Duplicate question detection (DQD) is important to increase efficiency of community and automatic question answering systems.
Past research shows that users benefit from systems that support them in their writing and exploration tasks.
In this paper, we apply BERT to DQD and advance it by unsupervised adaptation to StackExchange domains using self-supervised learning.
This paper explores domain adaptation for enabling question answering (QA) systems to answer questions posed against documents in new specialized domains.
We detail the process of extracting topical passages for queries submitted to a search engine, creating annotated sets of passages aligned to different stances on a topic, and assessing argument convincingness of passages using pairwise annotation.
Word embeddings typically represent different meanings of a word in a single conflated vector.