DEXTER: Deep Encoding of External Knowledge for Named Entity Recognition in Virtual Assistants
This work addresses NER challenges in voice assistants, but it is incremental as it builds on existing methods with specific enhancements.
The paper tackles the problem of noisy input and dynamic entity labels in named entity recognition (NER) for voice assistants by incorporating external knowledge, resulting in a 6% reduction in NER error rate and up to 5% improvement in semantic parsing error rate.
Named entity recognition (NER) is usually developed and tested on text from well-written sources. However, in intelligent voice assistants, where NER is an important component, input to NER may be noisy because of user or speech recognition error. In applications, entity labels may change frequently, and non-textual properties like topicality or popularity may be needed to choose among alternatives. We describe a NER system intended to address these problems. We test and train this system on a proprietary user-derived dataset. We compare with a baseline text-only NER system; the baseline enhanced with external gazetteers; and the baseline enhanced with the search and indirect labelling techniques we describe below. The final configuration gives around 6% reduction in NER error rate. We also show that this technique improves related tasks, such as semantic parsing, with an improvement of up to 5% in error rate.