CLApr 22, 2018
Reduce, Reuse, Recycle: New uses for old QA resources
arXiv:1804.08125v21 citations
Originality Synthesis-oriented
AI Analysis
This work addresses relation extraction for NLP researchers, but it is incremental as it applies existing methods to a new task.
The paper tackled the problem of relation extraction by repurposing existing QA resources, finding that training on SQuAD data improved zero-shot performance and robustness compared to task-specific training.
We investigate applying repurposed generic QA data and models to a recently proposed relation extraction task. We find that training on SQuAD produces better zero-shot performance and more robust generalisation compared to the task specific training set. We also show that standard QA architectures (e.g. FastQA or BiDAF) can be applied to the slot filling queries without the need for model modification.