Multilingual Email Zoning
This addresses the problem of limited multilingual email zoning tools for NLP practitioners, though it is incremental as it extends existing methods to new languages.
The paper tackled the lack of multilingual resources for email zoning by creating a new benchmark of 625 emails in Portuguese, Spanish, and French, and introduced OKAPI, a multilingual model that achieved competitive performance with English benchmarks and set new state-of-the-art results for domain adaptation tasks in English.
The segmentation of emails into functional zones (also dubbed email zoning) is a relevant preprocessing step for most NLP tasks that deal with emails. However, despite the multilingual character of emails and their applications, previous literature regarding email zoning corpora and systems was developed essentially for English. In this paper, we analyse the existing email zoning corpora and propose a new multilingual benchmark composed of 625 emails in Portuguese, Spanish and French. Moreover, we introduce OKAPI, the first multilingual email segmentation model based on a language agnostic sentence encoder. Besides generalizing well for unseen languages, our model is competitive with current English benchmarks, and reached new state-of-the-art performances for domain adaptation tasks in English.