Amirhossein Kazemnejad

amirhossein.kazemnejad@mila.quebec

Maîtrise recherche - McGill University

Superviseur⋅e principal⋅e

Siva Reddy

Github

Publications

Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models

Amirhossein Kazemnejad

Mehdi Rezagholizadeh

Prasanna Parthasarathi

Sarath Chandar Anbil Parthipan

2023-12-01

Findings of the Association for Computational Linguistics: EMNLP 2023 (publié)

doi.org

openreview.net

The Impact of Positional Encoding on Length Generalization in Transformers

Amirhossein Kazemnejad

Inkit Padhi

Karthikeyan Natesan

K. Ramamurthy

Payel Das

Siva Reddy

Length generalization, the ability to generalize from small training context sizes to larger ones, is a critical challenge in the developmen… (voir plus)t of Transformer-based language models. Positional encoding (PE) has been identified as a major factor influencing length generalization, but the exact impact of different PE schemes on extrapolation in downstream tasks remains unclear. In this paper, we conduct a systematic empirical study comparing the length generalization performance of decoder-only Transformers with five different position encoding approaches including Absolute Position Embedding (APE), T5's Relative PE, ALiBi, and Rotary, in addition to Transformers without positional encoding (NoPE). Our evaluation encompasses a battery of reasoning and mathematical tasks. Our findings reveal that the most commonly used positional encoding methods, such as ALiBi, Rotary, and APE, are not well suited for length generalization in downstream tasks. More importantly, NoPE outperforms other explicit positional encoding methods while requiring no additional computation. We theoretically demonstrate that NoPE can represent both absolute and relative PEs, but when trained with SGD, it mostly resembles T5's relative PE attention patterns. Finally, we find that scratchpad is not always helpful to solve length generalization and its format highly impacts the model's performance. Overall, our work suggests that explicit position embeddings are not essential for decoder-only Transformers to generalize well to longer sequences.

openreview.net

The Curious Case of Absolute Position Embeddings

Koustuv Sinha

Amirhossein Kazemnejad

Siva Reddy

Joelle Pineau

Dieuwke Hupkes

Adina Williams

2022-01-01

EMNLP (Findings) (publié)

doi.org

arxiv.org