# Learning to answer questions

Source: [Learning to answer questions](<https://www.sota2.com/research/paper/68fa610a1e209131ce9f242b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T19:51:34.486Z

Authors: Ana Cristina Mendes, Lu\\'isa Coheur, S\\'ergio Curto

Published: 2013-09-04T18:10:22.000Z

## Abstract

We present an open-domain Question-Answering system that learns to answer questions based on successful past interactions. We follow a pattern-based approach to Answer-Extraction, where (lexico-syntactic) patterns that relate a question to its answer are automatically learned and used to answer future questions. Results show that our approach contributes to the system's best performance when it is conjugated with typical Answer-Extraction strategies. Moreover, it allows the system to learn with the answered questions and to rectify wrong or unsolved past questions.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1309.1125>)

[PDF](<https://arxiv.org/pdf/1309.1125.pdf>)