Abstract
Large datasets are essential for many NLP tasks. Current publicly available open-domain dialogue datasets offer a trade-off between size and quality (e.g. DailyDialog vs. Opensubtitles). We aim to close this gap by building a high-quality dataset consisting of 14.8M utterances in English. We extract and process dialogues from publicly available online books. We present a detailed description of our pipeline and heuristics and an error analysis of extracted dialogues. Better response quality can be achieved in zero-shot and finetuning settings by training on our data than on the larger but much noisier Opensubtitles dataset. Researchers can easily build their versions of the dataset by adjusting various trade-off parameters. The code can be extended to further languages with limited effort (this https URL).
Abstract (translated)
URL
https://arxiv.org/abs/2004.12752
