Mark my Word: A Sequence-to-Sequence Approach to Definition Modeling
This work addresses the task of definition modeling for natural language processing applications, offering a conceptual improvement over prior methods.
The paper tackled the problem of generating word definitions from textual context by formalizing it as a sequence-to-sequence task, achieving state-of-the-art results in both contextual and non-contextual definition modeling.
Defining words in a textual context is a useful task both for practical purposes and for gaining insight into distributed word representations. Building on the distributional hypothesis, we argue here that the most natural formalization of definition modeling is to treat it as a sequence-to-sequence task, rather than a word-to-sequence task: given an input sequence with a highlighted word, generate a contextually appropriate definition for it. We implement this approach in a Transformer-based sequence-to-sequence model. Our proposal allows to train contextualization and definition generation in an end-to-end fashion, which is a conceptual improvement over earlier works. We achieve state-of-the-art results both in contextual and non-contextual definition modeling.