Systems
Just.Ask
Just.Ask is a QA system for the English language, that combines rule- with machine learning-based components and implements several state of the art strategies in question answering, within a flexible architecture, that allows further extensions.
A first version of Just.Ask can be found here. Please note that we distribute Just.Ask in the hope that it will be useful, but WITHOUT ANY WARRANTY.
Further details about Just.Ask can be found in [ 17 ]
The-Mentor
The-Mentor is a system that employs a fully automatic approach to generate multiple-choice tests.
- In a first offline step, a set of lexico-syntactic patterns are bootstrapped by using several question/answer seed pairs and leveraging the redundancy of the Web.
- Afterwards, in an online step, the patterns are used to select sentences in a text document from which answers can be extracted and the respective questions built.
- In the end, several filters are applied to discard low quality items and distractors are named entities that comply with the question category, extracted from the same text.
See more on The-Mentor here.
QA@L2F
QA@L2F was the question-answering (QA) system from L2F/INESC-ID, that participated in 2007 and 2008 in the monolingual QA task of the Cross Language Evaluation Forum (CLEF)
This system was built to answer questions formulated in Portuguese, and followed an approach that relies on three main steps:
- Corpus pre-processing: information sources are partly processed in order to extract potentially relevant information, like named entities and relations between concepts. The latter information represents possible answers to questions and is stored in a database;
- Question Interpretation: the question is analysed and transformed into a frame, which is afterwards mapped into an SQL query or used to search relevant snippets;
- Answer Extraction: each question type is mapped into a single strategy. As a result, depending on the question type, different strategies are used to find the answer. If no answer is found, the system proceeds and tries to find an answer using alternative strategies.
