ReMLAV: Relational Machine Learning for Argument Validation

我们关注论点验证，这是论证机器的一个重要方面，并将问题形式化为我们所称的论点链接的验证：一个论点中的两个连续句子。当且仅当这两个句子形成论元的有效部分时，论元链接才被归类为有效，例如，因为第一句蕴含或逻辑上暗示第二句。我们提出了一种新的论元链接验证方法，该方法基于三个方面的工作：(I)关系机器学习，(Ii)嵌入和(Iii)子空间分析。(I)关系机器学习涉及对象之间的关系模型；我们在这里应用它，将句子建模为对象，将关系建模为(在更细的粒度上)有效性或(在更细的粒度上)作为蕴涵、因果、矛盾等。(Ii)嵌入是语言对象的高维表示，支持强大的模型，很好地概括到新的数据。我们在这里将它们应用于在论点中表示句子。(3)嵌入存在难以检查和理解的缺点。但这一能力对于人类可用的论证机器至关重要。我们建立了嵌入空间的子空间模型，以支持人类理解句子嵌入空间和论证机器决策。

We focus on argument validation, one important aspect of argumentation machines, and formalize the problem as the validation of what we call an argument link: two consecutive sentences in an argument. An argument link is classified as valid if and only if the two sentences form a valid part of an argument, e.g., because the first entails or logically implies the second. We propose a new argument link validation method that is based on three bodies of prior work: (i) relational machine learning, (ii) embeddings and(iii) subspace analysis. (i) Relational machine learning is concerned with models of relations between objects; we apply it here by modeling sentences as objects and relations as (in)validity or (on a finer grain) as entailment, causality, contradiction etc. (ii) Embeddings are high-dimensional representations of linguistic objects and support powerful models that generalize well to new data. We apply them here to representing sentences in arguments. (iii) Embeddings have the drawback that they are difficult to inspect andunderstand. But this ability is critical for argumentation machines that are usable by humans. We develop subspace models of the embedding space that support humans in understanding sentence embedding spaces and argumentation machine decisions.