paper-with-me

홈 › Papers

What do tokens know about their characters and how do they know it?

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Pre-trained language models (PLMs) that use subword tokenization schemes can succeed at a variety of language tasks that require character-level information, despite lacking explicit access to the character composition of tokens. Here, studying a range of models (e.g., GPT-J, BERT, RoBERTa, GloVe), we probe what word pieces encode about character-level information by training classifier to predict the presence or absence of a particular alphabetical character in an English-language token, based on its embedding (e.g., probing whether the model embedding for "cat" encodes that it contains the character "a"). We find that these models robustly encode character-level information and, in general, larger models perform better at the task. Through a series of experiments and analyses, we investigate the mechanisms through which PLMs acquire character information during training and argue that this knowledge is acquired through multiple phenomena, including a systematic relationship between particular characters and particular parts of speech, as well as natural variability in the tokenization of related strings.

📄 PDF Abstract BibTeX

Code (1)

anonymous-arr/code 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
RoBERTa 설명 없음
Adam 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 Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

What do tokens know about their characters and how do they know it?

2022-06-06 · NAACL 2022 7 · Ayush Kaushal, Kyle Mahowald

Pre-trained language models (PLMs) that use subword tokenization schemes can succeed at a variety of language tasks that require character-level information, despite lacking explicit access to the character composition o…

Understanding the Role of Input Token Characters in Language Models: How Does Information Loss Affect Performance?

2023-10-26 · Ahmed Alajrami, Katerina Margatina, Nikolaos Aletras

Understanding how and what pre-trained language models (PLMs) learn about language is an open challenge in natural language processing. Previous work has focused on identifying whether they capture semantic and syntactic…

“Politeness, you simpleton!” retorted [MASK]: Masked prediction of literary characters

2021-06-01 · IWCS (ACL) 2021 6 · Eric Holgate, Katrin Erk

What is the best way to learn embeddings for entities, and what can be learned from them? We consider this question for the case of literary characters. We address the highly challenging task of guessing, from a sentence…

Entity EmbeddingsSentence

CUTE: Measuring LLMs' Understanding of Their Tokens

2024-09-23 · Lukas Edman, Helmut Schmid, Alexander Fraser

Large Language Models (LLMs) show remarkable performance on a wide variety of tasks. Most LLMs split text into multi-character tokens and process them as atomic units without direct access to individual characters. This …

Zipf's Law and the Frequency of Characters or Words of Oracles

2014-12-09 · Xiuli Wang

The article discusses the frequency of characters of Oracle,concluding that the frequency and the rank of a word or character is fit to Zipf-Mandelboit Law or Zipf's law with three parameters,and figuring out the paramet…