paper-with-me

홈 › Papers

SemGloVe: Semantic Co-occurrences for GloVe from BERT

2020-12-30 · Leilei Gan, Zhiyang Teng, Yue Zhang, Linchao Zhu, Fei Wu, Yi Yang

GloVe learns word embeddings by leveraging statistical information from word co-occurrence matrices. However, word pairs in the matrices are extracted from a predefined local context window, which might lead to limited word pairs and potentially semantic irrelevant word pairs. In this paper, we propose SemGloVe, which distills semantic co-occurrences from BERT into static GloVe word embeddings. Particularly, we propose two models to extract co-occurrence statistics based on either the masked language model or the multi-head attention weights of BERT. Our methods can extract word pairs without limiting by the local window assumption and can define the co-occurrence weights by directly considering the semantic distance between word pairs. Experiments on several word similarity datasets and four external tasks show that SemGloVe can outperform GloVe.

📄 PDF Abstract BibTeX arXiv:2012.15197

Code (3)

2023-MindSpore-4/Code12/tree/main/ganleilei/SemGloVeMindspore-master mindspore
2024-MindSpore-1/Code2/tree/main/tengzhiyang/LogiQA2.0-main mindspore
2024-MindSpore-1/Code2/tree/main/tengzhiyang/SemGloVeMindspore-master mindspore

Tasks

Language ModelingLanguage ModellingWord EmbeddingsWord Similarity

Methods 이 논문이 사용한 방법론

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…
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 $x$…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
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…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Word-Node2Vec: Improving Word Embedding with Document-Level Non-Local Word Co-occurrences

2019-06-01 · NAACL 2019 6 · Procheta Sen, Debasis Ganguly, Gareth Jones

A standard word embedding algorithm, such as word2vec and glove, makes a strong assumption that words are likely to be semantically related only if they co-occur locally within a window of fixed size. However, this stron…

ViCo: Word Embeddings from Visual Co-occurrences

2019-08-22 · ICCV 2019 10 · Tanmay Gupta, Alexander Schwing, Derek Hoiem

We propose to learn word embeddings from visual co-occurrences. Two words co-occur visually if both words apply to the same image or image region. Specifically, we extract four types of visual co-occurrences between obje…

AttributeClusteringWord Embeddings

SST-BERT at SemEval-2020 Task 1: Semantic Shift Tracing by Clustering in BERT-based Embedding Spaces

2020-10-02 · SEMEVAL 2020 · K Vani, Sandra Mitrovic, Alessandro Antonucci, Fabio Rinaldi

Lexical semantic change detection (also known as semantic shift tracing) is a task of identifying words that have changed their meaning over time. Unsupervised semantic shift tracing, focal point of SemEval2020, is parti…

Change DetectionClustering

The aftermath of compounds: Investigating Compounds and their Semantic Representations

2025-10-31 · Swarang Joshi arxiv

This study investigates how well computational embeddings align with human semantic judgments in the processing of English compound words. We compare static word vectors (GloVe) and contextualized embeddings (BERT) again…

Exponential Family Word Embeddings: An Iterative Approach for Learning Word Vectors

2018-10-22 · NIPS Workshop IRASL 2018 · Anonymous

GloVe and Skip-gram word embedding methods learn word vectors by decomposing a denoised matrix of word co-occurrences into a product of low-rank matrices. In this work, we propose an iterative algorithm for computing wor…

Word Embeddings