End-to-End Slot Alignment and Recognition for Cross-Lingual NLU

2020/04/29 by Weijia Xu, Batool Haider, Batool A Haider +4 · 8 citations
Computer Science · #Algorithm #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Context (archaeology) #Dialog box #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine translation #Natural Language Processing Techniques #Natural language #Natural language processing #Natural language understanding #Projection (relational algebra) #Rule-based machine translation #Speech and dialogue systems #Topic Modeling #Translation (biology) #World Wide Web #cs.CL #cs.LG

paper · pdf · doi:10.48550/arxiv.2004.14353

published in arXiv (Cornell University) (Cornell University) · Accepted at EMNLP 2020

openalex publication_date 2020/04/29 · arxiv created 2020/10/08 · arxiv updated 2020/10/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Bidirectional recurrent neural networks

Cited by

• Multi-Intent Spoken Language Understanding: Methods, Trends, and Challenges
• Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding
• Multilingual Text-to-SQL: Benchmarking the Limits of Language Models with Collaborative Language Agents
• WolBanking77: Wolof Banking Speech Intent Classification Dataset
• Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions
• Intent Classification on Low-Resource Languages with Query Similarity Search

Related

• Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
• Call Larisa Ivanovna: Code-Switching Fools Multilingual NLU Models
• Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs
• From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding
• Frustratingly Easy Label Projection for Cross-lingual Transfer