We address efficient calculation of influence functions for tracking predictions back to the
training data. We propose and analyze a new approach to speeding up the inverse Hessian …

Large, multilingual language models exhibit surprisingly good zero-or few-shot machine
translation capabilities, despite having never seen the intentionally-included translation …

Large language models'(LLMs) abilities are drawn from their pretraining data, and model
development begins with data curation. However, decisions around what data is retained or …

The Routledge Handbook of Language Contact provides an overview of the state of the art
of current research in contact linguistics. Presenting contact linguistics as an established …

Multilingual question answering (MLQA) is a critical part of an accessible natural language
interface. However, current solutions demonstrate performance far below that of …

Abstract Machine translation of user-generated code-mixed inputs to English is of crucial
importance in applications like web search and targeted advertising. We address the …

Language identification for code-switching (CS), the phenomenon of alternating between
two or more languages in conversations, has traditionally been approached under the …

Multilingual speakers tend to mix different languages in text and speech; a phenomenon
referred to by linguists as “code-switching”(CS). Also, speakers switch between morphemes …

Named entity recognition systems perform well on standard datasets comprising English
news. But given the paucity of data, it is difficult to draw conclusions about the robustness of …

This paper presents the SAGT Turkish–German code-switching treebank, and observations
and annotation challenges we encountered during its development. The treebank consists …