On Evaluating Multilingual Compositional Generalization with Translated Datasets
–arXiv.org Artificial Intelligence
Compositional generalization allows efficient learning and human-like inductive biases. Since most research investigating compositional generalization in NLP is done on English, important questions remain underexplored. Do the necessary compositional generalization abilities differ across languages? Can models compositionally generalize cross-lingually? As a first step to answering these questions, recent work used neural machine translation to translate datasets for evaluating compositional generalization in semantic parsing. However, we show that this entails critical semantic distortion. To address this limitation, we craft a faithful rule-based translation of the MCWQ dataset from English to Chinese and Japanese. Even with the resulting robust benchmark, which we call MCWQ-R, we show that the distribution of compositions still suffers due to linguistic divergences, and that multilingual models still struggle with cross-lingual compositional generalization. Our dataset and methodology will be useful resources for the study of cross-lingual compositional generalization in other tasks.
arXiv.org Artificial Intelligence
Jun-20-2023
- Country:
- North America
- Dominican Republic (0.04)
- United States
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Michigan > Washtenaw County
- Ann Arbor (0.04)
- California > Santa Cruz County
- Santa Cruz (0.04)
- Minnesota > Hennepin County
- Europe
- Sweden > Östergötland County
- Linköping (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Iceland > Capital Region
- Reykjavik (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Croatia > Dubrovnik-Neretva County
- Dubrovnik (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Sweden > Östergötland County
- Asia
- Middle East
- UAE > Abu Dhabi Emirate
- Abu Dhabi (0.04)
- Republic of Türkiye > Batman Province
- Batman (0.04)
- Qatar > Ad-Dawhah
- Doha (0.04)
- UAE > Abu Dhabi Emirate
- Japan > Honshū
- Kansai > Osaka Prefecture > Osaka (0.04)
- China
- Hong Kong (0.04)
- Guangxi Province > Nanning (0.04)
- Beijing > Beijing (0.04)
- Middle East
- North America
- Genre:
- Research Report (0.64)
- Technology: