arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.12903cs.CLcs.AI
收藏

NoPPA:用于句子表示的非参数成对注意力随机游走模型

NoPPA: Non-Parametric Pairwise Attention Random Walk Model for Sentence Representation

University of Georgia(佐治亚大学);Tufts University(塔夫茨大学)

Xuansheng Wu, Zhiyi Zhao, Ninghao Liu

摘要:

我们提出了一种新的非参数/不可训练的语言模型,命名为非参数成对注意随机游走模型(NoPPA),生成句子嵌入只有预先训练的词嵌入和预先计数的词频。据我们所知,这项研究是第一次成功的尝试,打破了词袋假设的约束与非参数注意力机制。我们评估我们的方法对八个不同的下游分类任务。实验结果表明,NoPPA在每个数据集上都优于各种基于词袋的方法,并且平均而言,它提供了与最先进的非参数方法相当或更好的性能。此外,可视化支持NoPPA可以理解上下文主题,常见短语和单词因果关系。我们的模型可以在https://github.com/JacksonWuxs/NoPPA上找到。

英文摘要:

We propose a novel non-parametric/un-trainable language model, named Non-Parametric Pairwise Attention Random Walk Model (NoPPA), to generate sentence embedding only with pre-trained word embedding and pre-counted word frequency. To the best we know, this study is the first successful attempt to break the constraint on bag-of-words assumption with a non-parametric attention mechanism. We evaluate our method on eight different downstream classification tasks. The experiment results show that NoPPA outperforms all kinds of bag-of-words-based methods in each dataset and provides a comparable or better performance than the state-of-the-art non-parametric methods on average. Furthermore, visualization supports that NoPPA can understand contextual topics, common phrases, and word causalities. Our model is available at https://github.com/JacksonWuxs/NoPPA.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