Relation Extraction from Community Generated Question-Answer Pairs
نویسندگان
چکیده
● Even largest available knowledge bases are incomplete ● Relation extraction from unstructured data is one way to narrow the gap ● Question-Answer pairs (QnA) are attractive data source for relation extraction, they contain information users are interested in ● Existing approaches are typically based on various syntactic patterns and operate over individual sentences ● However, often an answer is hard to understand without knowing the question Intelligent Information
منابع مشابه
Advanced Community Question Answering Sites with Multimedia Answers
There are many question answer sites are available now a days. Community question answering sites are efficient when compare with the automate question answering sites. The drawback of available community question answering system is that it can only provide textual answer. In this paper, we propose a scheme that enriches the textual answer with multimedia data. Our scheme consists of four comp...
متن کاملDiscovering high quality answers in community question answering archives using a hierarchy of classifiers
Keywords: Question answering system User generated content Answer quality Question type analysis Hierarchical supervised learning a b s t r a c t In community-based question answering (CQA) services where answers are generated by human, users may expect better answers than an automatic question answering system. However, in some cases, the user generated answers provided by CQA archives are not...
متن کاملTraining IBM Watson Using Automatically Generated Question-Answer Pairs
IBM Watson is a cognitive computing system capable of question answering in natural languages. It is believed that IBM Watson can understand large corpora and answer relevant questions more effectively than any other question-answering system currently available. To unleash the full power of Watson, however, we need to train its instance with a large number of wellprepared question-answer pairs...
متن کاملFora: Leveraging the Power of Internet Communities for Question Answering
This paper introduces a system for searching question answer pairs automatically extracted from the discussions in internet communities. The system, named Fora, aggregates discussions from multiple forums and newsgroups in the same domain, automatically extracts question answer pairs from the data, and provides searches of the question answer pairs. The system also offers expert search, query s...
متن کاملAugmenting Conversational Characters with Generated Question-Answer Pairs
We take a conversational character trained on a set of linked question-answer pairs authored by hand, and augment its training data by adding sets of question-answer pairs which are generated automatically from texts on different topics. The augmented characters can answer questions about the new topics, at the cost of some performance loss on questions about the topics that the original charac...
متن کامل