LMMS Wordnet Embeddings for SemCor corpus

This dataset contains word vectors generated after training the LMMS Language Modelling Makes Sense (ACL 2019) model with the whole train set of SemCor, adapted by rdenaux.

The main modifications include:

support for transformers backend ** this makes it possible to experiment with other transformer architectures besides BERT, e.g. XLNet, XLM, RoBERTa ** optimised training since we no longer have to pad sequences to 512 wordpiece tokens

Introduced SentenceEncoder which is an experimental generalisation of bert-as-service like encoding services using the transformers backend ** allows to extract various types of embeddings from a single execution of a batch of sequences

rolling cosine similarity metrics during training phase

The original repository includes the code to replicate the experiments in the "Language Modelling Makes Sense (ACL 2019)" paper.

This project is designed to be modular so that others can easily modify or reuse the portions that are relevant for them. Its composed of a series of scripts that when run in sequence produce most of the work described in the paper (for simplicity, we've focused this release on BERT, let us know if you need ELMo).

The code is available here.