arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.04438cs.CLcs.AI
收藏

TexIm FAST:基于Transformer的文本到图像表示用于语义相似度评估

TexIm FAST: Text-to-Image Representation for Semantic Similarity Evaluation using Transformers

A. K. Choudhury School of IT(A.K.乔杜里信息技术学院);University of Calcutta(加尔各答大学);Bangabasi Morning College(班加巴希晨学院)

Wazib Ansar, Saptarsi Goswami, Amlan Chakrabarti

AI总结:

本文提出TexIm FAST方法,利用自监督VAE和Transformer将变长文本转换为固定长度图像表示,在语义相似度任务中减少75%以上内存占用并提升6%准确率。

摘要:

自然语言处理(NLP)的主要目标之一是从文本中生成有意义的表示。提高表示的信息量导致了维度和内存占用的巨大增长,进而产生级联效应,通过增加下游模型的参数来放大其复杂性。现有技术无法应用于文本到图像等跨模态应用。为了改善这些问题,本文提出了一种新颖的文本到图像方法TexIm FAST,该方法通过自监督变分自编码器(VAE)生成固定长度表示,并应用Transformer进行语义评估。图像化表示允许在不直接推理文本的情况下进行推断,同时保留语言细节,并且在跨模态应用中具有强大能力。TexIm FAST处理变长序列并生成固定长度表示,内存占用减少超过75%。它通过减少参数来提高下游任务模型的效率。本文在MSRPC、CNN/Daily Mail和XSum数据集上针对语义文本相似性(STS)任务对TexIm FAST的有效性进行了广泛分析。结果表明,与基线相比准确率提高了6%,并展示了其在比较不同长度序列(如文本与其摘要)方面的卓越能力。

英文摘要:

One of the principal objectives of Natural Language Processing (NLP) is to generate meaningful representations from text. Improving the informativeness of the representations has led to a tremendous rise in the dimensionality and the memory footprint. It leads to a cascading effect amplifying the complexity of the downstream model by increasing its parameters. The available techniques cannot be applied to cross-modal applications such as text-to-image. To ameliorate these issues, a novel Text-to-Image methodology for generating fixed-length representations through a self-supervised Variational Auto-Encoder (VAE) for semantic evaluation applying transformers (TexIm FAST) has been proposed in this paper. The pictorial representations allow oblivious inference while retaining the linguistic intricacies, and are potent in cross-modal applications. TexIm FAST deals with variable-length sequences and generates fixed-length representations with over 75% reduced memory footprint. It enhances the efficiency of the models for downstream tasks by reducing its parameters. The efficacy of TexIm FAST has been extensively analyzed for the task of Semantic Textual Similarity (STS) upon the MSRPC, CNN/ Daily Mail, and XSum data-sets. The results demonstrate 6% improvement in accuracy compared to the baseline and showcase its exceptional ability to compare disparate length sequences such as a text with its summary.

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。

↑