Energy-based Self-attentive Learning of Abstractive Communities for Spoken Language Understanding

04/20/2019
by   Guokan Shang, et al.
0

Abstractive Community Detection is an important Spoken Language Understanding task, whose goal is to group utterances in a conversation according to whether they can be jointly summarized by a common abstractive sentence. This paper provides a novel approach to this task. We first introduce a neural contextual utterance encoder featuring three types of self-attention mechanisms. We then evaluate it against multiple baselines within the powerful siamese and triplet energy-based meta-architectures. Moreover, we propose a general sampling scheme that enables the triplet architecture to capture subtle clustering patterns, such as overlapping and nested communities. Experiments on the AMI corpus show that our system improves on the state-of-the-art and that our triplet sampling scheme is effective. Code and data are publicly available.

READ FULL TEXT
research
12/13/2021

Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding

Recent years have seen significant advances in end-to-end (E2E) spoken l...
research
08/12/2020

End-to-End Neural Transformer Based Spoken Language Understanding

Spoken language understanding (SLU) refers to the process of inferring t...
research
09/18/2019

CASA-NLU: Context-Aware Self-Attentive Natural Language Understanding for Task-Oriented Chatbots

Natural Language Understanding (NLU) is a core component of dialog syste...
research
10/28/2019

Modeling Inter-Speaker Relationship in XLNet for Contextual Spoken Language Understanding

We propose two methods to capture relevant history information in a mult...
research
07/01/2022

Vers la compréhension automatique de la parole bout-en-bout à moindre effort

Recent advances in spoken language understanding benefited from Self-Sup...
research
10/02/2019

Hierarchical Multi-Task Natural Language Understanding for Cross-domain Conversational AI: HERMIT NLU

We present a new neural architecture for wide-coverage Natural Language ...

Please sign up or login with your details

Forgot password? Click here to reset