When the answer comes into question in question-answering: survey and open issues

2012 ◽  
Vol 19 (1) ◽  
pp. 1-32 ◽  
Author(s):  
ANA CRISTINA MENDES ◽  
LUÍSA COHEUR
Keyword(s):  
Question Answering ◽  
Information Sources ◽  
State Of The Art ◽  
Research Community ◽  
The State ◽  
Present Survey ◽  
Cooperative Answering ◽  
Open Issues

AbstractThe answer determines the success of a Question-Answering (QA) system. In redundancy-based QA systems, a common approach is to extract the candidate answers from the information sources and select the most frequent answers as the final answers. However, this strategy has some pitfalls. For instance, if a system is not able to detect equivalences between the candidate answers, their frequencies might be erroneously calculated. Moreover, the user who posed the question should also be taken into account when answering: different persons require different (correct) answers. This can involve the use of suitable vocabulary and/or information details. In these situations, the generation of a response can be a more suitable strategy, instead of the extraction and direct retrieval of the answer from the information sources. The present survey targets the state of the art in the answering task in QA under three different lines of research. First, we present several works that focus on relating candidate answers. Then, we recover the concept of cooperative answer – a correct, useful, and non-misleading answer – and we bring up attempts to address cooperative answering. Finally, we investigate the research community endeavors on response generation. We will also present our perspective on each of these three topics throughout this paper.

Current Approaches, Challenges, and Perspectives on Spatial OLAP for Agri-Environmental Analysis

2016 ◽  
Vol 7 (4) ◽  
pp. 32-49 ◽  
Author(s):  
Sandro Bimonte
Keyword(s):  
Urban Development ◽  
Environmental Analysis ◽  
Scientific Community ◽  
State Of The Art ◽  
Environmental Context ◽  
Research Community ◽  
The State ◽  
Environmental Data ◽  
Multidimensional Model ◽  
Open Issues

Spatial OLAP (SOLAP) systems are powerful GeoBusiness Intelligence tools for analysing massive volumes of geo-referenced datasets. Therefore, these technologies are receiving considerable attention in the research community and in the database industry as well. Applications of these technologies are current in several domains such as ad marketing, healthcare, and urban development, to name a few. Contrary to other application domains, in the context of agri-environmental data and analysis, SOLAP systems have been underexploited. Therefore, in this paper, the author makes an exhaustive survey of most of the published studies in the domain of the SOLAP analysis of agri-environmental data with an emphasis on the reasons why only few recent works investigate the use of SOLAP systems in the agri-environmental context. In particular, the author focuses on the complexity of the spatio-multidimensional model and its implementation. Moreover, based on surveying the state of the art in this domain, this paper identifies some general guidelines that must be considered by the scientific community to design and implement efficient SOLAP approaches to the analysis of geo-referenced agri-environmental datasets. Finally, open issues about warehousing and OLAPing agri-environmental data are also shown in the paper.

Current Approaches, Challenges, and Perspectives on Spatial OLAP for Agri-Environmental Analysis

2019 ◽  
pp. 1-21
Author(s):  
Sandro Bimonte
Keyword(s):  
Urban Development ◽  
Environmental Analysis ◽  
Scientific Community ◽  
State Of The Art ◽  
Environmental Context ◽  
Research Community ◽  
The State ◽  
Environmental Data ◽  
Multidimensional Model ◽  
Open Issues

Spatial OLAP (SOLAP) systems are powerful GeoBusiness Intelligence tools for analysing massive volumes of geo-referenced datasets. Therefore, these technologies are receiving considerable attention in the research community and in the database industry as well. Applications of these technologies are current in several domains such as ad marketing, healthcare, and urban development, to name a few. Contrary to other application domains, in the context of agri-environmental data and analysis, SOLAP systems have been underexploited. Therefore, in this paper, the author makes an exhaustive survey of most of the published studies in the domain of the SOLAP analysis of agri-environmental data with an emphasis on the reasons why only few recent works investigate the use of SOLAP systems in the agri-environmental context. In particular, the author focuses on the complexity of the spatio-multidimensional model and its implementation. Moreover, based on surveying the state of the art in this domain, this paper identifies some general guidelines that must be considered by the scientific community to design and implement efficient SOLAP approaches to the analysis of geo-referenced agri-environmental datasets. Finally, open issues about warehousing and OLAPing agri-environmental data are also shown in the paper.

