paper-with-me

Papers

Influence Patterns for Explaining Information Flow in BERT

2020-11-02 · NeurIPS 2021 12 · Kaiji Lu, Zifan Wang, Piotr Mardziel, Anupam Datta

While attention is all you need may be proving true, we do not know why: attention-based transformer models such as BERT are superior but how information flows from input tokens to output predictions are unclear. We introduce influence patterns, abstractions of sets of paths through a transformer model. Patterns quantify and localize the flow of information to paths passing through a sequence of model nodes. Experimentally, we find that significant portion of information flow in BERT goes through skip connections instead of attention heads. We further show that consistency of patterns across instances is an indicator of BERT's performance. Finally, We demonstrate that patterns account for far more model performance than previous attention-based and layer-based methods.

📄 PDF Abstract BibTeX arXiv:2011.00740

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
WordPiece 설명 없음
Attention 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

ABSTRACTING INFLUENCE PATHS FOR EXPLAINING (CONTEXTUALIZATION OF) BERT MODELS

2020-09-28 · Kaiji Lu, Zifan Wang, Piotr Mardziel, Anupam Datta

While “attention is all you need” may be proving true, we do not yet know why: attention-based transformer models such as BERT are superior but how they contextualize information even for simple grammatical rules such as…

Explaining and Improving BERT Performance on Lexical Semantic Change Detection

2021-03-12 · EACL 2021 2 · Severin Laicher, Sinan Kurtyigit, Dominik Schlechtweg, Jonas Kuhn 외

Type- and token-based embedding architectures are still competing in lexical semantic change detection. The recent success of type-based models in SemEval-2020 Task 1 has raised the question why the success of token-base…

Change Detection

Detecting Deceptive Dark Patterns in E-commerce Platforms

2024-05-27 · Arya Ramteke, Sankalp Tembhurne, Gunesh Sonawane, Ratnmala N. Bhimanpallewar

Dark patterns are deceptive user interfaces employed by e-commerce websites to manipulate user's behavior in a way that benefits the website, often unethically. This study investigates the detection of such dark patterns…

Telling BERT's full story: from Local Attention to Global Aggregation

2020-04-10 · EACL 2021 2 · Damian Pascual, Gino Brunner, Roger Wattenhofer

We take a deep look into the behavior of self-attention heads in the transformer architecture. In light of recent work discouraging the use of attention distributions for explaining a model's behavior, we show that atten…

“Mama Always Had a Way of Explaining Things So I Could Understand”: A Dialogue Corpus for Learning to Construct Explanations

2022-10-01 · COLING 2022 10 · Henning Wachsmuth, Milad Alshomary

As AI is more and more pervasive in everyday life, humans have an increasing demand to understand its behavior and decisions. Most research on explainable AI builds on the premise that there is one ideal explanation to b…