Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks
Laura Aina | Nikos Voskarides | Roi Blanco
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Pre-trained language models (LMs) obtain state-of-the-art performance when adapted to text classification tasks. However, when using such models in real world applications, efficiency considerations are paramount. In this paper, we study how different training procedures that adapt LMs to text classification perform, as we vary model and train set size. More specifically, we compare standard fine-tuning, prompting, and knowledge distillation (KD) when the teacher was trained with either fine-tuning or prompting. Our findings suggest that even though fine-tuning and prompting work well to train large LMs on large train sets, there are more efficient alternatives that can reduce compute or data cost. Interestingly, we find that prompting combined with KD can reduce compute and data cost at the same time.
Book QA: Stories of Challenges and Opportunities
Stefanos Angelidis | Lea Frermann | Diego Marcheggiani | Roi Blanco | Lluís Màrquez
Proceedings of the 2nd Workshop on Machine Reading for Question Answering
We present a system for answering questions based on the full text of books (BookQA), which first selects book passages given a question at hand, and then uses a memory network to reason and predict an answer. To improve generalization, we pretrain our memory network using artificial questions generated from book sentences. We experiment with the recently published NarrativeQA corpus, on the subset of Who questions, which expect book characters as answers. We experimentally show that BERT-based retrieval and pretraining improve over baseline results significantly. At the same time, we confirm that NarrativeQA is a highly challenging data set, and that there is need for novel research in order to achieve high-precision BookQA results. We analyze some of the bottlenecks of the current approach, and we argue that more research is needed on text representation, retrieval of relevant passages, and reasoning, including commonsense knowledge.
- Laura Aina 1
- Nikos Voskarides 1
- Stefanos Angelidis 1
- Lea Frermann 1
- Diego Marcheggiani 1
- show all...