Answer Extraction Research Articles

Answer Extraction Model Based on Named Entity Recognition

The answer extraction model has a direct impact on the performance of the Automatic Question Answering System (QA System). In this paper, an answer extraction model based on named entity recognition was presented. It mainly answers specific questions whose answers are related with the named entity. Firstly, it classified the questions according to answer types. And then it identified named entities with suitable types in the fragmented information. Finally, it got the final answer based on scores. The experiments in the paper proved that the model could accurately answer the questions provided by Text REtrieval Conference (TREC). Thus, the proposed model is easy to implement and its performance is good for specific questions.

Arabic Question Answering: Systems, Resources, Tools, and Future Trends

Arabic is the 6th most wide-spread natural language in the world with more than 350 million native speakers. Arabic question answering systems are gaining great importance due to the increasing amounts of Arabic content on the Internet and the increasing demand for information that regular information retrieval techniques cannot satisfy. In spite of the importance of Arabic question answering, there is no review that covers Arabic question answering systems, tools, resources, and test-sets so far, which was the motivation for this work. In this survey, different Arabic question answering systems are demonstrated and analyzed and the main question answering tasks like question analysis, passage retrieval, and answer extraction are explored. The main difficulties of modern standard Arabic and how these difficulties are tamed and classified are also explained. Arabic question answering evaluation metrics, test-sets, and language resources are reviewed, and future trends are also highlighted to guide new research in this area. This survey provides guidance for new research in Arabic question answering to get up-to-date knowledge about the state-of-the-art approaches in this area. It also demonstrates the tools created and used by researchers to build an Arabic question answering system.

Architecture of an Ontology-Based DomainSpecific Natural Language Question Answering System

Question answering (QA) system aims at retrieving precise information from a large collection of documents against a query. This paper describes the architecture of a Natural Language Question Answering (NLQA) system for a specific domain based on the ontological information, a step towards semantic web question answering. The proposed architecture defines four basic modules suitable for enhancing current QA capabilities with the ability of processing complex questions. The first module was the question processing, which analyses and classifies the question and also reformulates the user query. The second module allows the process of retrieving the relevant documents. The next module processes the retrieved documents, and the last module performs the extraction and generation of a response. Natural language processing techniques are used for processing the question and documents and also for answer extraction. Ontology and domain knowledge are used for reformulating queries and identifying the relations. The aim of the system is to generate short and specific answer to the question that is asked in the natural language in a specific domain. We have achieved 94 % accuracy of natural language question answering in our implementation.

Architecture of an Ontology-Based Domain-Specific Natural Language Question Answering System

Question answering (QA) system aims at retrieving precise information from a large collection of documents against a query. This paper describes the architecture of a Natural Language Question Answering (NLQA) system for a specific domain based on the ontological information, a step towards semantic web question answering. The proposed architecture defines four basic modules suitable for enhancing current QA capabilities with the ability of processing complex questions. The first module was the question processing, which analyses and classifies the question and also reformulates the user query. The second module allows the process of retrieving the relevant documents. The next module processes the retrieved documents, and the last module performs the extraction and generation of a response. Natural language processing techniques are used for processing the question and documents and also for answer extraction. Ontology and domain knowledge are used for reformulating queries and identifying the relations. The aim of the system is to generate short and specific answer to the question that is asked in the natural language in a specific domain. We have achieved 94 % accuracy of natural language question answering in our implementation.

A Rule Based Answer Extraction System with Stemming & Anaphora Resolution

Natural Language Processing (NLP) is an area of computer Science and Sub area of Artificial Intelligence (AI).We are developing a rule-based system that can read a large collection of text (say for e.g. story) and find the sentence in the text that best answers the given question. The system uses set of handcrafted rules augmented with some NLP techniques like stemming, named entity extraction etc. that look for Lexical and semantic clues in the question and the text (i.e. story). Each rule awards a certain number of points to each sentence. After all of the rules have been applied, the sentence that obtains the highest score is returned as the answer.

Interactive Document Expansion for Answer Extraction of Question Answering System

In this paper, we propose a method to navigate getting a correct answer for Question Answering (QA) system using user interaction. QA is a technology which extracts appropriate answer strings for a given question sentence from huge documents such as Web, newspaper articles etc. If a given question is ambiguous, answers will be various ones according to its possible understandings and retrieved documents with query words of the question sentence will consists of various types of information. In order to focus on intended topic, it is necessary to provide more information to narrow down search area for a question. In our approach, a QA system selects a clue word to decide an appropriate topic from topics in retrieved documents and interacts with a user whether this clue word is appropriate one or not. Then, search space will be reduced using this clue word. However, such narrowing down reduces the number of answer candidates because the number of target documents will be decreased. We will re-retrieve documents using this clue words and expand search space to increase possibility of getting correct answer candidates.

