paper-with-me

홈 › Papers

Adaptable Embeddings Network (AEN)

2024-11-21 · Stan Loosmore, Alexander Titus

Modern day Language Models see extensive use in text classification, yet this comes at significant computational cost. Compute-effective classification models are needed for low-resource environments, most notably on edge devices. We introduce Adaptable Embeddings Networks (AEN), a novel dual-encoder architecture using Kernel Density Estimation (KDE). This architecture allows for runtime adaptation of classification criteria without retraining and is non-autoregressive. Through thorough synthetic data experimentation, we demonstrate our model outputs comparable and in certain cases superior results to that of autoregressive models an order of magnitude larger than AEN's size. The architecture's ability to preprocess and cache condition embeddings makes it ideal for edge computing applications and real-time monitoring systems.

📄 PDF Abstract BibTeX arXiv:2411.13786

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationDensity EstimationEdge-computingtext-classificationText Classification

Similar Papers 제목 키워드 기반

Domain-shift Conditioning using Adaptable Filtering via Hierarchical Embeddings for Robust Chinese Spell Check

2020-08-27 · Minh Nguyen, Gia H. Ngo, Nancy F. Chen

Spell check is a useful application which processes noisy human-generated text. Spell check for Chinese poses unresolved problems due to the large number of characters, the sparse distribution of errors, and the dearth o…

Spelling Correction

Evaluating Embeddings for One-Shot Classification of Doctor-AI Consultations

2024-02-06 · Olumide Ebenezer Ojo, Olaronke Oluwayemisi Adebanji, Alexander Gelbukh, Hiram Calvo 외

Effective communication between healthcare providers and patients is crucial to providing high-quality patient care. In this work, we investigate how Doctor-written and AI-generated texts in healthcare consultations can …

Facing the most difficult case of Semantic Role Labeling: A collaboration of word embeddings and co-training

2016-12-01 · COLING 2016 12 · Quynh Ngoc Thi Do, Steven Bethard, Marie-Francine Moens

We present a successful collaboration of word embeddings and co-training to tackle in the most difficult test case of semantic role labeling: predicting out-of-domain and unseen semantic frames. Despite the fact that co-…

Semantic Role LabelingWord Embeddings

Learning to Create Sentence Semantic Relation Graphs for Multi-Document Summarization

2019-09-20 · WS 2019 11 · Diego Antognini, Boi Faltings

Linking facts across documents is a challenging task, as the language used to express the same information in a sentence can vary significantly, which complicates the task of multi-document summarization. Consequently, e…

Document SummarizationMulti-Document SummarizationRelationSentence+1

Cross-Lingual Word Embeddings for Turkic Languages

2020-05-17 · LREC 2020 5 · Elmurod Kuriyozov, Yerai Doval, Carlos Gómez-Rodríguez

There has been an increasing interest in learning cross-lingual word embeddings to transfer knowledge obtained from a resource-rich language, such as English, to lower-resource languages for which annotated data is scarc…

Cross-Lingual Word EmbeddingsSentiment AnalysisWord Embeddings