Making Sense About Sense

We suggest that the standard fine-grained division of senses and (larger) homographs by a lexicographer for use by a human reader may not be an appropriate goal for the computational WSD task. We argue that the level of sense-discrimination that natural language processing (NLP) needs corresponds roughly to homographs, though we discuss psycholinguistic evidence that there are broad sense divisions with some etymological derivation (i.e., non-homographic) that are as distinct for humans as homographic ones and they may be part of the broad class of sense-divisions we seek to identify here. We link this discussion to the observation that major NLP tasks like machine translation (MT) and information retrieval (IR) seem not to need independent WSD modules of the sort produced in the Research field, even though they are undoubtedly doing WSD by other means. Our conclusion is that WSD should continue to focus on these broad discriminations, at which it can do very well, thereby possibly offering the close-to-100% success that most NLP seemingly requires, with the possible exception of very fine questions of target word choice in MT. This proposal can be seen as reorienting WSD to what it can actually perform at the standard success levels, but we argue that this, rather than some more idealized vision of sense inherited from lexicography, is what humans and machines can reliably discriminate.