Clippers 02/19 Evan Jaffe on Coreference Resolution

Towards a Coreference-aware Measure of Surprisal

This talk will describe ongoing work to model coreference as an incremental process, discussing current results, model design, and current challenges. Coreference is the semantic identity relationship between entities. Humans are able to effortlessly produce and comprehend language that describes coreference relations. While much work has explored coreference from a psycholinguistic angle, extensive modeling efforts have come from a more task-oriented NLP domain that does not seek to model cognitively plausible mechanisms. The current work attempts to bridge the two approaches by modeling coreference as part of an incremental semantic parsing process. Ultimately the model will be evaluated on parsing performance, coreference performance, and how well its predictions correlate with human processing data.

Clippers 02/12 Denis Newman-Griffis on Word Sense Disambiguation

Learning to disambiguate by combining multiple sense representations

This talk will discuss ongoing work investigating the combination of multiple sense representation methods for word sense disambiguation (WSD). A variety of recent methods have been proposed for learning representations of semantic senses in different domains, and there is some evidence that different methods capture complementary information for WSD. We consider a simple but competitive cosine similarity-based model for WSD, and augment it by learning to produce a context-sensitive linear transformation of representations of candidate senses. In addition to transforming the input sense space, our method allows us to jointly project multiple sense representations into a single space. We find that a single learned projection matches or outperforms directly updated sense embeddings for single embedding methods, and demonstrate that combining multiple representations improves over any individual method alone. Further, by transforming and conjoining complete embedding spaces, we gain the ability to transfer model knowledge to ambiguous terms not seen during training; we are currently investigating the effectiveness of this transfer.