A Survey of Text Question Answering Techniques

Question Answering (QA) is a specific type of information retrieval. Given a set of documents, a Question Answering system attempts to find out the correct answer to the question pose in natural language. Question answering is multidisciplinary. It involves information technology, artificial intelligence, natural language processing, knowledge and database management and cognitive science. From the technological perspective, question answering uses natural or statistical language processing, information retrieval, and knowledge representation and reasoning as potential building blocks. It involves text classification, information extraction and summarization technologies. In general, question answering system (QAS) has three components such as question classification, information retrieval, and answer extraction. These components play a essential role in QAS. Question classification play primary role in QA system to categorize the question based upon on the type of its entity. Information retrieval method is get of identify success by extracting out applicable answer post by their intelligent question answering system. Finally, answer extraction module is rising topics in the QAS where these systems are often requiring ranking and validating a candidate’s answer. Most of the Question Answering systems consists of three main modules: question processing, document processing and answer processing. Question processing module plays an important part in QA systems. If this module doesn't work correctly, it will make problems for other sections. Moreover answer processing module is an emerging topic in Question Answering, in which these systems are often required to rank and validate candidate answers. These techniques aiming at discovering the short and precise answers are often based on the semantic classification. QA systems give the ability to answer questions posed in natural language by extracting, from a repository of documents, fragments of documents that contain material relevant to the answer.

Sibyl, a factoid question-answering system for spoken documents

In this article, we present a factoid question-answering system, Sibyl, specifically tailored for question answering (QA) on spoken-word documents. This work explores, for the first time, which techniques can be robustly adapted from the usual QA on written documents to the more difficult spoken document scenario. More specifically, we study new information retrieval (IR) techniques designed or speech, and utilize several levels of linguistic information for the speech-based QA task. These include named-entity detection with phonetic information, syntactic parsing applied to speech transcripts, and the use of coreference resolution. Sibyl is largely based on supervised machine-learning techniques, with special focus on the answer extraction step, and makes little use of handcrafted knowledge. Consequently, it should be easily adaptable to other domains and languages. Sibyl and all its modules are extensively evaluated on the European Parliament Plenary Sessions English corpus, comparing manual with automatic transcripts obtained by three different automatic speech recognition (ASR) systems that exhibit significantly different word error rates. This data belongs to the CLEF 2009 track for QA on speech transcripts. The main results confirm that syntactic information is very useful for learning to rank question candidates, improving results on both manual and automatic transcripts, unless the ASR quality is very low. At the same time, our experiments on coreference resolution reveal that the state-of-the-art technology is not mature enough to be effectively exploited for QA with spoken documents. Overall, the performance of Sibyl is comparable or better than the state-of-the-art on this corpus, confirming the validity of our approach.

Reuse of Chinese Domain Ontology for the restricted domain Question Answering System

Expressing knowledge by ontology is favorable for reuse and reasoning of knowledge. The structure of domain ontology for question answering system (QA) was formally defined, and the relations between ontology elements and semantic analysis of question and answer extraction were illustrated. The method of reusing Chinese ontology was proposed in the same domain, and the method can construct new initial ontology after extracting and classifying new instances based on the existing ontology using support vector machine (SVM) and reuse the other elements of the existing ontology. By the experiment of ontology reuse in certain medical domain, the average F-value of extraction and classification of instances reached 82.8%, and it verified validity of the method. The proposed method has significance for fast constructing Chinese ontology for QA in same domain.

Leveraging Wikipedia Characteristics for Search and Candidate Generation in Question Answering

Most existing Question Answering (QA) systems adopt a type-and-generate approach to candidate generation that relies on a pre-defined domain ontology. This paper describes a type independent search and candidate generation paradigm for QA that leverages Wikipedia characteristics. This approach is particularly useful for adapting QA systems to domains where reliable answer type identification and type-based answer extraction are not available. We present a three-pronged search approach motivated by relations an answer-justifying title-oriented document may have with the question/answer pair. We further show how Wikipedia metadata such as anchor texts and redirects can be utilized to effectively extract candidate answers from search results without a type ontology. Our experimental results show that our strategies obtained high binary recall in both search and candidate generation on TREC questions, a domain that has mature answer type extraction technology, as well as on Jeopardy! questions, a domain without such technology. Our high-recall search and candidate generation approach has also led to high overall QA performance in Watson, our end-to-end system.

Machine learning for query formulation in question answering

AbstractResearch on question answering dates back to the 1960s but has more recently been revisited as part of TREC's evaluation campaigns, where question answering is addressed as a subarea of information retrieval that focuses on specific answers to a user's information need. Whereas document retrieval systems aim to return the documents that are most relevant to a user's query, question answering systems aim to return actual answers to a users question. Despite this difference, question answering systems rely on information retrieval components to identify documents that contain an answer to a user's question. The computationally more expensive answer extraction methods are then applied only to this subset of documents that are likely to contain an answer. As information retrieval methods are used to filter the documents in the collection, the performance of this component is critical as documents that are not retrieved are not analyzed by the answer extraction component. The formulation of queries that are used for retrieving those documents has a strong impact on the effectiveness of the retrieval component. In this paper, we focus on predicting the importance of terms from the original question. We use model tree machine learning techniques in order to assign weights to query terms according to their usefulness for identifying documents that contain an answer. Term weights are learned by inspecting a large number of query formulation variations and their respective accuracy in identifying documents containing an answer. Several linguistic features are used for building the models, including part-of-speech tags, degree of connectivity in the dependency parse tree of the question, and ontological information. All of these features are extracted automatically by using several natural language processing tools. Incorporating the learned weights into a state-of-the-art retrieval system results in statistically significant improvements in identifying answer-bearing documents.

Enhanced semantic expansion for question classification

Most question and answering systems are based on three research themes: question classification and analysis, document retrieval and answer extraction. The performance in every stage affects the final result. To respond correctly to a question given a large collection of textual data is not an easy task. There is a need to perceive and recognise the question at a level that permits to detect some constraints that the question imposes on possible answers. The classification of questions appears as an important task because it deduces the type of expected answers. The purpose is to provide additional information to reduce the gap between answer and question. A method to improve the performance of question classification focusing on linguistic analysis and statistical approaches is presented. This work also proposes two methods of questions expansion. Various questions representation, term weighting and diverse machine learning algorithms are studied. Experiments conducted on actual data are presented. Of interest is the improvement in the precision on the classification of questions.

A Semantic Approach to Extract the Final Answer in SBUQA Question Answering System

In this paper we introduce the semantic approach of the answer extraction component of a question answering system called SBUQA. The answer extraction component gets the retrieved documents from a search engine according to a query (here NL question) as input. Then it represents both the question and candidate sentences using Lexical Functional Grammar (LFG), a meaning based grammar that analyses sentences in a deeper level than syntactic parsing. Then the meaning of the question and the candidate sentence will be expanded according to lexico-conceptual relations in a lexical ontology such as WordNet. The results of these expansions- stored in f-structure patterns- will be compared together exploiting our proposed extended unification algorithm. The answers will be ranked according to the type of found matches between the expanded meaning of the question and the expanded meaning of the candidate sentence (which contains the answer). There are four introduced types of matches from exact to different levels of approximate matching. After selecting the best (most matched) sentences, the final answer phrase will be extracted according to some predefined templates and ranked in descending order of relevance.

A structural support vector method for extracting contexts and answers of questions from online forums

This article addresses the issue of extracting contexts and answers of questions from posts of online discussion forums. In previous work, general-purpose graphical models have been employed without any customization to this specific extraction problem. Instead, in this article, we propose a unified approach to context and answer extraction by customizing the structural support vector machine method. The customization enables our proposal to explore various relations among sentences of posts and complex structures of threads. We design new inference algorithms to find or approximate the most violated constraint by utilizing the specific structure of forum threads, which enables us to efficiently find the global optimum of the customized optimizing problem. We also optimize practical performance measures by varying loss functions. Experimental results show that our methods are both promising and flexible.

Combining semantic information in question answering systems

This paper presents two proposals based on semantic information, semantic roles and WordNet, for the answer extraction module of a general open-domain question answering (QA) system. The main objective of this research is to determine how the system performance is influenced by using this kind of information, and compare it with that of current QA systems based on named entities (NEs). NE-based QA systems achieve good results with NE-based questions. However, with common noun (CN) based questions, like “ Where is the stomach? In the abdomen”, they fail, and this is the main reason for our study. In this paper our new proposals for answering different types of questions are evaluated and compared with an NE-based approach for both NE-based and CN-based questions. From the results obtained it may be concluded that, with the aid of our proposals, the QA system performs much better with CN-based questions when semantic information is used (semantic information F β = 1 = 74.73 % vs. NE F β = 1 = 12.19 % ). Moreover, the more semantic information the system uses, the better the precision and correctness of the answer it achieves.

