DeepAI AI Chat
Log In Sign Up

Modeling Context in Answer Sentence Selection Systems on a Latency Budget

by   Rujun Han, et al.

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 latency. All experiments in this work were conducted in English.


page 1

page 2

page 3

page 4


Context-based Transformer Models for Answer Sentence Selection

An important task for the design of Question Answering systems is the se...

ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks

With the development of deep learning techniques and large scale dataset...

Knowledge Based Machine Reading Comprehension

Machine reading comprehension (MRC) requires reasoning about both the kn...

Tradeoffs in Sentence Selection Techniques for Open-Domain Question Answering

Current methods in open-domain question answering (QA) usually employ a ...

DP-KB: Data Programming with Knowledge Bases Improves Transformer Fine Tuning for Answer Sentence Selection

While transformers demonstrate impressive performance on many knowledge ...

Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems

Large transformer models can highly improve Answer Sentence Selection (A...