress on techniques for quickly finding exact answers. Existing Question Answering system is unable to handle variety of questions and reasoning-based question. In case of absence of data sources, QA system fails to answer the query. This paper investigates a novel technique for indexing the semantic Web for efficient Question Answering system. Proposed techniques include manual constructed question classifier based on , retrieval of documents specifically for Question Answering, semantic type answer extraction, answer extraction via manually constructed index for every category of Question.

Community question answering (CQA) sites such as Yahoo! Chiebukuro are known to be very useful resources for automatic question answering (QA) systems. However, CQA users often post questions expecting not some general truths but rather opinions of different people. We believe that a QA system should act according to these different question types. We therefore define two question types based on whether the questioner expects subjective or objective answers, and report on an automatic question classification experiment. We achieve over 80% weighted accuracy using uni-gram and bi-gram features learned by Naive Bayes with smoothing. We also discuss the inter-annotator agreement and its impact on automatic classification accuracy, as well as what kind of questions tend to be misclassified.

In recent years, there is growing interest in intelligent conversation systems. In this context, Question Classification is an essential subtask in Question Answering systems that determines the question type, therefore, also the type of the answer. However, while there is abundant research for English, little research work has been carried out for other languages. In this paper we deal with classification of questions in the Albanian language which is considered a complex Indo-European language. We employ both machine learning and deep learning approaches on a large corpus in Albanian based on the six-class TREC dataset with approximately 5000 questions. Experiments with and without stop-words show that the impact of stop-words is significant in the accuracy of the classifier. Extensive comparison of algorithms for the task of question classification in Albanian show that deep learning algorithms outperform conventional machine learning approaches. To the best of our knowledge this is the first approach in literature for classifying questions in Albanian and the results are highly comparable to English.

On the use of the Price equation

When confronted with a query, question answering systems endeavor to extract the most exact answers possible by determining the answer type that fits with the query and the key terms used in the query. However, the efficacy of such systems is limited by the fact that the terms used in a query may be in a syntactic form different to that of the same words in a document. In this paper, we present an efficient semantic query expansion methodology based on a question category concept list comprised of terms that are semantically close to terms used in a query. The semantically close terms of a term in a query may be hypernyms, synonyms, or terms in a different syntactic category. The proposed system first constructs a concept list for each question type and then builds the concept list for each question category using a learning algorithm. When a new query is given, the question is classified into the node in question category, and the query is expanded using the concept list of the classified category. In the question answering experiments on 42,654 Wall Street Journal documents of the TREC collection, the traditional system showed in 0.223 in MRR and the proposed system showed 0.50 superior to the traditional question answering system. The results of the present experiments suggest the promise of the proposed method.

The classification of questions plays a key role in the system of the question-answer system, helping in the search or construction of accurate answers and thereby improving the quality of the answers provided. The following approaches are usually used to classify questions: rule-based, machine learning, and hybrid. The Kazakh language is an agglutinative language with complex morphological and syntactic involvement of polysynthetism, and therefore it is difficult to conduct machine learning research. This article presents a study on the classification of questions using rules. The question processing module helps you assign appropriate categories to questions and identify keywords from the provided input question. A prototype program was developed based on the proposed method, and an experiment was conducted involving 200 legislative questions collected from government websites such as egov.kz, adilet.kz and zan.kz . Using these question templates, the questions were categorized into specific categories. In this article, we have proposed a compact and effective method for classifying questions. The results of the experiment show that even with a small set of question categories, we can classify them with a more satisfactory and improved result.

The present study aimed to explore the types of classroom questions which Jordanian English language teachers ask. The sample of the study consisted of 77 teachers who were randomly selected from different public and private schools in Amman- Jordan. A total of 1574 classroom questions were collected and analyzed using descriptive statistics, t test and analysis of variance. The results showed that 80% of teachers’ questions were on low thinking levels; 77% were closed-ended questions; and 86% were display questions. The results also indicated that teachers used higher thinking questions, more referential questions, and more open- ended questions at upper basic stage and secondary stage. It was recommended that EFL teachers in Jordan ask different types of questions at each grade level.