paper-with-me

Papers

Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings

2018-04-14 · NAACL 2018 6 · Joshua Coates, Danushka Bollegala

Creating accurate meta-embeddings from pre-trained source embeddings has received attention lately. Methods based on global and locally-linear transformation and concatenation have shown to produce accurate meta-embeddings. In this paper, we show that the arithmetic mean of two distinct word embedding sets yields a performant meta-embedding that is comparable or better than more complex meta-embedding learning methods. The result seems counter-intuitive given that vector spaces in different source embeddings are not comparable and cannot be simply averaged. We give insight into why averaging can still produce accurate meta-embedding despite the incomparability of the source vector spaces.

📄 PDF Abstract BibTeX arXiv:1804.05262

Code (1)

Shujian2015/meta-embedding-paper-list

Tasks

Word Embeddings

Similar Papers 제목 키워드 기반

Return of Frustratingly Easy Unsupervised Video Domain Adaptation

2026-05-19 · Pengfei Wei, Yiqun Sun, Zhiqiang Xu, Yiping Ke 외 arxiv

Unsupervised video domain adaptation (UVDA) is a practical but under-explored problem. In this paper, we propose a frustratingly easy UVDA method, called MetaTrans. Specifically, MetaTrans adopts a concise learning objec…

Action RecognitionDomain Adaptation

On the Effectiveness of Sentence Encoding for Intent Detection Meta-Learning

2022-07-01 · NAACL 2022 7 · Tingting Ma, Qianhui Wu, Zhiwei Yu, Tiejun Zhao 외

Recent studies on few-shot intent detection have attempted to formulate the task as a meta-learning problem, where a meta-learning model is trained with a certain capability to quickly adapt to newly specified few-shot t…

Intent DetectionMeta-LearningSemantic SimilaritySemantic Textual Similarity+4

Minimizing Memorization in Meta-learning: A Causal Perspective

2021-09-29 · Yinjie Jiang, Zhengyu Chen, Luotian Yuan, Ying WEI 외

Meta-learning has emerged as a potent paradigm for quick learning of few-shot tasks, by leveraging the meta-knowledge learned from meta-training tasks. Well-generalized meta-knowledge that facilitates fast adaptation in …

Causal InferenceMemorizationMeta-Learning

Joint Embedding of Meta-Path and Meta-Graph for Heterogeneous Information Networks

2018-09-11 · Lichao Sun, Lifang He, Zhipeng Huang, Bokai Cao 외

Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks,where a meta-graph is a composition of meta-paths that captures the complex structural information. However, curr…

Network EmbeddingTensor Decomposition

Frustratingly Easy Uncertainty Estimation for Distribution Shift

2021-06-07 · Tiago Salvador, Vikram Voleti, Alexander Iannantuono, Adam Oberman

Distribution shift is an important concern in deep image classification, produced either by corruption of the source images, or a complete change, with the solution involving domain adaptation. While the primary goal is …

Domain Adaptationimage-classificationImage ClassificationUnsupervised Domain Adaptation