About The Webinar
In this talk I present two novel approaches, Generationary and Exemplification Modeling, that go beyond the mainstream assumption that word senses can be represented as discrete items of a predefined inventory, and put forward generative models which produce contextualized definitions and usage examples for arbitrary lexical items, from words to phrases. Generationary employs a novel span-based encoding scheme to fine-tune an English pre-trained Encoder-Decoder system and generate new definitions. Generationary outperforms previous approaches in the generative task of Definition Modeling in many settings, but it also matches or surpasses the state of the art in discriminative tasks such as Word Sense Disambiguation and Word-in-Context. Exemplification Modeling takes the opposite perspective: it puts forward a novel task and a seq2seq architecture which generates usage examples given one or more words with their sense definitions. In addition to their considerable degree of freedom in "understanding" lexical meanings, we show that both approaches benefit from training on definitions from multiple inventories, with strong gains across benchmarks.
Some of our speakers