Interpretable Word Embeddings via Informative Priors
, 2019 Word embeddings have demonstrated strong performance on NLP tasks. However, lack of interpretability and the unsupervised nature of word embeddings have limited their use within computational social science and digital humanities.
Arvidsson, Martin, +2 more
core
Predicting drug-gene relations via analogy tasks with word embeddings. [PDF]
Sci RepYamagiwa H +8 more
europepmc +1 more source
Multimodal Human–Robot Interaction Using Human Pose Estimation and Local Large Language Models
Advanced Robotics Research, EarlyView.A multimodal human–robot interaction framework integrates human pose estimation (HPE) and a large language model (LLM) for gesture‐ and voice‐based robot control. Speech‐to‐text (STT) enables voice command interpretation, while a safety‐aware arbitration mechanism prioritizes gesture input for rapid intervention.
Nasiru Aboki +2 more
wiley +1 more source
Teleosemantics for Neural Word Embeddings
This paper applies a consumer-based teleosemantic framework to give a detailed analysis of a particular algorithm for generating word embeddings. In the process, it addresses several of the challenges facing teleosemantic approaches to artificial neural ...
Mallory, Fintan
core
Interpreting Word Embeddings with Eigenvector Analysis
, 2018 Dense word vectors have proven their values in many downstream NLP tasks over the past few years. However, the dimensions of such embeddings are not easily interpretable.
Shin, Jamin +2 more
core
Leveraging word embeddings to enhance co-occurrence networks: A statistical analysis. [PDF]
PLoS OneAmancio DR, Machicao J, Quispe LVC.
europepmc +1 more source
Evaluating Biomedical Word Embeddings for Vocabulary Alignment at Scale in the UMLS Metathesaurus Using Siamese Networks. [PDF]
Proc Conf Assoc Comput Linguist Meet, 2022 Bajaj G +7 more
europepmc +1 more source
LLM‐Integrated Human–Robot Interaction System for Microrobots
Advanced Robotics Research, EarlyView.This paper proposes an LLM‐based control framework for guiding microrobots using human natural language. This framework can convert the natural human speech into safe and executable command sets for reliable navigation in complex environments. The experimental results show high accuracy and robustness in task performance, demonstrating the potential of
Bairong Zhu, Amar Salehi, Tingting Yu
wiley +1 more source
Back-translation effects on static and contextual word embeddings for topic classification embedding in classification tasks. [PDF]
PLoS OneDržík D, Kelebercová L.
europepmc +1 more source
Negative Associations in Word Embeddings Predict Anti-black Bias across Regions-but Only via Name Frequency. [PDF]
Proc Int AAAI Conf Weblogs Soc Media, 2022 van Loon A +3 more
europepmc +1 more source