Neural Semantic Role Labeling with Dependency Path Embeddings

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 1192–1202, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics Neural Semantic Role Labeling with Dependency Path Embeddings Michael Roth and Mirella Lapata School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB {mroth,mlap}@inf.ed.ac.uk Abstract This paper introduces a novel model for semantic role labeling that makes use of neural sequence modeling techniques. Our approach is motivated by the obser- vation that complex syntactic structures and related phenomena, such as nested subordinations and nominal predicates, are not handled well by existing models. Our model treats such instances as sub- sequences of lexicalized dependency paths and learns suitable embedding representa- tions. We experimentally demonstrate that such embeddings can improve results over previous state-of-the-art semantic role la- belers, and showcase qualitative improve- ments obtained by our method. 1 Introduction The goal of semantic role labeling (SRL) is to identify and label the arguments of semantic predi- cates in a sentence according to a set of predefined relations (e.g., “who” did “what” to “whom”). Se- mantic roles provide a layer of abstraction be- yond syntactic dependency relations, such as sub- ject and object, in that the provided labels are in- sensitive to syntactic alternations and can also be applied to nominal predicates. Previous work has shown that semantic roles are useful for a wide range of natural language processing tasks, with recent applications including statistical machine translation (Aziz et al., 2011; Xiong et al., 2012), plagiarism detection (Osman et al., 2012; Paul and Jamal, 2015), and multi-document abstractive summarization (Khan et al., 2015). The task of semantic role labeling (SRL) was pioneered by Gildea and Jurafsky (2002). In System Analysis mate-tools *He had [troubleA0] raising [fundsA1]. mateplus *He had [troubleA0] raising [fundsA1]. TensorSRL *He had trouble raising [fundsA1]. easySRL *He had trouble raising [fundsA1]. This work [HeA0] had trouble raising [fundsA1]. Table 1: Outputs of SRL systems for the sentence He had trouble raising funds. Arguments of raise are shown with predicted roles as defined in Prop- Bank (A0: getter of money; A1: money). Asterisks mark flawed analyses that miss the argument He. their work, features based on syntactic constituent trees were identified as most valuable for labeling predicate-argument relationships. Later work con- firmed the importance of syntactic parse features (Pradhan et al., 2005; Punyakanok et al., 2008) and found that dependency parse trees provide a better form of representation to assign role labels to arguments (Johansson and Nugues, 2008). Most semantic role labeling approaches to date rely heavily on lexical and syntactic indicator fea- tures. Through the availability of large annotated resources, such as PropBank (Palmer et al., 2005), statistical models based on such features achieve high accuracy. However, results often fall short when the input to be labeled involves instances of linguistic phenomena that are relevant for the la- beling decision but appear infrequently at training time. Examples include control and raising verbs, nested conjunctions or other recursive structures, as well as rare nominal predicates. …

Content truncated to 500 words