paper-with-me

Papers

Visualizing Attention in Transformer-Based Language Representation Models

2019-04-04 · Jesse Vig

We present an open-source tool for visualizing multi-head self-attention in Transformer-based language representation models. The tool extends earlier work by visualizing attention at three levels of granularity: the attention-head level, the model level, and the neuron level. We describe how each of these views can help to interpret the model, and we demonstrate the tool on the BERT model and the OpenAI GPT-2 model. We also present three use cases for analyzing GPT-2: detecting model bias, identifying recurring patterns, and linking neurons to model behavior.

📄 PDF Abstract BibTeX arXiv:1904.02679

Code (0)

등록된 구현이 없습니다.

Tasks

Language Modelling

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
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 &…

Similar Papers 제목 키워드 기반

Visualizing and Measuring the Geometry of BERT

2019-06-06 · NeurIPS 2019 12 · Andy Coenen, Emily Reif, Ann Yuan, Been Kim 외

Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks, these networks appear to extract general…

Word Embeddings

Visualizing Music Transformer

2018-10-23 · NIPS Workshop IRASL 2018 · Anonymous

Like language, music can be represented as a sequence of discrete symbols that form a hierarchical syntax, with notes being roughly like characters and motifs of notes like words. Unlike text however, music relies heavi…

ARCDescriptiveInductive Bias

Effective Attention Sheds Light On Interpretability

2021-05-18 · Findings (ACL) 2021 8 · Kaiser Sun, Ana Marasović

An attention matrix of a transformer self-attention sublayer can provably be decomposed into two components and only one of them (effective attention) contributes to the model output. This leads us to ask whether visuali…

Language ModelingLanguage Modelling

Explainability Techniques for Chemical Language Models

2023-05-25 · Stefan Hödl, William Robinson, Yoram Bachrach, Wilhelm Huck 외

Explainability techniques are crucial in gaining insights into the reasons behind the predictions of deep learning models, which have not yet been applied to chemical language models. We propose an explainable AI techniq…

AttentionBender: Manipulating Cross-Attention in Video Diffusion Transformers as a Creative Probe

2026-04-22 · Adam Cole, Mick Grierson arxiv

We present AttentionBender, a tool that manipulates cross-attention in Video Diffusion Transformers to help artists probe the internal mechanics of black-box video generation. While generative outputs are increasingly re…

Video Generation