Learning to Rank Context for Named Entity Recognition Using a Synthetic Dataset

arXiv:2310.10118v3 Announce Type: replace
Abstract: While recent pre-trained transformer-based models can perform named entity recognition (NER) with great accuracy, their limited range remains an issue when applied to long documents such as whole novels. To alleviate this issue, a solution is to retrieve relevant context at the document level. Unfortunately, the lack of supervision for such a task means one has to settle for unsupervised approaches. Instead, we propose to generate a synthetic context retrieval training dataset using Alpaca, an …

abstract accuracy arxiv context cs.cl dataset document documents issue ner recognition solution synthetic transformer transformer-based models type