paper-with-me

Papers

ALTA: Compiler-Based Analysis of Transformers

2024-10-23 · Peter Shaw, James Cohan, Jacob Eisenstein, Kenton Lee, Jonathan Berant, Kristina Toutanova

We propose a new programming language called ALTA and a compiler that can map ALTA programs to Transformer weights. ALTA is inspired by RASP, a language proposed by Weiss et al. (2021), and Tracr (Lindner et al., 2023), a compiler from RASP programs to Transformer weights. ALTA complements and extends this prior work, offering the ability to express loops and to compile programs to Universal Transformers, among other advantages. ALTA allows us to constructively show how Transformers can represent length-invariant algorithms for computing parity and addition, as well as a solution to the SCAN benchmark of compositional generalization tasks, without requiring intermediate scratchpad decoding steps. We also propose tools to analyze cases where the expressibility of an algorithm is established, but end-to-end training on a given training set fails to induce behavior consistent with the desired algorithm. To this end, we explore training from ALTA execution traces as a more fine-grained supervision signal. This enables additional experiments and theoretical analyses relating the learnability of various algorithms to data availability and modeling decisions, such as positional encodings. We make the ALTA framework -- language specification, symbolic interpreter, and weight compiler -- available to the community to enable further applications and insights.

📄 PDF Abstract BibTeX arXiv:2410.18077

Code (1)

google-deepmind/alta 공식 구현 jax

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
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…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Transformers are Efficient Compilers, Provably

2024-10-07 · Xiyu Zhai, Runlong Zhou, Liao Zhang, Simon Shaolei Du

Transformer-based large language models (LLMs) have demonstrated surprisingly robust performance across a wide range of language-related tasks, including programming language understanding and generation. In this paper, …

BERT’s The Word : Sarcasm Target Detection using BERT

2021-12-01 · ALTA 2021 12 · Pradeesh Parameswaran, Andrew Trotman, Veronica Liesaputra, David Eyers

In 2019, the Australasian Language Technology Association (ALTA) organised a shared task to detect the target of sarcastic comments posted on social media. However, there were no winners as it proved to be a difficult ta…

REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers

2023-02-04 · Aivin V. Solatorio, Olivier Dupriez

Tabular data is a common form of organizing data. Multiple models are available to generate synthetic tabular datasets where observations are independent, but few have the ability to produce relational datasets. Modeling…

Synthetic Data Generation

Automatically Predicting Judgement Dimensions of Human Behaviour

2020-12-01 · ALTA 2020 12 · Segun Taofeek Aroyehun, Alexander Gelbukh

This paper describes our submission to the ALTA-2020 shared task on assessing behaviour from short text, We evaluate the effectiveness of traditional machine learning and recent transformers pre-trained models. Our submi…

BIG-bench Machine Learning

Malta National Language Technology Platform: A vision for enhancing Malta’s official languages using Machine Translation

2021-09-01 · MMTLRL (RANLP) 2021 9 · Keith Cortis, Judie Attard, Donatienne Spiteri

In this paper we introduce a vision towards establishing the Malta National Language Technology Platform; an ongoing effort that aims to provide a basis for enhancing Malta’s official languages, namely Maltese and Englis…

Machine TranslationTranslation