Cross-Lingual Induction for Deep Broad-Coverage Syntax: A Case Study on German Participles
نویسندگان
چکیده
This paper is a case study on cross-lingual induction of lexical resources for deep, broad-coverage syntactic analysis of German. We use a parallel corpus to induce a classifier for German participles which can predict their syntactic category. By means of this classifier, we induce a resource of adverbial participles from a huge monolingual corpus of German. We integrate the resource into a German LFG grammar and show that it improves parsing coverage while maintaining accuracy.
منابع مشابه
A Cross-Lingual Induction Technique for German Adverbial Participles
We provide a detailed comparison of strategies for implementing medium-tolow frequency phenomena such as German adverbial participles in a broadcoverage, rule-based parsing system. We show that allowing for general adverb conversion of participles in the German LFG grammar seriously affects its overall performance, due to increased spurious ambiguity. As a solution, we present a corpus-based cr...
متن کاملWhat about lexical semantics if syntax is the only generative component of the grammar ? A case study on word meaning in German
This paper explores the semantic consequences of the principle of containment embodied by the popular assumption that word formation is entirely syntactic and that there is no generative lexicon. According to the principle of containment, the analysis and structure of a given form must also be contained within the analysis of any structure derived from that form. The implications of the contain...
متن کاملSpotting Social Signals in Conversational Speech over IP: A Deep Learning Perspective
The automatic detection and classification of social signals is an important task, given the fundamental role nonverbal behavioral cues play in human communication. We present the first cross-lingual study on the detection of laughter and fillers in conversational and spontaneous speech collected ‘in the wild’ over IP (internet protocol). Further, this is the first comparison of LSTM and GRU ne...
متن کاملScaling up Automatic Cross-Lingual Semantic Role Annotation
Broad-coverage semantic annotations for training statistical learners are only available for a handful of languages. Previous approaches to cross-lingual transfer of semantic annotations have addressed this problem with encouraging results on a small scale. In this paper, we scale up previous efforts by using an automatic approach to semantic annotation that does not rely on a semantic ontology...
متن کاملLTG vs. ITG Coverage of Cross-Lingual Verb Frame Alternations
We show in an empirical study that not only did all cross-lingual alternations of verb frames across Chinese–English translations fall within the reordering capacity of Inversion Transduction Grammars, but more surprisingly, about 97% of the alternations were expressible by the far more restrictive Linear Transduction Grammars. Also, about 71% of the cross-lingual verb frame alternations turn o...
متن کامل