activity
20182022
most citedEvaluating Word Embedding Models: Methods and Experimental Results

331 citations · 331 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2022

Just Rank: Rethinking Evaluation with Word and Sentence Similarities

Bin Wang, C. -C. Jay Kuo, Haizhou Li

Word and sentence embeddings are useful feature representations in natural language processing. However, intrinsic evaluation for embeddings lags far behind, and there has been no…

cs.CL2020

Efficient Sentence Embedding via Semantic Subspace Analysis

Bin Wang, Fenxiao Chen, Yuncheng Wang +1

A novel sentence embedding method built upon semantic subspace analysis, called semantic subspace sentence embedding (S3E), is proposed in this work. Given the fact that word embed…

cs.CL2020

SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models

Bin Wang, C. -C. Jay Kuo

Sentence embedding is an important research topic in natural language processing (NLP) since it can transfer knowledge to downstream tasks. Meanwhile, a contextualized word represe…

cs.CL2019331 cited

Evaluating Word Embedding Models: Methods and Experimental Results

Bin Wang, Angela Wang, Fenxiao Chen +2

Extensive evaluation on a large number of word embedding models for language processing applications is conducted in this work. First, we introduce popular word embedding models an…

cs.CL2018

Graph-based Deep-Tree Recursive Neural Network (DTRNN) for Text Classification

Fenxiao Chen, Bin Wang, C. -C. Jay Kuo

A novel graph-to-tree conversion mechanism called the deep-tree generation (DTG) algorithm is first proposed to predict text data represented by graphs. The DTG method can generate…

cs.CL2018

Post-Processing of Word Representations via Variance Normalization and Dynamic Embedding

Bin Wang, Fenxiao Chen, Angela Wang +1

Although embedded vector representations of words offer impressive performance on many natural language processing (NLP) applications, the information of ordered input sequences is…