Ranking suspected answers to natural language questions using predictive annotation

TL;DR

This paper introduces a novel ranking system for suspected answers to natural language questions, utilizing predictive annotation to improve passage analysis and ranking accuracy, evaluated through TREC Q&A benchmarks.

Contribution

The paper presents a new predictive annotation technique for processing and ranking answer passages in natural language question answering systems.

Findings

Effective ranking of answer passages demonstrated in TREC Q&A evaluation.

Predictive annotation improves the relevance of retrieved answers.

System outperforms baseline methods in answer ranking accuracy.

Abstract

In this paper, we describe a system to rank suspected answers to natural language questions. We process both corpus and query using a new technique, predictive annotation, which augments phrases in texts with labels anticipating their being targets of certain kinds of questions. Given a natural language question, an IR system returns a set of matching passages, which are then analyzed and ranked according to various criteria described in this paper. We provide an evaluation of the techniques based on results from the TREC Q&A evaluation in which our system participated.