Can You Tag the Modal? You Should

Computational linguistics methods are typically first developed and tested in English. When applied to other languages, assumptions from English data are often applied to the target language. One of the most common such assumptions is that a “standard” part-of-speech (POS) tagset can be used across languages with only slight variations. We discuss in this paper a specific issue related to the definition of a POS tagset for Modern Hebrew, as an example to clarify the method through which such variations can be defined. It is widely assumed that Hebrew has no syntactic category of modals. There is, however, an identified
class of words which are modal-like in their semantics, and can be characterized through distinct syntactic and morphologic criteria. We have found wide disagreement among traditional dictionaries on the POS tag attributed to such words. We describe three main approaches when deciding how to tag such words in Hebrew. We illustrate the impact of selecting each of these approaches on agreement among human taggers, and on the accuracy of automatic POS taggers induced for each method. We finally recommend the use of a “modal” tag in Hebrew
and provide detailed guidelines for this tag. Our overall conclusion is that tagset definition is a complex task which deserves appropriate methodology.