The task of a question answering (QA) system is to automatically answer questions asked by humans, expressed in a natural language. In recent years, platforms, where QA systems are applicable, have emerged on the web and gained in popularity. Related to the answering of complex questions, with subjective or ambiguous answers, there is a growing interest in understanding how semantic features can be utilized further to enhance the capability of the systems. In this thesis, it was investigated how sentiment information contained in questions and answers influenced the performance of a QA system built using logistic regression. In addition to the sentiment model, an additional baseline model, which did not consider sentiment, was constructed a...
Abstract: Question answering System (QAS) represents a specialized information retrieval (IR) mecha...
Accessing vast volume of information quickly and easily through the Internet has become a major chal...
This thesis explores the possibility of applying sentiment analysis to extract tonality of user revi...
Readability metrics assess the ease with which human beings read and understand written texts. With ...
With the rapid growth and maturity of Question-Answering (QA) domain, non-factoid Question-Answering...
This report presents a method for extracting answer phrases, suitable as answers to reading comprehe...
The treatment of factual data has been widely studied in different areas of Natural Language Process...
Informationssökning mot ostrukturerade datakällor som fri text är ett av de områden där användargrän...
In this paper, we report on Qaviar, an experimental automated evaluation system for question answeri...
Sentiment analysis of Swedish data is often performed using English tools and machine. This thesis c...
Classification of sentiment on customer reviews is a real-world application for many companies that ...
This report presents a method for doing automatic reading comprehension in Swedish. The method is ba...
AbstractQuestion Answering (QA) Systems is an automated approach to retrieve correct responses to th...
Idag finns det stora mängder användar-skapat data i form av texter från spelomdömen till åsikter i m...
The development of the Web 2.0 led to the birth of new textual genres such as blogs, reviews or foru...
Abstract: Question answering System (QAS) represents a specialized information retrieval (IR) mecha...
Accessing vast volume of information quickly and easily through the Internet has become a major chal...
This thesis explores the possibility of applying sentiment analysis to extract tonality of user revi...
Readability metrics assess the ease with which human beings read and understand written texts. With ...
With the rapid growth and maturity of Question-Answering (QA) domain, non-factoid Question-Answering...
This report presents a method for extracting answer phrases, suitable as answers to reading comprehe...
The treatment of factual data has been widely studied in different areas of Natural Language Process...
Informationssökning mot ostrukturerade datakällor som fri text är ett av de områden där användargrän...
In this paper, we report on Qaviar, an experimental automated evaluation system for question answeri...
Sentiment analysis of Swedish data is often performed using English tools and machine. This thesis c...
Classification of sentiment on customer reviews is a real-world application for many companies that ...
This report presents a method for doing automatic reading comprehension in Swedish. The method is ba...
AbstractQuestion Answering (QA) Systems is an automated approach to retrieve correct responses to th...
Idag finns det stora mängder användar-skapat data i form av texter från spelomdömen till åsikter i m...
The development of the Web 2.0 led to the birth of new textual genres such as blogs, reviews or foru...
Abstract: Question answering System (QAS) represents a specialized information retrieval (IR) mecha...
Accessing vast volume of information quickly and easily through the Internet has become a major chal...
This thesis explores the possibility of applying sentiment analysis to extract tonality of user revi...