Factoring Ambiguity out of the Prediction of Compositionality for German Multi-Word Expressions
نویسندگان
چکیده
Multi-Word Expressions Mean Ratings Modifier Head Ahorn|blatt ‘maple leaf’ maple leaf 5.64 5.71 Blatt|salat ‘green salad’ leaf salad 3.56 5.68 See|zunge ‘sole’ sea tongue 3.57 3.27 Löwen|zahn ‘dandelion’ lion tooth 2.10 2.23 Fliegen|pilz ‘toadstool’ fly/bow tie mushroom 1.93 6.55 Fleisch|wolf ‘meat chopper’ meat wolf 6.00 1.90 an|leuchten ‘illuminate’ anPRT illuminate – 5.95 auf|horchen ‘listen attentively’ aufPRT listen – 4.55 aus|reizen ‘exhaust’ ausPRT provoke – 3.62 ein|fallen ‘remember/invade’ einPRT fall – 2.54 an|stiften ‘instigate’ anPRT create – 1.80
منابع مشابه
GhoSt-PV: A Representative Gold Standard of German Particle Verbs
German particle verbs represent a frequent type of multi-word-expression that forms a highly productive paradigm in the lexicon. Similarly to other multi-word expressions, particle verbs exhibit various levels of compositionality. One of the major obstacles for the study of compositionality is the lack of representative gold standards of human ratings. In order to address this bottleneck, this ...
متن کاملUsing Distributional Similarity of Multi-way Translations to Predict Multiword Expression Compositionality
We predict the compositionality of multiword expressions using distributional similarity between each component word and the overall expression, based on translations into multiple languages. We evaluate the method over English noun compounds, English verb particle constructions and German noun compounds. We show that the estimation of compositionality is improved when using translations into m...
متن کاملOptimizing a Distributional Semantic Model for the Prediction of German Particle Verb Compositionality
In the work presented here we assess the degree of compositionality of German Particle Verbs with a Distributional Semantics Model which only relies on word window information and has no access to syntactic information as such. Our method only takes the lexical distributional distance between the Particle Verb to its Base Verb as a predictor for compositionality. We show that the ranking of dis...
متن کاملA Word Embedding Approach to Predicting the Compositionality of Multiword Expressions
This paper presents the first attempt to use word embeddings to predict the compositionality of multiword expressions. We consider both singleand multi-prototype word embeddings. Experimental results show that, in combination with a back-off method based on string similarity, word embeddings outperform a method using count-based distributional similarity. Our best results are competitive with, ...
متن کاملDetecting Compositionality of Multi-Word Expressions using Nearest Neighbours in Vector Space Models
We present a novel unsupervised approach to detecting the compositionality of multi-word expressions. We compute the compositionality of a phrase through substituting the constituent words with their “neighbours” in a semantic vector space and averaging over the distance between the original phrase and the substituted neighbour phrases. Several methods of obtaining neighbours are presented. The...
متن کامل