We are just a few days away from Coling 2018!
- I will present the paper SeVeN: Augmenting Word Embeddings
with Unsupervised Relation Vectors. The main idea is to learn relation vectors from which we abstract away the properties of the words involved in the relation. The code and a working example are available here. Take this example (from the paper), for instance. Our 10 dimensional vector encoding the relation between gmail and email is similar to ie and browser, firefox and browser and even helvetica and font. Interestingly, and when compared with the traditional vector difference (the diffvec column), we see that these similarities are more relational and less attributional, i.e., they rely less on the semantics of the words involved in the relation.
- I will also be hosting the third edition of the SemDeep workhsop. We will have a great mix of papers and invited talks, both of which will focus on knowledge representation, but from very different prisms.
And of course, looking forward to all the scientific program, meeting old friends, and the cooking lesson included in the social program 🙂