Linguistic Profiling of a Neural Language Model

Proceedings of the 28th International Conference on Computational Linguistics, pages 745–756 Barcelona, Spain (Online), December 8-13, 2020 745 Linguistic Profiling of a Neural Language Model Alessio Miaschi⋆ ⋄, Dominique Brunato⋄, Felice Dell’Orletta⋄, Giulia Venturi⋄ ⋆Department of Computer Science, University of Pisa ⋄Istituto di Linguistica Computazionale “Antonio Zampolli”, Pisa ItaliaNLP Lab – www.italianlp.it alessio.miaschi@phd.unipi.it, {name.surname}@ilc.cnr.it Abstract In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems. We use a wide set of probing tasks, each of which corresponds to a distinct sentence-level feature extracted from different levels of linguistic annotation. We show that BERT is able to encode a wide range of linguistic characteristics, but it tends to lose this information when trained on specific downstream tasks. We also find that BERT’s capacity to encode different kind of linguistic properties has a positive influence on its predictions: the more it stores readable linguistic information of a sentence, the higher will be its capacity of predicting the expected label assigned to that sentence. 1 Introduction Neural Language Models (NLMs) have become a central component in NLP systems over the last few years, showing outstanding performance and improving the state-of-the-art on many tasks (Peters et al., 2018; Radford et al., 2018; Devlin et al., 2019). However, the introduction of such systems has come at the cost of interpretability and, consequently, at the cost of obtaining meaningful explanations when automated decisions take place. Recent work has begun to study these models in order to understand whether they encode linguistic phenomena even without being explicitly designed to learn such properties (Marvin and Linzen, 2018; Goldberg, 2019; Warstadt et al., 2019). Much of this work focused on the analysis and interpretation of attention mechanisms (Tang et al., 2018; Jain and Wallace, 2019; Clark et al., 2019) and on the definition of probing models trained to predict simple linguistic properties from unsupervised representations. Probing models trained on different contextual representations provided evidences that such models are able to capture a wide range of linguistic phenomena (Adi et al., 2016; Perone et al., 2018; Tenney et al., 2019b) and even to organize this information in a hierarchical manner (Belinkov et al., 2017; Lin et al., 2019; Jawahar et al., 2019). However, the way in which this knowledge affects the decisions they make when solving specific downstream tasks has been less studied. In this paper, we extended prior work by studying the linguistic properties encoded by one of the most prominent NLM, BERT (Devlin et al., 2019), and how these properties affect its predictions when solving a specific downstream task. We defined three research questions aimed at understanding: (i) what kind of linguistic properties are already encoded in a pre-trained version of BERT and where across its 12 layers; (ii) how the knowledge of these properties is modified after a fine-tuning process; (iii) whether this implicit knowledge affects the ability of the model to solve a specific …

Content truncated to 500 words