Name
Abstract | ||
|---|---|---|
We consider language modelling (LM) as a multi-label structured prediction task by re-framing training from solely predicting a single ground-truth word to ranking a set of words which could continue a given context. To avoid annotating top-k ranks, we generate them using pre-trained LMs: GPT-2, BERT, and Born-Again models. This leads to a rank-based form of knowledge distillation (KD). We also develop a method using N-grams to create a non-probabilistic teacher which generates the ranks without the need of a pre-trained LM. We confirm the hypotheses: that we can treat LMing as a ranking task and that we can do so without the use of a pre-trained LM. We show that rank-based KD generally gives a modest improvement to perplexity (PPL) -- though often with statistical significance -- when compared to Kullback–Leibler-based KD. Surprisingly, given the naivety of the method, the N-grams act as competitive teachers and achieve similar performance as using either BERT or a Born-Again model teachers. Unsurprisingly, GPT-2 always acts as the best teacher. Using it and a Transformer-XL student on Wiki-02, rank-based KD reduces a cross-entropy baseline from 65.27 to 55.94 and against a KL-based KD of 56.70. |
Year | Venue | Keywords |
|---|---|---|
2022 | AAAI Conference on Artificial Intelligence | Speech & Natural Language Processing (SNLP),Machine Learning (ML) |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Arvid Frydenlund | 1 | 2 | 1.12 |
| Gagandeep Singh | 2 | 78 | 11.52 |
| Frank Rudzicz | 3 | 231 | 44.82 |