Edinburgh Research Explorer Using automatically labelled examples to classify rhetorical relations: an assessment
Edinburgh Research Explorer Using automatically labelled examples to classify rhetorical relations: an assessment
复制标题
DOI：
--
复制
发表时间：
--
期刊：
影响因子：
--
通讯作者：
R. Carolinesporlede
中科院分区：
文献类型：
--
作者：
R. Carolinesporlede
能够识别哪些修辞关系（例如，对比或解释）保持对于许多自然语言处理应用是重要的。使用机器学习来获得可以区分不同关系的分类器通常取决于手动标记的训练数据的可用性，这是非常耗时的。然而，修辞关系有时是词汇标记的，即，由话语标记发出信号（例如，因为，但是，因此等等），并且已经提出（Marcu和Echiffel，2002），在某些示例中这些线索的存在可以被利用来用对应关系自动地标记它们。然后移除话语标记，并使用自动标记的数据来训练分类器，即使不存在话语标记（基于其他语言线索，如单词共现）也能确定关系。在本文中，我们实证研究如何可行的这种方法是。特别是，我们测试自动标记的词汇标记的例子是否真的适合用于分类器的训练材料，然后应用于未标记的例子。我们的研究结果表明，在这种类型的数据上进行训练可能不是一个很好的策略，因为以这种方式训练的模型似乎不能很好地推广到未标记的数据。此外，我们发现一些证据表明，这种行为在很大程度上与所使用的分类器无关，似乎存在于数据本身（例如
Being able to identify which rhetorical relations (e.g., contrast or explanation ) hold between spans of text is important for many natural language processing applications. Using machine learning to obtain a classifier which can distinguish between different relations typically depends on the availability of manually labelled training data, which is very time-consuming to create. However, rhetorical relations are sometimes lexically marked, i.e., signalled by discourse markers (e.g., because , but , consequently etc.), and it has been suggested (Marcu and Echihabi, 2002) that the presence of these cues in some examples can be exploited to label them automatically with the corresponding relation. The discourse markers are then removed and the automatically labelled data are used to train a classifier to determine relations even when no discourse marker is present (based on other linguistic cues such as word co-occurrences). In this paper, we investigate empirically how feasible this approach is. In particular, we test whether automatically labelled, lexically marked examples are really suitable training material for classifiers that are then applied to unmarked examples. Our results suggest that training on this type of data may not be such a good strategy, as models trained in this way do not seem to generalise very well to unmarked data. Furthermore, we found some evidence that this behaviour is largely independent of the classifiers used and seems to lie in the data itself (e