Christian Dugast


2022

pdf bib
Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model
Nico Daheim | David Thulke | Christian Dugast | Hermann Ney
Findings of the Association for Computational Linguistics: EMNLP 2022

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 based on the dialog context and generated response.We propose different approximate decoding schemes and evaluate our approach on multiple open-domain and task-oriented document-grounded dialog datasets.Our experiments show that the model is more factual in terms of automatic factuality metrics than the baseline model.Furthermore, we outline how introducing scaling factors between the components allows for controlling the tradeoff between factuality and fluency in the model output.Finally, we compare our approach to a recently proposed method to control factuality in grounded dialog, CTRL (Rashkin et al., 2021), and show that both approaches can be combined to achieve additional improvements.

2021

pdf bib
Investigation on Data Adaptation Techniques for Neural Named Entity Recognition
Evgeniia Tokarchuk | David Thulke | Weiyue Wang | Christian Dugast | Hermann Ney
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop

Data processing is an important step in various natural language processing tasks. As the commonly used datasets in named entity recognition contain only a limited number of samples, it is important to obtain additional labeled data in an efficient and reliable manner. A common practice is to utilize large monolingual unlabeled corpora. Another popular technique is to create synthetic data from the original labeled data (data augmentation). In this work, we investigate the impact of these two methods on the performance of three different named entity recognition tasks.

pdf bib
Cascaded Span Extraction and Response Generation for Document-Grounded Dialog
Nico Daheim | David Thulke | Christian Dugast | Hermann Ney
Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021)

This paper summarizes our entries to both subtasks of the first DialDoc shared task which focuses on the agent response prediction task in goal-oriented document-grounded dialogs. The task is split into two subtasks: predicting a span in a document that grounds an agent turn and generating an agent response based on a dialog and grounding document. In the first subtask, we restrict the set of valid spans to the ones defined in the dataset, use a biaffine classifier to model spans, and finally use an ensemble of different models. For the second sub-task, we use a cascaded model which grounds the response prediction on the predicted span instead of the full document. With these approaches, we obtain significant improvements in both subtasks compared to the baseline.

2020

pdf bib
Neural Language Modeling for Named Entity Recognition
Zhihong Lei | Weiyue Wang | Christian Dugast | Hermann Ney
Proceedings of the 28th International Conference on Computational Linguistics

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 commonly used for the output. This work proposes to use a neural language model as an alternative to the conditional random field layer, which is more flexible for the size of the corpus. Experimental results show that the proposed system has a significant advantage in terms of training speed, with a marginal performance degradation.