TWEAC: Transformer with Extendable QA Agent Classifiers

by   Gregor Geigle, et al.

Question answering systems should help users to access knowledge on a broad range of topics and to answer a wide array of different questions. Most systems fall short of this expectation as they are only specialized in one particular setting, e.g., answering factual questions with Wikipedia data. To overcome this limitation, we propose composing multiple QA agents within a meta-QA system. We argue that there exist a wide range of specialized QA agents in literature. Thus, we address the central research question of how to effectively and efficiently identify suitable QA agents for any given question. We study both supervised and unsupervised approaches to address this challenge, showing that TWEAC - Transformer with Extendable Agent Classifiers - achieves the best performance overall with 94 on the scalability of TWEAC, demonstrating that it scales robustly to over 100 QA agents with each providing just 1000 examples of questions they can answer.


page 1

page 2

page 3

page 4


What Question Answering can Learn from Trivia Nerds

In addition to the traditional task of getting machines to answer questi...

Question Answering as Global Reasoning over Semantic Abstractions

We propose a novel method for exploiting the semantic structure of text ...

Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering

In this paper we propose a novel approach towards improving the efficien...

QA2Explanation: Generating and Evaluating Explanations for Question Answering Systems over Knowledge Graph

In the era of Big Knowledge Graphs, Question Answering (QA) systems have...

Leveraging Term Banks for Answering Complex Questions: A Case for Sparse Vectors

While open-domain question answering (QA) systems have proven effective ...

DEEPAGÉ: Answering Questions in Portuguese about the Brazilian Environment

The challenge of climate change and biome conservation is one of the mos...

Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies

A key limitation in current datasets for multi-hop reasoning is that the...

Code Repositories