Women in Brazilian CS Research Community

2012 ◽  
pp. 1824-1839
Author(s):  
Mirella M. Moro ◽  
Taisy Weber ◽  
Carla M.D.S. Freitas
Keyword(s):  
Computer Science ◽  
State Of The Art ◽  
Research Community ◽  
Current Situation ◽  
The State ◽  
Do So

Many communities have been concerned with the problem of bringing more girls to technology and science related areas. The authors believe that the first step in order to solve such a problem is to understand the current situation, like to investigate the “state-of-the-art” of the problem. Therefore, in this chapter, they present the first study to identify which areas of Computer Science have more and less feminine participation. In order to do so, they have considered the program committees of the Brazilian conferences in those areas. The authors’ study evaluates the 2008 and previous editions of such conferences. They also discuss some Brazilian initiatives to bring more girls to Computer Science as well present what else can be done.

scholarly journals Towards relation extraction from Arabic text: a review

2019 ◽  
Vol 5 (5) ◽  
pp. 212-215
Author(s):  
Abeer AlArfaj
Keyword(s):  
Language Processing ◽  
Question Answering ◽  
State Of The Art ◽  
Relation Extraction ◽  
Arabic Language ◽  
Extraction Methods ◽  
The State ◽  
Semantic Relations ◽  
Arabic Text ◽  
Taxonomic Relation

Semantic relation extraction is an important component of ontologies that can support many applications e.g. text mining, question answering, and information extraction. However, extracting semantic relations between concepts is not trivial and one of the main challenges in Natural Language Processing (NLP) Field. The Arabic language has complex morphological, grammatical, and semantic aspects since it is a highly inflectional and derivational language, which makes task even more challenging. In this paper, we present a review of the state of the art for relation extraction from texts, addressing the progress and difficulties in this field. We discuss several aspects related to this task, considering the taxonomic and non-taxonomic relation extraction methods. Majority of relation extraction approaches implement a combination of statistical and linguistic techniques to extract semantic relations from text. We also give special attention to the state of the work on relation extraction from Arabic texts, which need further progress.

Women in Brazilian CS Research Community

2010 ◽  
pp. 301-317
Author(s):  
Mirella M. Moro ◽  
Taisy Weber ◽  
Carla M.D.S. Freitas
Keyword(s):  
Computer Science ◽  
State Of The Art ◽  
Research Community ◽  
Current Situation ◽  
The State ◽  
Do So

Many communities have been concerned with the problem of bringing more girls to technology and science related areas. The authors believe that the first step in order to solve such a problem is to understand the current situation, like to investigate the “state-of-the-art” of the problem. Therefore, in this chapter, they present the first study to identify which areas of Computer Science have more and less feminine participation. In order to do so, they have considered the program committees of the Brazilian conferences in those areas. The authors’ study evaluates the 2008 and previous editions of such conferences. They also discuss some Brazilian initiatives to bring more girls to Computer Science as well present what else can be done.

scholarly journals Lattice CNNs for Matching Based Chinese Question Answering

2019 ◽  
Vol 33 ◽  
pp. 6634-6641 ◽  
Author(s):  
Yuxuan Lai ◽  
Yansong Feng ◽  
Xiaohan Yu ◽  
Zheng Wang ◽  
Kun Xu ◽  
...  
Keyword(s):  
Question Answering ◽  
State Of The Art ◽  
The State ◽  
Experimental Results ◽  
Short Text ◽  
Knowledge Based ◽  
Noisy Information ◽  
Word Lattice ◽  
Matching Models ◽  
Strong Ability

