Open-Domain Question Answering on Heterogeneous Data
نویسندگان
چکیده
Open-domain question answering is a hot research topic in recent years. QA Track held by NIST has offered a new evaluation on this topic. However, its target is aimed at plain text collection only. This paper focuses on QA for heterogeneous data, including plain text, summaries, tabular data, and video programs. Discussion of what necessary adaptation could be done to deal with such kind of data is shown. MRR scores of QA on each kind of data are: plain text, 0.62; summaries, 0.43; and tables, 0.36.
منابع مشابه
Investigating Embedded Question Reuse in Question Answering
The investigation presented in this paper is a novel method in question answering (QA) that enables a QA system to gain performance through reuse of information in the answer to one question to answer another related question. Our analysis shows that a pair of question in a general open domain QA can have embedding relation through their mentions of noun phrase expressions. We present methods f...
متن کاملAQUA: A Question Answering System for Heterogeneous Sources
This paper describes AQUA our question answering over the Web. AQUA was designed to work over heterogeneous sources. This means that AQUA is equipped to work as closed domain and in addition to open-domain question answering. As a first instance, AQUA tries to answer a question using a Knowledge base. If a query cannot be satisfied over a knowledge base/database. Then, AQUA tries to find an ans...
متن کاملScoQAS: A Semantic-based Closed and Open Domain Question Answering System
Question Answering (QA) has reappeared in research activities and in companies over the past years. We present an architecture of Semantic-based closed and open domain Question Answering System (ScoQAS ) over ontology resources (not free text) with two different prototyping: Ontology-based closed domain and an open domain under Linked Open Data (LOD) resource. Both scenarios are presented, disc...
متن کاملDo it your own (DIY) Jeopardy Question Answering System
The evolution and maturity of semantic technologies techniques and frameworks are bringing functionalities which were once considered academic or prototypical into real-life applications. Products such as IBM Watson [1] and Siri are examples of applications which are heavily leveraged on state-of-the-art semantic technologies. These systems provide a synthesis of the functionalities which are a...
متن کاملSelecting Domain-Specific Concepts for Question Generation With Lightly-Supervised Methods
In this paper we propose content selection methods for question generation (QG) which exploit domain knowledge. Traditionally, QG systems apply syntactical transformation on individual sentences to generate open domain questions. We hypothesize that a QG system informed by domain knowledge can ask more important questions. To this end, we propose two lightly-supervised methods to select salient...
متن کامل