refer to things that can not be seen, heard, felt, smelled, or tasted as opposed to concrete words. Among other applications, the degree of abstractness has been shown to be a useful information for metaphor detection. Our contribution to this topic are as follows: i) we compare supervised techniques to learn and extend abstractness ratings for huge vocabularies ii) we learn and investigate norms for multi-word units by propagating abstractness to verb-noun pairs which lead to better metaphor detection, iii) we overcome the limitation of learning a single rating per word and show that multisense abstractness ratings are potentially useful for metaphor detection. Finally, with this paper we publish automatically created abstractness norms for 3 million English words and multi-words as well as automatically created sense-specific abstractness ratings.
We present a novel neural model HyperVec to learn hierarchical embeddings for hypernymy detection and directionality. While previous embeddings have shown limitations on prototypical hypernyms, HyperVec represents an unsupervised measure where embeddings are learned in a specific order and capture the hypernym-hyponym distributional hierarchy. Moreover, our model is able to generalize over unseen hypernymy pairs, when using only small sets of training data, and by mapping to other languages. Results on benchmark datasets show that HyperVec outperforms both state-of-theart unsupervised measures and embedding models on hypernymy detection and directionality, and on predicting graded lexical entailment.
This paper provides a binary, token-based classification of German particle verbs (PVs) into literal vs. non-literal usage. A random forest improving standard features (e.g., bagof-words; affective ratings) with PV-specific information and abstraction over common nouns significantly outperforms the majority baseline. In addition, PV-specific classification experiments demonstrate the role of shared particle semantics and semantically related base verbs in PV meaning shifts.
Our submission to the WASSA-2017 shared task on the prediction of emotion intensity in tweets is a supervised learning method with extended lexicons of affective norms. We combine three main information sources in a random forrest regressor, namely (1), manually created resources, (2) automatically extended lexicons, and (3) the output of a neural network (CNN-LSTM) for sentence regression. All three feature sets perform similarly well in isolation (≈ .67 macro average Pearson correlation). The combination achieves .72 on the official test set (ranked 2nd out of 22 participants). Our analysis reveals that performance is increased by providing cross-emotional intensity predictions. The automatic extension of lexicon features benefit from domain specific embeddings. Complementary ratings for affective norms increase the impact of lexicon features. Our resources (ratings for 1.6 million twitter specific words) and our implementation is publicly available at http: //www.ims.uni-stuttgart.de/ data/ims_emoint.
Abstract. This paper implements a simple vector space model relying on lexico-syntactic patterns to distinguish between the paradigmatic relations synonymy, antonymy and hypernymy. Our study is performed across word classes, and models the lexical relations between German nouns, verbs and adjectives. Applying nearest-centroid classification to the relation vectors, we achieve a precision of 59.80%, which significantly outperforms the majority baseline (χ 2 , p<0.05). The best results rely on large-scale, noisy patterns, without significant improvements from various pattern generalisations and reliability filters. Analysing the classification shows that (i) antonym/synonym distinction is performed significantly better than synonym/hypernym distinction, and (ii) that paradigmatic relations between verbs are more difficult to predict than paradigmatic relations between nouns or adjectives.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.