In this paper we present an approach to train subatom embeddings for verbs. For each verb we learn not just one embedding, but several. One for the verb itself and embeddings for each grammatical role of this verb. For example, for the verb ‘to give’ we learn four embeddings: one for the lemma ‘give’, one for the subject, one for the direct object and one for the indirect object of it. We are e...

Martín Mingorance’s Functional-Lexematic Model (FLM) and Mel’c•uk’s Meaning Text Theory (MTT) are two complementary models of lexical description, which can also be applied to the description of terminological information. The FLM is compatible with general terminology theory because it envisions a lexicon structured onomasiologically in terms of areas of meaning or lexical domains. The MTT is ...

Recent studies of distributional semantic models have set up a competition between word embeddings obtained from predictive neural networks and word vectors obtained from count-based models. This paper is an attempt to reveal the underlying contribution of additional training data and post-processing steps on each type of model in word similarity and relatedness inference tasks. We do so by des...

This paper summarizes FBK-irst participation at the lexical substitution task of the SEMEVAL competition. We submitted two different systems, both exploiting synonym lists extracted from dictionaries. For each word to be substituted, the systems rank the associated synonym list according to a similarity metric based on Latent Semantic Analysis and to the occurrences in the Web 1T 5-gram corpus,...

Most methods used in knowledge organization systems (KOS) organize knowledge in form of concepts and the relations between them, though the level of differentiating relations varies. Major knowledge representation methods make some of the relations explicit, but they use only a small number of paradigmatic semantic relations so far. This approach is somewhat contrary to the detailed and highly-...

This study explores literature reading and reception of narrative texts among Swedish middle school students. Through a written assignment think-aloud protocol, students’ comprehension interpretation are investigated. The shows that students tend to focus mainly on the plot. main hindrance is at lexical level, but cultural aspects, such as general knowledge surrounding world, also crucial. have...

This research aims to reveal and describe the structure of Gerak Silek Gelombang Sanggar Tunas Harapan Nagari Aua Kuniang Pasaman Barat. type is qualitative using content analysis methods. The data uses primary secondary data. main instrument in this study was researcher himself assisted with supporting instruments such as stationery, camera flash drive. Data collection techniques are done by m...

WordNet and FrameNet are widely used lexical resources, but they are very different from each other and are often used in completely different ways in NLP. In a case study in which a short passage is annotated in both frameworks, we show how the synsets and definitions of WordNet and the syntagmatic information from FrameNet can complement each other, forming a more complete representation of t...