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 2006.00693cs.LGstat.ML
收藏

信息论指导下的解纠缠文本表示学习改进

Improving Disentangled Text Representation Learning with Information-Theoretic Guidance

Duke University(杜克大学);NEC Labs America(NEC美国实验室);Microsoft Dynamics 365 AI(微软Dynamics 365人工智能);Microsoft Research(微软研究院)

Pengyu Cheng, Martin Renqiang Min, Dinghan Shen, Christopher Malon, Yizhe Zhang, Yitong Li, Lawrence Carin

摘要:

学习自然语言的分解表示对于许多NLP任务是必不可少的,例如,条件文本生成、风格转换、个性化对话系统等。对于其它形式的数据,例如图像和视频,已经广泛地研究了类似的问题。然而,自然语言的离散性质使得文本表示的解开更具挑战性(例如,不能容易地实现对数据空间的操纵)。受信息论的启发,我们提出了一种新的方法,有效地体现了解开表示的文本,没有任何监督的语义。一个新的互信息上限推导和杠杆来衡量风格和内容之间的依赖性。通过最小化这个上界,所提出的方法将风格和内容嵌入到两个独立的低维空间中。两个有条件的文本生成和文本风格转移的实验表明,我们的解纠缠表示的内容和风格保存方面的高品质。

英文摘要:

Learning disentangled representations of natural language is essential for many NLP tasks, e.g., conditional text generation, style transfer, personalized dialogue systems, etc. Similar problems have been studied extensively for other forms of data, such as images and videos. However, the discrete nature of natural language makes the disentangling of textual representations more challenging (e.g., the manipulation over the data space cannot be easily achieved). Inspired by information theory, we propose a novel method that effectively manifests disentangled representations of text, without any supervision on semantics. A new mutual information upper bound is derived and leveraged to measure dependence between style and content. By minimizing this upper bound, the proposed method induces style and content embeddings into two independent low-dimensional spaces. Experiments on both conditional text generation and text-style transfer demonstrate the high quality of our disentangled representation in terms of content and style preservation.

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。

↑