Both -ity and -ness are frequent and productive suffixes in English that fulfill the same core function: turning adjectives into nouns that denote the state or quality of whatever the adjective denotes. This well-known affix rivalry raises two core questions: 1. What determines the choice between -ity and -ness for a given base word? 2. