Exploring the Robustness of Task-oriented Dialogue Systems for Colloquial German Varieties
This work addresses a gap in cross-lingual dialogue systems by evaluating their performance on lower-resource colloquial varieties, which is incremental as it extends existing methods to new linguistic contexts.
The study investigated the robustness of task-oriented dialogue systems when applied to colloquial German varieties, finding that while intent recognition performance dropped by only 6% on average, slot detection suffered a significant 31% decrease in F1 score.
Mainstream cross-lingual task-oriented dialogue (ToD) systems leverage the transfer learning paradigm by training a joint model for intent recognition and slot-filling in English and applying it, zero-shot, to other languages. We address a gap in prior research, which often overlooked the transfer to lower-resource colloquial varieties due to limited test data. Inspired by prior work on English varieties, we craft and manually evaluate perturbation rules that transform German sentences into colloquial forms and use them to synthesize test sets in four ToD datasets. Our perturbation rules cover 18 distinct language phenomena, enabling us to explore the impact of each perturbation on slot and intent performance. Using these new datasets, we conduct an experimental evaluation across six different transformers. Here, we demonstrate that when applied to colloquial varieties, ToD systems maintain their intent recognition performance, losing 6% (4.62 percentage points) in accuracy on average. However, they exhibit a significant drop in slot detection, with a decrease of 31% (21 percentage points) in slot F1 score. Our findings are further supported by a transfer experiment from Standard American English to synthetic Urban African American Vernacular English.