← Search

Christian Dugast

2 accepted papers

2022

Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model

EMNLP 2022finding

In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes’ theorem.One component is a traditional ungrounded response generation model and the other component models the reconstruction of the grounding document base…

2020

Neural Language Modeling for Named Entity Recognition

COLING 2020main

Named entity recognition is a key component in various natural language processing systems, and neural architectures provide significant improvements over conventional approaches. Regardless of different word embedding and hidden layer structures of the networks, a conditional random field layer is…