Predicting user intent and detecting the corresponding slots from text are two key problems in Natural Language Understanding (NLU). Since annotated datasets are only available for a handful of languages, our work focuses particularly on a zero-shot scenario where the target language is unseen during training. In the context of zero-shot learning, this task is typically approached using representations from pre-trained multilingual language models such as mBERT or by fine-tuning on data automatically translated into the target language. We propose a novel method which augments monolingual source data using multilingual code-switching via random translations, to enhance generalizability of large multilingual language models when fine-tuning them for downstream tasks. Experiments on the MultiATIS++ benchmark show that our method leads to an average improvement of +4.2% in accuracy for the intent task and +1.8% in F1 for the slot-filling task over the state-of-the-art across 8 typologically diverse languages. We also study the impact of code-switching into different families of languages on downstream performance. Furthermore, we present an application of our method for crisis informatics using a new human-annotated tweet dataset of slot filling in English and Haitian Creole, collected during the Haiti earthquake.

Ever increasing ransomware attacks and thefts of intellectual property demand cybersecurity solutions to protect critical documents. One emerging solution is to place fake text documents in the repository of critical documents for deceiving and catching cyber attackers. We can generate fake text documents by obscuring the salient information in legit text documents. However, the obscuring process can result in linguistic inconsistencies, such as broken co-references and illogical flow of ideas across the sentences, which can discern the fake document and render it unbelievable. In this paper, we propose a novel method to generate believable fake text documents by automatically improving the linguistic consistency of computer-generated fake text. Our method focuses on enhancing syntactic cohesion and semantic coherence across discourse segments. We conduct experiments with human subjects to evaluate the effect of believability improvements in distinguishing legit texts from fake texts. Results show that the probability to distinguish legit texts from believable fake texts is consistently lower than from fake texts that have not been improved in believability. This indicates the effectiveness of our method in generating believable fake text.