# Modeling Context in Answer Sentence Selection Systems on a Latency Budget

Source: [Modeling Context in Answer Sentence Selection Systems on a Latency Budget](<https://www.sota2.com/research/paper/68fa69391e209131cea20f82>)

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

Data updated: 2025-10-25T22:56:51.523Z

Authors: Rujun Han, Luca Soldaini, Alessandro Moschitti

Published: 2021-01-28T16:24:48.000Z

## Abstract

Answer Sentence Selection (AS2) is an efficient approach for the design of open-domain Question Answering (QA) systems. In order to achieve low latency, traditional AS2 models score question-answer pairs individually, ignoring any information from the document each potential answer was extracted from. In contrast, more computationally expensive models designed for machine reading comprehension tasks typically receive one or more passages as input, which often results in better accuracy. In this work, we present an approach to efficiently incorporate contextual information in AS2 models. For each answer candidate, we first use unsupervised similarity techniques to extract relevant sentences from its source document, which we then feed into an efficient transformer architecture fine-tuned for AS2. Our best approach, which leverages a multi-way attention architecture to efficiently encode context, improves 6% to 11% over noncontextual state of the art in AS2 with minimal impact on system latency. All experiments in this work were conducted in English.

## 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/2101.12093>)

[PDF](<https://arxiv.org/pdf/2101.12093.pdf>)
