End-to-End Slot Alignment and Recognition for Cross-Lingual NLU
This work addresses the challenge of efficiently expanding NLU systems to new languages for multilingual dialog applications, representing an incremental improvement over existing projection-based methods.
The paper tackles the problem of cross-lingual natural language understanding (NLU) for goal-oriented dialog systems, where existing methods rely on error-prone machine translation and slot label projection. The proposed end-to-end model outperforms a simple label projection method on most languages and achieves competitive performance to a state-of-the-art projection method with half the training time, as evaluated on a new multilingual corpus covering nine languages.
Natural language understanding (NLU) in the context of goal-oriented dialog systems typically includes intent classification and slot labeling tasks. Existing methods to expand an NLU system to new languages use machine translation with slot label projection from source to the translated utterances, and thus are sensitive to projection errors. In this work, we propose a novel end-to-end model that learns to align and predict target slot labels jointly for cross-lingual transfer. We introduce MultiATIS++, a new multilingual NLU corpus that extends the Multilingual ATIS corpus to nine languages across four language families, and evaluate our method using the corpus. Results show that our method outperforms a simple label projection method using fast-align on most languages, and achieves competitive performance to the more complex, state-of-the-art projection method with only half of the training time. We release our MultiATIS++ corpus to the community to continue future research on cross-lingual NLU.