Motivated by cognitive lexical models, network-based distributional semantic models (DSMs) were proposed in [Iosif and Potamianos (2013)] and were shown to achieve state-of-the-art performance on semantic similarity tasks. Based on evidence for cognitive organization of concepts based on degree of concreteness, we investigate the performance and organization of network DSMs for abstract vs. con...

Text similarity, as an important basis for scoring subjective items in the examination, directly determines examination results of candidates and work efficiency teachers. Therefore, this paper first introduces theoretical text similarity computing compares different calculation methods. Then, text-similarity algorithm is designed, where by conceptualizing terms, methods based on corpus knowled...

Modern paraphrase research would benefit from large corpora with detailed annotations. However, currently these corpora are still thin on the ground. In this paper, we describe the development of such a corpus for Dutch, which takes the form of a parallel monolingual treebank consisting of over 2 million tokens and covering various text genres, including both parallel and comparable text. This ...

We present an empirical study on the use of semantic information for Concept Segmentation and Labeling (CSL), which is an important step for semantic parsing. We represent the alternative analyses output by a state-of-the-art CSL parser with tree structures, which we rerank with a classifier trained on two types of semantic tree kernels: one processing structures built with words, concepts and ...

We present a matrix factorization model for learning cross-lingual representations for sentences. Using sentence-aligned corpora, the proposed model learns distributed representations by factoring the given data into language-dependent factors and one shared factor. As a result, input sentences from both languages can be mapped into fixed-length vectors and then compared directly using the cosi...

As text sources are getting broader, measuring text similarity is becoming more compelling. Automatic text classification, search engines and auto answering systems are samples of applications that rely on text similarity. Learning management systems (LMS) are becoming more important since electronic media is getting more publicly available. As LMS continuously needs content enrichment and the ...