Scholarlink

Sentence structure consists of a complex structure of words and relationships between words, which can be hard to represent with only a sequential representation and makes it challenging to learn long-range dependencies. This research presents a novel dynamic word embedding method designed to improve text classification performance. The method leverages a next word prediction model trained on a massive text corpus to extract dynamic text representations. These representations capture the evolving meaning of words based on context and are then combined with static embeddings like Word2Vec. A noteworthy approach is that the method incorporates an undirected graph model to capture contextual relationships between words. Three variations of the method are explored: ELMo-Like Baseline Dynamic, ARMA Graph Dynamic, and ARMA+ELMo Dynamic. Experiments utilizing deep learning models for sentiment analysis and disaster tweet classification demonstrate the effectiveness of the proposed approach.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Leveraging Dynamic Graph Word Embedding for Efficient Contextual Representations

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ryan E. Himes,
  • Hai-Anh Tran,
  • Truong X. Tran

摘要

Sentence structure consists of a complex structure of words and relationships between words, which can be hard to represent with only a sequential representation and makes it challenging to learn long-range dependencies. This research presents a novel dynamic word embedding method designed to improve text classification performance. The method leverages a next word prediction model trained on a massive text corpus to extract dynamic text representations. These representations capture the evolving meaning of words based on context and are then combined with static embeddings like Word2Vec. A noteworthy approach is that the method incorporates an undirected graph model to capture contextual relationships between words. Three variations of the method are explored: ELMo-Like Baseline Dynamic, ARMA Graph Dynamic, and ARMA+ELMo Dynamic. Experiments utilizing deep learning models for sentiment analysis and disaster tweet classification demonstrate the effectiveness of the proposed approach.