Red Dragon AI at TextGraphs 2019 Shared Task: Language Model Assisted Explanation Generation

by   Yew Ken Chia, et al.

The TextGraphs-13 Shared Task on Explanation Regeneration asked participants to develop methods to reconstruct gold explanations for elementary science questions. Red Dragon AI's entries used the language of the questions and explanation text directly, rather than a constructing a separate graph-like representation. Our leaderboard submission placed us 3rd in the competition, but we present here three methods of increasing sophistication, each of which scored successively higher on the test set after the competition close.


page 1

page 2

page 3

page 4


Lucid Explanations Help: Using a Human-AI Image-Guessing Game to Evaluate Machine Explanation Helpfulness

While there have been many proposals on how to make AI algorithms more t...

Red Dragon AI at TextGraphs 2020 Shared Task: LIT : LSTM-Interleaved Transformer for Multi-Hop Explanation Ranking

Explainable question answering for science questions is a challenging ta...

QiaoNing at SemEval-2020 Task 4: Commonsense Validation and Explanation system based on ensemble of language model

In this paper, we present language model system submitted to SemEval-202...

WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-Hop Inference

Developing methods of automated inference that are able to provide users...

Musketeer (All for One, and One for All): A Generalist Vision-Language Model with Task Explanation Prompts

We present a sequence-to-sequence vision-language model whose parameters...

Explanation from Specification

Explainable components in XAI algorithms often come from a familiar set ...

Please sign up or login with your details

Forgot password? Click here to reset