paper-with-me

홈 › Papers

Contextualized Sensorimotor Norms: multi-dimensional measures of sensorimotor strength for ambiguous English words, in context

2022-03-10 · Sean Trott, Benjamin Bergen

Most large language models are trained on linguistic input alone, yet humans appear to ground their understanding of words in sensorimotor experience. A natural solution is to augment LM representations with human judgments of a word's sensorimotor associations (e.g., the Lancaster Sensorimotor Norms), but this raises another challenge: most words are ambiguous, and judgments of words in isolation fail to account for this multiplicity of meaning (e.g., "wooden table" vs. "data table"). We attempted to address this problem by building a new lexical resource of contextualized sensorimotor judgments for 112 English words, each rated in four different contexts (448 sentences total). We show that these ratings encode overlapping but distinct information from the Lancaster Sensorimotor Norms, and that they also predict other measures of interest (e.g., relatedness), above and beyond measures derived from BERT. Beyond shedding light on theoretical questions, we suggest that these ratings could be of use as a "challenge set" for researchers building grounded language models.

📄 PDF Abstract BibTeX arXiv:2203.05648

Code (1)

seantrott/cs_norms 공식 구현

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
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
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

Contextualized Sensorimotor Norms: multi-dimensional measures of sensorimotor strength for ambiguous English words, in context

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

Most large language models are trained on linguistic input alone, yet humans appear to ground their understanding of words in sensorimotor experience. A natural solution is to augment LM representations with human judgme…

Chinese sensorimotor and embodiment norms for 3,000 lexicalized concepts

2026-05-21 · Jing Chen, Gábor Parti, Yin Zhong, Chu-Ren Huang 외 arxiv

Understanding how conceptual knowledge is grounded in bodily experience, and to what extent machine systems can acquire such knowledge without direct sensorimotor experience, are central questions in both cognitive scien…

Words that make SENSE: Sensorimotor Norms in Learned Lexical Token Representations

2026-01-31 · Abhinav Gupta, Toben H. Mintz, Jesse Thomason arxiv

While word embeddings derive meaning from co-occurrence patterns, human language understanding is grounded in sensory and motor experience. We present $\text{SENSE}$ $(\textbf{S}\text{ensorimotor }$ $\textbf{E}\text{mbed…

Enriching Language Models with Visually-grounded Word Vectors and the Lancaster Sensorimotor Norms

2021-11-01 · CoNLL (EMNLP) 2021 11 · Casey Kennington

Language models are trained only on text despite the fact that humans learn their first language in a highly interactive and multimodal environment where the first set of learned words are largely concrete, denoting phys…

Visual Dialog

A correlational analysis of multiagent sensorimotor interactions: clustering autonomous and controllable entities

2017-11-22 · M. Sánchez-Fibla, C. Moulin-Frier, X. Arsiwalla, P. Verschure

A first step to reach Theory of Mind (ToM) abilities (attribution of beliefs to others) in synthetic agents through sensorimotor interactions, would be to tag sensory data with agent typology and action intentions: auton…

ClusteringTAG