El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 1009–1021 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 1009 El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing Arash Einolghozati Abhinav Arora Lorena Sainz-Maza Lecanda Anuj Kumar Sonal Gupta Facebook {arashe,abhinavarora,lorenasml,anujk,sonalgupta}@fb.com Abstract Being able to parse code-switched (CS) utterances, such as Spanish+English or Hindi+English, is essential to democratize task-oriented semantic parsing systems for certain locales. In this work, we focus on Spanglish (Spanish+English) and release a dataset, CSTOP, containing 5800 CS utter- ances alongside their semantic parses. We examine the CS generalizability of various Cross-lingual (XL) models and exhibit the advantage of pre-trained XL language models when data for only one language is present. As such, we focus on improving the pre-trained models for the case when only English corpus alongside either zero or a few CS training instances are available. We propose two data augmentation methods for the zero-shot and the few-shot settings: fine-tune using translate-and-align and augment using a gen- eration model followed by match-and-filter. Combining the few-shot setting with the above improvements decreases the initial 30-point accuracy gap between the zero-shot and the full-data settings by two thirds. 1 Introduction Code-switching (CS) is the alternation of languages within an utterance or a conversation (Poplack, 2004). It occurs under certain linguistic constraints but can vary from one locale to another (Joshi, 1982). We envision two usages of CS for virtual as- sistants. First, CS is very common in locales where there is a heavy influence of a foreign language (usually English) in the native “substrate” language (e.g., Hindi or Latin-American Spanish). Sec- ond, for other native languages, the prevalence of English-related tech words (e.g., Internet, screen) or media vocabulary (e.g., movie names) is very common. While in the second case, a model using contextual understanding should be able to parse the utterance, the first form of CS, which is our focus in this paper, needs Cross-Lingual(XL) capa- bilities in order to infer the meaning. There are various challenges for CS seman- tic parsing. First, collecting CS data is hard be- cause it needs bilingual annotators. This gets even worse considering that the number of CS pairs grows quadratically. Moreover, CS is very dy- namic and changes significantly by occasion and in time (Poplack, 2004). As such, we need extensible solutions that need little or no CS data while having the more commonly-accessible English data avail- able. In this paper, we first focus on the zero-shot setup for which we only use EN data for the same task domains (we call this in-domain EN data). We show that by translating the utterances to ES and aligning the slot values, we can achieve high ac- curacy on the CS data. Moreover, we show that having a limited number of CS data alongside aug- mentation with synthetically generated data can significantly improve the performance. Our contributions are as follows: 1) We re- lease a code-switched task-oriented dialog data set, CSTOP1, containing …

Content truncated to 500 words