Short text matching often faces the challenges that there are great word mismatch and expression diversity between the two texts, which would be further aggravated in languages like Chinese where there is no natural space to segment words explicitly. In this paper, we propose a novel lattice based CNN model (LCNs) to utilize multi-granularity information inherent in the word lattice while maintaining strong ability to deal with the introduced noisy information for matching based question answering in Chinese. We conduct extensive experiments on both document based question answering and knowledge based question answering tasks, and experimental results show that the LCNs models can significantly outperform the state-of-the-art matching models and strong baselines by taking advantages of better ability to distill rich but discriminative information from the word lattice input.

scholarly journals An Adaptive Framework for Conversational Question Answering

2019 ◽  
Vol 33 ◽  
pp. 10041-10042
Author(s):  
Lixin Su ◽  
Jiafeng Guo ◽  
Yixing Fan ◽  
Yanyan Lan ◽  
Ruqing Zhang ◽  
...  
Keyword(s):  
Preliminary Analysis ◽  
Information Needs ◽  
Question Answering ◽  
State Of The Art ◽  
The State ◽  
Dominant Type ◽  
New Knowledge ◽  
Specific Object ◽  
Overall Performance ◽  
Adaptive Framework

In Conversational Question Answering (CoQA), humans propose a series of questions to satisfy their information needs. Based on our preliminary analysis, there are two major types of questions, namely verification questions and knowledgeseeking questions. The first one is to verify some existing facts, while the latter is to obtain new knowledge about some specific object. These two types of questions differ significantly in their answering ways. However, existing methods usually treat them uniformly, which may easily be biased by the dominant type of questions and obtain inferior overall performance. In this work, we propose an adaptive framework to handle these two types of questions in different ways based on their own characteristics. We conduct experiments on the recently released CoQA benchmark dataset, and the results demonstrate that our method outperforms the state-of-the-art baseline methods.

A Survey of Mobile Internet Data Management: Models and Searching Methods

2011 ◽  
Vol 109 ◽  
pp. 738-742 ◽  
Author(s):  
Hui Zheng ◽  
Yuan Xu
Keyword(s):  
Data Management ◽  
State Of The Art ◽  
The State ◽  
Mobile Internet ◽  
Point Of View ◽  
Application Area ◽  
Management Models ◽  
Open Issues

We survey the state-of-the-art in mobile internet data management. We focus on the models and searching methods presented in the literature. We explore the models and searching methods in mobile internet data management from two perspectives: application area and research content. We outline the entire landscape of the models and searching methods of mobile internet data management from researcher’s point of view. Some researchers have proposed the models and searching methods to achieve the data management of mobile internet. But there are many open issues which still need to be addressed.

Tracking and Fingerprinting in E-Business

2013 ◽  
pp. 134-166
Author(s):  
Károly Boda ◽  
Ádám Máté Földes ◽  
Gábor György Gulyás ◽  
Sándor Imre
Keyword(s):  
State Of The Art ◽  
Research Community ◽  
The State ◽  
Related Literature ◽  
The Will ◽  
Marketing Tool ◽  
Identification Techniques ◽  
Information Collecting ◽  
The Web

Online user tracking is a widely used marketing tool in e-business, even though it is often neglected in the related literature. In this chapter, the authors provide an exhaustive survey of tracking-related identification techniques, which are often applied against the will and preferences of the users of the Web, and therefore violate their privacy one way or another. After discussing the motivations behind the information-collecting activities targeting Web users (i.e., profiling), and the nature of the information that can be collected by various means, the authors enumerate the most important techniques of the three main groups of tracking, namely storage-based tracking, history stealing, and fingerprinting. The focus of the chapter is on the last, as this is the field where both the techniques intended to protect users and the current legislation are lagging behind the state-of-the-art technology; nevertheless, the authors also discuss conceivable defenses, and provide a taxonomy of tracking techniques, which, to the authors’ knowledge, is the first of its kind in the literature. At the end of the chapter, the authors attempt to draw the attention of the research community of this field to new tracking methods.

Sign in / Sign up

Export Citation Format

Share Document