General-Purpose Question-Answering with Macaw

by   Oyvind Tafjord, et al.
Allen Institute for Artificial Intelligence

Despite the successes of pretrained language models, there are still few high-quality, general-purpose QA systems that are freely available. In response, we present Macaw, a versatile, generative question-answering (QA) system that we are making available to the community. Macaw is built on UnifiedQA, itself built on T5, and exhibits strong performance, zero-shot, on a wide variety of topics, including outperforming GPT-3 by over 10 Challenge300, a suite of 300 challenge questions, despite being an order of magnitude smaller (11 billion vs. 175 billion parameters). In addition, Macaw allows different permutations ("angles") of its inputs and outputs to be used, for example Macaw can take a question and produce an answer; or take an answer and produce a question; or take an answer and question, and produce multiple-choice options. We describe the system, and illustrate a variety of question types where it produces surprisingly good answers, well outside the training setup. We also identify question classes where it still appears to struggle, offering insights into the limitations of pretrained language models. Macaw is freely available, and we hope that it proves useful to the community. Macaw is available at


Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

Video question answering (VideoQA) is a complex task that requires diver...

Cooperative Learning of Zero-Shot Machine Reading Comprehension

Pretrained language models have significantly improved the performance o...

Transforming Question Answering Datasets Into Natural Language Inference Datasets

Existing datasets for natural language inference (NLI) have propelled re...

Prompting as Probing: Using Language Models for Knowledge Base Construction

Language Models (LMs) have proven to be useful in various downstream app...

DREAM: Uncovering Mental Models behind Language Models

To what extent do language models (LMs) build "mental models" of a scene...

Ask Me Anything: A simple strategy for prompting language models

Large language models (LLMs) transfer well to new tasks out-of-the-box s...

Please sign up or login with your details

Forgot password? Click here to reset