学位论文提案：我们是否在自然语言处理中丧失了文本多样性？
Thesis proposal: Are We Losing Textual Diversity to Natural Language Processing?
AI总结：
该论文以神经机器翻译为测试平台，探究自然语言处理算法的归纳偏置是否会损害非典型文本处理、降低生成文本多样性，分析其训练与解码层面的成因并提出优化方向。
摘要：
本论文提出，当前广泛使用的自然语言处理算法在其处理和生成的文本属性方面可能存在多种局限性。随着这些工具在快速发展中被广泛采用，我们必须追问这些局限性是什么，以及将此类工具更深层次融入我们日常生活可能带来的影响。\n 作为测试平台，我们选择了神经机器翻译（Neural Machine Translation，NMT）任务。尽管如此，我们的目标是获得具有普适性的洞见与成果，甚至能适用于当前的大语言模型（Large Language Models，LLMs）。我们探究NMT所使用的算法是否存在固有归纳偏置——这类偏置对大多数类型的输入有益，但可能会损害非典型文本的处理。为验证这一假设，我们基于文本的统计属性（如词级惊奇度的均匀性或节奏性），在多个尺度（句子、语篇、语言）上定义了一套量化文本多样性的度量指标。随后我们开展了一系列实验，研究与人工译者相比，NMT系统是否难以维持这类文本的多样性，进而可能降低这些系统生成语言的丰富度。\n 我们探寻这些局限性根植于训练目标和解码算法的潜在成因。我们的最终目标是开发替代方案，这类方案不会强制输出的统计属性分布趋于均匀，并且能够结合翻译任务固有的模糊性，实现更好的翻译全局规划。
英文摘要：
This thesis argues that the currently widely used Natural Language Processing algorithms possibly have various limitations related to the properties of the texts they handle and produce. With the wide adoption of these tools in rapid progress, we must ask what these limitations are and what are the possible implications of integrating such tools even more deeply into our daily lives. As a testbed, we have chosen the task of Neural Machine Translation (NMT). Nevertheless, we aim for general insights and outcomes, applicable even to current Large Language Models (LLMs). We ask whether the algorithms used in NMT have inherent inductive biases that are beneficial for most types of inputs but might harm the processing of untypical texts. To explore this hypothesis, we define a set of measures to quantify text diversity based on its statistical properties, like uniformity or rhythmicity of word-level surprisal, on multiple scales (sentence, discourse, language). We then conduct a series of experiments to investigate whether NMT systems struggle with maintaining the diversity of such texts, potentially reducing the richness of the language generated by these systems, compared to human translators. We search for potential causes of these limitations rooted in training objectives and decoding algorithms. Our ultimate goal is to develop alternatives that do not enforce uniformity in the distribution of statistical properties in the output and that allow for better global planning of the translation, taking into account the intrinsic ambiguity of the translation task.
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。
