paper-with-me

홈 › Papers

Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings

2021-01-26 · EACL 2021 2 · Katharina Kann, Mauro M. Monsalve-Mercado

In contrast to their word- or sentence-level counterparts, character embeddings are still poorly understood. We aim at closing this gap with an in-depth study of English character embeddings. For this, we use resources from research on grapheme-color synesthesia -- a neuropsychological phenomenon where letters are associated with colors, which give us insight into which characters are similar for synesthetes and how characters are organized in color space. Comparing 10 different character embeddings, we ask: How similar are character embeddings to a synesthete's perception of characters? And how similar are character embeddings extracted from different models? We find that LSTMs agree with humans more than transformers. Comparing across tasks, grapheme-to-phoneme conversion results in the most human-like character embeddings. Finally, ELMo embeddings differ from both humans and other models.

📄 PDF Abstract BibTeX arXiv:2101.10565

Code (0)

등록된 구현이 없습니다.

Tasks

Grapheme-to-Phoneme ConversionSentence

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
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 $x$…
ELMo Embeddings from Language Models, or ELMo, is a type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and…

Similar Papers 제목 키워드 기반

Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensing

2023-12-04 · Ying Yuan, Haichuan Che, Yuzhe Qin, Binghao Huang 외

Executing contact-rich manipulation tasks necessitates the fusion of tactile and visual feedback. However, the distinct nature of these modalities poses significant challenges. In this paper, we introduce a system that l…

Contact-rich Manipulation

On Blackbox Backpropagation and Jacobian Sensing

2017-12-01 · NeurIPS 2017 12 · Krzysztof M. Choromanski, Vikas Sindhwani

From a small number of calls to a given “blackbox" on random input perturbations, we show how to efficiently recover its unknown Jacobian, or estimate the left action of its Jacobian on a given vector. Our methods are ba…

compressed sensing

Gray-Box Optimization and the Vertex Coloring Problem

2026-06-06 · Johanna Gasse, Antonia Heinen, Hendrik Higl, Timo Kötzing arxiv

Gray-box optimization is an approach for making some problem-specific information available to the algorithm while still relying on fitness information as the main guide to an optimum. This approach was shown to be benef…

What do language models model? Transformers, automata, and the format of thought

2025-08-26 · Colin Klein arxiv

What do large language models actually model? Do they tell us something about human capacities, or are they models of the corpus we've trained them on? I give a non-deflationary defence of the latter position. Cognitive …

What a neural language model tells us about spatial relations

2019-06-01 · WS 2019 6 · Mehdi Ghanimifard, Simon Dobnik

Understanding and generating spatial descriptions requires knowledge about what objects are related, their functional interactions, and where the objects are geometrically located. Different spatial relations have differ…

Image DescriptionLanguage ModelingLanguage Modelling