Investigating BERT’s Knowledge of Language: Five Analysis Methods with NPIs

Abstract

Though state-of-the-art sentence representation models can perform tasks requiring significant knowledge of grammar, it is an open question how best to evaluate their grammatical knowledge. We explore five experimental methods inspired by prior work evaluating pretrained sentence representation models. We use a single linguistic phenomenon, negative polarity item (NPI) licensing in English, as a case study for our experiments. NPIs like any are grammatical only if they appear in a licensing environment like negation (Sue doesn't have any cats vs. *Sue has any cats). This phenomenon is challenging because of the variety of NPI licensing environments that exist. We introduce an artificially generated dataset that manipulates key features of NPI licensing for the experiments. We find that BERT has significant knowledge of these features, but its success varies widely across different experimental methods. We conclude that a variety of methods is necessary to reveal all relevant aspects of a model's grammatical knowledge in a given domain. 1 Other prominent theories of NPI licensing are based on notions of non-veridicality (

Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?

“…Within the paradigm of training large pretrained Transformer language representations via intermediate-stage training before fine-tuning on a target task, positive transfer has been shown in both sequential task-to-task (Phang et al, 2018) and multi-task-to-task Raffel et al, 2019) formats. Wang et al (2019a) perform an extensive study on transfer with BERT, finding language modeling and NLI tasks to be among the most beneficial tasks for improving target-task performance. Talmor and Berant (2019) perform a similar cross-task transfer study on reading comprehension datasets, finding similar positive transfer in most cases, with the biggest gains stemming from a combination of multiple QA datasets.…”

“…Unsupervised pretraining-e.g., BERT (Devlin et al, 2019) or RoBERTa (Liu et al, 2019b)-has recently pushed the state of the art on many natural language understanding tasks. One method of further improving pretrained models that has been shown to be broadly helpful is to first finetune a pretrained model on an intermediate task, before fine-tuning again on the target task of interest (Phang et al, 2018;Wang et al, 2019a;Clark et al, 2019a;Sap et al, 2019), also referred to as * Equal contribution. STILTs.…”

“…This paper offers a large-scale empirical study aimed at addressing this open question. We perform a broad survey of intermediate and target task pairs, following an experimental pipeline similar to Phang et al (2018) and Wang et al (2019a). This differs from previous work in that we use a larger and more diverse set of intermediate and target tasks, introduce additional analysis-oriented probing tasks, and use a better-performing base model RoBERTa (Liu et al, 2019b).…”

OCNLI: Original Chinese Natural Language Inference

“…These large corpora have been used as part of larger benchmark sets, e.g., GLUE (Wang et al, 2018), and have proven useful for problems beyond NLI, such as sentence representation and transfer learning (Conneau et al, 2017;Subramanian et al, 2018;Reimers and Gurevych, 2019), automated question-answering (Khot et al, 2018;Trivedi et al, 2019) and model probing (Warstadt et al, 2019;Geiger et al, 2020;Jeretic et al, 2020).…”

On the Robustness of Language Encoders against Grammatical Errors

“…To evaluate and promote the robustness of neural models against noise, some studies manually create new datasets with specific linguistic phenomena (Linzen et al, 2016;Marvin and Linzen, 2018;Goldberg, 2019;Warstadt et al, 2019a). Others have introduced various methods to generate synthetic errors on clean downstream datasets, in particular, machine translation corpora.…”