The Heads Hypothesis: A Unifying Statistical Approach Towards Understanding Multi-Headed Attention in BERT

Abstract

Multi-headed attention heads are a mainstay in transformer-based models. Different methods have been proposed to classify the role of each attention head based on the relations between tokens which have high pair-wise attention. These roles include syntactic (tokens with some syntactic relation), local (nearby tokens), block (tokens in the same sentence) and delimiter (the special [CLS], [SEP] tokens). There are two main challenges with existing methods for classification: (a) there are no standard scores across studies or across functional roles, and (b) these scores are often average quantities measured across sentences without capturing statistical significance. In this work, we formalize a simple yet effective score that generalizes to all the roles of attention heads and employs hypothesis testing on this score for robust inference. This provides us the right lens to systematically analyze attention heads and confidently comment on many commonly posed questions on analyzing the BERT model. In particular, we comment on the co-location of multiple functional roles in the same attention head, the distribution of attention heads across layers, and effect of fine-tuning for specific NLP tasks on these functional roles. The code is made publicly available at https://github.com/iitmnlp/heads-hypothesis

Acceptability Judgements via Examining the Topology of Attention Maps

“…Our findings on the heads' roles align with several related studies. The results on the COLA-style and BLIMP benchmarks indicate that (i) a single head can perform multiple linguistic functions (Pande et al, 2021), (ii) some linguistic phenomena, e.g., phrasal movement and island effects, are better captured by head ensembles rather than one head (Htut et al, 2019), and (iii) heads within the same or nearby layers extract similar grammatical phenomena (Bian et al, 2021).…”

“…Prior work has demonstrated that heads induce grammar formalisms and structural knowledge (Zhou and Zhao, 2019;Luo, 2021), and linguistic features motivate attention patterns (Kovaleva et al, 2019;Clark et al, 2019). Recent studies also show that certain heads can have multiple functional roles (Pande et al, 2021) and even perform syntactic functions for typologically distant languages (Ravishankar et al, 2021).…”

StatMix: Data Augmentation Method that Relies on Image Statistics in Federated Learning

“…In essence, based on the results presented in Tables 2, 3 and 4 we conclude that using information from the attention mechanism is helpful in creating augmented samples. At the same time, a detailed The existence of unintuitive attention heads has been already observed in the literature [4,13]. The first paper, besides other topics, studies the socalled vertical attention heads that attend mostly to dots, comas and BERT special tokens.…”