Document Type

Conference Proceeding

Publication Title

International Conference Recent Advances in Natural Language Processing, RANLP


Detecting the user's intent and finding the corresponding slots among the utterance's words are important tasks in natural language understanding. Their interconnected nature makes their joint modeling a standard part of training such models. Moreover, data scarceness and specialized vocabularies pose additional challenges. Recently, the advances in pre-trained language models, namely contextualized models such as ELMo and BERT have revolutionized the field by tapping the potential of training very large models with just a few steps of fine-tuning on a task-specific dataset. Here, we leverage such models, and we design a novel architecture on top of them. Moreover, we propose an intent pooling attention mechanism, and we reinforce the slot filling task by fusing intent distributions, word features, and token representations. The experimental results on standard datasets show that our model outperforms both the current non-BERT state of the art as well as stronger BERT-based baselines.

First Page


Last Page




Publication Date



Attention mechanisms, Fine tuning, Intent detection, Joint models, Language model, Large models, Natural language understanding, Novel architecture, State of the art


Archived thanks to ACLAnthology

License: CC BY-4.0 DEED

Uploaded: 15 February 2024