Composition of Word Representations Improves Semantic Role Labelling
Composition of Word Representations Improves Semantic Role Labelling
复制标题
DOI：
10.3115/v1/d14-1045
复制
发表时间：
2014-10
期刊：
影响因子：
--
通讯作者：
Michael Roth;K. Woodsend
中科院分区：
文献类型：
--
作者：
Michael Roth;K. Woodsend
最先进的语义角色标注系统需要大量的标注语料库才能达到完全的性能。不幸的是，这样的语料库制作成本很高，而且往往不能很好地跨域推广。即使在领域中，当句法信息不能提供足够的线索时，也经常会出现错误。在本文中，我们通过使用从未标记数据中收集的分布词表示来缓解这两个问题。虽然谓词和论元的直截了当的单词表示法提高了性能，但我们证明了通过组合对谓词和论元之间的交互进行建模并捕获完整的论元跨度的表示法，可以进一步获得收益。
State-of-the-art semantic role labelling systems require large annotated corpora to achieve full performance. Unfortunately, such corpora are expensive to produce and often do not generalize well across domains. Even in domain, errors are often made where syntactic information does not provide sufficient cues. In this paper, we mitigate both of these problems by employing distributional word representations gathered from unlabelled data. While straight-forward word representations of predicates and arguments improve performance, we show that further gains are achieved by composing representations that model the interaction between predicate and argument, and capture full argument spans.