paper-with-me

홈 › Papers

Syntactic Learnability of Echo State Neural Language Models at Scale

2025-03-03 · Ryo Ueda, Tatsuki Kuribayashi, Shunsuke Kando, Kentaro Inui

What is a neural model with minimum architectural complexity that exhibits reasonable language learning capability? To explore such a simple but sufficient neural language model, we revisit a basic reservoir computing (RC) model, Echo State Network (ESN), a restricted class of simple Recurrent Neural Networks. Our experiments showed that ESN with a large hidden state is comparable or superior to Transformer in grammaticality judgment tasks when trained with about 100M words, suggesting that architectures as complex as that of Transformer may not always be necessary for syntactic learning.

📄 PDF Abstract BibTeX arXiv:2503.01724

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Attention 설명 없음
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…
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…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Comparing learnability of two dependency schemes: ‘semantic’ (UD) and ‘syntactic’ (SUD)

2021-11-01 · Findings (EMNLP) 2021 11 · Ryszard Tuora, Adam Przepiórkowski, Aleksander Leczkowski

This paper contributes to the thread of research on the learnability of different dependency annotation schemes: one (‘semantic’) favouring content words as heads of dependency relations and the other (‘syntactic’) favou…

Vocal Bursts Valence Prediction

Learnability-Based Syntactic Annotation Design

2012-12-01 · COLING 2012 12 · Roy Schwartz, Omri Abend, Ari Rappoport

A systematic investigation of learnability from single child linguistic input

2024-02-12 · Yulu Qin, Wentao Wang, Brenden M. Lake

Language models (LMs) have demonstrated remarkable proficiency in generating linguistically coherent text, sparking discussions about their relevance to understanding human language learnability. However, a significant g…

Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Relations between words are governed by hierarchical structure rather than linear ordering. Sequence-to-sequence (seq2seq) models, despite their success in downstream NLP applications, often fail to generalize in a hiera…

Inductive Bias

Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models

2022-03-17 · Findings (ACL) 2022 5 · Aaron Mueller, Robert Frank, Tal Linzen, Luheng Wang 외

Relations between words are governed by hierarchical structure rather than linear ordering. Sequence-to-sequence (seq2seq) models, despite their success in downstream NLP applications, often fail to generalize in a hiera…

Inductive Bias