Exploring the importance of context and embeddings in neural NER models for task-oriented dialogue systems
This work addresses the challenge of accurate slot filling in noisy, short conversational messages for task-oriented dialogue systems, representing an incremental improvement.
The paper tackled the problem of improving Named Entity Recognition (NER) in task-oriented dialogue systems by evaluating a modified state-of-the-art neural architecture in conversational settings, achieving performance gains through context inclusion and embeddings, with experiments on combined datasets including travel and restaurant domains.
Named Entity Recognition (NER), a classic sequence labelling task, is an essential component of natural language understanding (NLU) systems in task-oriented dialog systems for slot filling. For well over a decade, different methods from lookup using gazetteers and domain ontology, classifiers over handcrafted features to end-to-end systems involving neural network architectures have been evaluated mostly in language-independent non-conversational settings. In this paper, we evaluate a modified version of the recent state of the art neural architecture in a conversational setting where messages are often short and noisy. We perform an array of experiments with different combinations of including the previous utterance in the dialogue as a source of additional features and using word and character level embeddings trained on a larger external corpus. All methods are evaluated on a combined dataset formed from two public English task-oriented conversational datasets belonging to travel and restaurant domains respectively. For additional evaluation, we also repeat some of our experiments after adding automatically translated and transliterated (from translated) versions to the English only dataset.