paper-with-me

홈 › Papers

Revenge of the Fallen? Recurrent Models Match Transformers at Predicting Human Language Comprehension Metrics

2024-04-30 · James A. Michaelov, Catherine Arnett, Benjamin K. Bergen

Transformers have generally supplanted recurrent neural networks as the dominant architecture for both natural language processing tasks and for modelling the effect of predictability on online human language comprehension. However, two recently developed recurrent model architectures, RWKV and Mamba, appear to perform natural language tasks comparably to or better than transformers of equivalent scale. In this paper, we show that contemporary recurrent models are now also able to match - and in some cases, exceed - the performance of comparably sized transformers at modeling online human language comprehension. This suggests that transformer language models are not uniquely suited to this task, and opens up new directions for debates about the extent to which architectural features of language models make them better or worse models of human language comprehension.

📄 PDF Abstract BibTeX arXiv:2404.19178

Code (1)

jmichaelov/recurrent-vs-transformer-modeling 공식 구현

Tasks

Mamba

Similar Papers 제목 키워드 기반

Leveraging Transformers for StarCraft Macromanagement Prediction

2021-10-11 · Muhammad Junaid Khan, Shah Hassan, Gita Sukthankar

Inspired by the recent success of transformers in natural language processing and computer vision applications, we introduce a transformer-based neural architecture for two key StarCraft II (SC2) macromanagement tasks: g…

PredictionStarcraftStarcraft IITransfer Learning

Should You Fine-Tune BERT for Automated Essay Scoring?

2020-07-01 · WS 2020 7 · Elijah Mayfield, Alan W. black

Most natural language processing research now recommends large Transformer-based models with fine-tuning for supervised classification tasks; older strategies like bag-of-words features and linear models have fallen out …

Automated Essay Scoring

Expert-augmented actor-critic for ViZDoom and Montezumas Revenge

2018-09-10 · Michał Garmulewicz, Henryk Michalewski, Piotr Miłoś

We propose an expert-augmented actor-critic algorithm, which we evaluate on two environments with sparse rewards: Montezumas Revenge and a demanding maze from the ViZDoom suite. In the case of Montezumas Revenge, an agen…

LoopSpec: Pipelined Self-Speculative Decoding for Looped Transformers

2026-09-15 · SangLyul Cho, Langqing Cui, Sehoon Kim, Dongsu Han 외 arxiv

Looped Transformers achieve strong performance with compact parameter sizes by repeatedly applying a shared stack of Transformer blocks across recurrent depths. However, they incur higher decoding latency than standard T…

Fallen Angel Bonds Investment and Bankruptcy Predictions Using Manual Models and Automated Machine Learning

2022-12-07 · Harrison Mateika, Juannan Jia, Linda Lillard, Noah Cronbaugh 외

The primary aim of this research was to find a model that best predicts which fallen angel bonds would either potentially rise up back to investment grade bonds and which ones would fall into bankruptcy. To implement the…

feature selection