Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Incorporating Joint Embeddings into Goal-Oriented Dialogues with Multi-task Learning

: Kassawat, Firas; Chaudhuri, Debanjan; Lehmann, Jens

Postprint urn:nbn:de:0011-n-5618280 (467 KByte PDF)
MD5 Fingerprint: 13ada2125158dfcb43da743c3d316a0f
The original publication is available at
Erstellt am: 15.06.2020

Hitzler, P.:
The semantic web. 16th international conference, ESWC 2019. Proceedings : Portorož, Slovenia, June 2-6, 2019
Cham: Springer Nature, 2019 (Lecture Notes in Computer Science 11503)
ISBN: 978-3-030-21347-3 (Print)
ISBN: 978-3-030-21348-0 (Online)
Extended Semantic Web Conference (ESWC) <16, 2019, Portoroz/Slovenia>
European Commission EC
H2020; 642795; WDAqua
Answering Questions using Web Data
European Commission EC
H2020; 812997; Cleopatra
Cross-lingual Event-centric Open Analytics Research Academy
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IAIS ()
dialogue system; knowledge graph; joint embeddings; neural network

Attention-based encoder-decoder neural network models have recently shown promising results in goal-oriented dialogue systems. However, these models struggle to reason over and incorporate state-full knowledge while preserving their end-to-end text generation functionality. Since such models can greatly benefit from user intent and knowledge graph integration, in this paper we propose an RNN-based end-to-end encoder-decoder architecture which is trained with joint embeddings of the knowledge graph and the corpus as input. The model provides an additional integration of user intent along with text generation, trained with multi-task learning paradigm along with an additional regularization technique to penalize generating the wrong entity as output. The model further incorporates a Knowledge Graph entity lookup during inference to guarantee the generated output is state-full based on the local knowledge graph provided. We finally evaluated the model using the BLEU score, empirical evaluation depicts that our proposed architecture can aid in the betterment of task-oriented dialogue systems performance.