Answer extraction application based on dependency semantic analysis

An efficient answer extraction system named Dependency Inspection based AE System (DIAES) was proposed to improve the accuracy of locating candidate answers. The system used the Minimal Logical Form (MLF) to compare semantic similarity between query and candidate answers so as to remove irrelevant retrieval results. Experimental results prove that the proposed system has lower complexity and higher precision than the traditional ones.

A novel approach for question answering and automatic diagnosis based on pervasive agent ontology in medicine

With question answering system in medicine, users could use sentences in daily life to raise questions. The question answering system will analyze and comprehend these questions and return answers to users directly. Aiming at the problems in automatic diagnosis for medicine, such as low precision of question answering, imperfect expression of domain knowledge, low reuse rate, and lack of reasonable theory reference models, we put forward the information integration method of semantic Web based on pervasive agent ontology (SWPAO method) in medicine, which will integrate, analyze, and process enormous Web information and extract answers on the basis of semantics. A novel approach for automatic diagnosis in medicine based on ontology and fuzzy rough set is brought forward. The data mining algorithm for automatic diagnosis rules in medicine is brought forward: (1) computing the measurement matrix of effect; (2) extracting rules; (3) computing the importance of rules; (4) shearing the rules by genetic algorithm. In this paper, rough sets method is used to take potential diagnosis rule from the decision-making table in medicine. These rules can offer effective automatic diagnosis service. With the SWPAO method as the clue, we mainly study the method of concept extraction based on uniform semantic term mining, pervasive agent ontology construction method on account of multipoints and the answer extraction in view of semantic inference. Meanwhile, we present the structural model of the question answering system applying ontology, which adopts OWL language to describe domain knowledge base from where it infers and extracts answers by Jena inference engine, thus the precision of question answering in QA system could be improved. In the system testing, the precision has reached 86% and the recalling rate is 93%. The experiment indicates that this method is feasible, and it has the significance of reference and value of further study for the question answering systems in medicine. © 2010 Wiley Periodicals, Inc.

A novel approach for agent ontology and its application in question answering

The information integration method of semantic web based on agent ontology (SWAO method) was put forward aiming at the problems in current network environment, which integrates, analyzes and processes enormous web information and extracts answers on the basis of semantics. With SWAO method as the clue, the following technologies were studied: the method of concept extraction based on semantic term mining, agent ontology construction method on account of multi-points and the answer extraction in view of semantic inference. Meanwhile, the structural model of the question answering system applying ontology was presented, which adopts OWL language to describe domain knowledge from where QA system infers and extracts answers by Jena inference engine. In the system testing, the precision rate reaches 86%, and the recalling rate is 93%. The experimental results prove that it is feasible to use the method to develop a question answering system, which is valuable for further study in more depth.

An Answer Extraction Algorithm Based on Syntax Structure Feature Parsing and Classification

Due to the feature and difficulty of Chinese natural language processing and the lack of related resources, some foreign mature techniques can not be applied in Chinese Question Answering (QA) system. For the Chinese factoid QA system, a new answer extraction method based on syntax structure feature parsing and classification is presented in this paper. With the method, the answer extraction is regarded as candidate answer classification problem,i.e. candidate answers are classified into correct and incorrect answer. According to the part-of-speech information of candidate answers corresponding to question types,the candidate answers and their features (both simple and syntactic) in sentences from snippets are firstly extracted. Then these features are used to train the classifier. Finally, the trained classifier is used to distinguish whether the candidate answer is correct or not. For Chinese factoid questions, comparing to currently typical pattern matching based answer extraction algorithm, the new method improves precision by 6.2% and MRR by 9.7%.

The potential for automated question answering in the context of genomic medicine: an assessment of existing resources and properties of answers

Knowledge gained in studies of genetic disorders is reported in a growing body of biomedical literature containing reports of genetic variation in individuals that map to medical conditions and/or response to therapy. These scientific discoveries need to be translated into practical applications to optimize patient care. Translating research into practice can be facilitated by supplying clinicians with research evidence. We assessed the role of existing tools in extracting answers to translational research questions in the area of genomic medicine. We: evaluate the coverage of translational research terms in the Unified Medical Language Systems (UMLS) Metathesaurus; determine where answers are most often found in full-text articles; and determine common answer patterns. Findings suggest that we will be able to leverage the UMLS in development of natural language processing algorithms for automated extraction of answers to translational research questions from biomedical text in the area of genomic medicine.