Graph-based Clustering of Synonym Senses for German Particle Verbs
نویسندگان
چکیده
In this paper, we address the automatic induction of synonym paraphrases for the empirically challenging class of German particle verbs. Similarly to Cocos and Callison-Burch (2016), we incorporate a graph-based clustering approach for word sense discrimination into an existing paraphrase extraction system, (i) to improve the precision of synonym identification and ranking, and (ii) to enlarge the diversity of synonym senses. Our approach significantly improves over the standard system, but does not outperform an extended baseline integrating a simple distributional
منابع مشابه
Automatic Extraction of Synonyms for German Particle Verbs from Parallel Data with Distributional Similarity as a Re-Ranking Feature
We present a method for the extraction of synonyms for German particle verbs based on a word-aligned German-English parallel corpus: by translating the particle verb to a pivot, which is then translated back, a set of synonym candidates can be extracted and ranked according to the respective translation probabilities. In order to deal with separated particle verbs, we apply re-ordering rules to...
متن کاملRegular Meaning Shifts in German Particle Verbs: A Case Study
This paper provides a corpus-based study on German particle verbs. We hypothesize that there are regular mechanisms in meaning shifts of a base verb in combination with a particle that do not only apply to the individual verb, but across a semantically coherent set of verbs. For example, the syntactically similar base verbs brummen ‘hum’ and donnern ‘rumble’ both describe an irritating, displea...
متن کاملDetermining the Degree of Compositionality of German Particle Verbs by Clustering Approaches
This work determines the degree of compositionality of German particle verbs by two soft clustering approaches. We assume that the more compositional a particle verb is, the more often it appears in the same cluster with its base verb, after applying a probability threshold to establish cluster membership. As German particle verbs are difficult to approach automatically at the syntax-semantics ...
متن کاملExploring Soft-Clustering for German (Particle) Verbs across Frequency Ranges
In this paper we explore the role of verb frequencies and the number of clusters in soft-clustering approaches as a tool for automatic semantic classification. Relying on a large-scale setup including 4,871 base verb types and 3,173 complex verb types, and focusing on synonymy as a taskindependent goal in semantic classification, we demonstrate that low-frequency German verbs are clustered sign...
متن کاملSyntactic Transfer Patterns of German Particle Verbs and their Impact on Lexical Semantics
German particle verbs, like anblicken (to gaze at) combine a base verb (blicken) with a particle (an) to form a special kind of Multi Word Expression. Particle verbs may share the semantics of the base verb and the particle to a variable degree. However, while syntactic subcategorization frames tend to be good predictor for the semantics of verbs in general (verbs that are similar in meaning al...
متن کامل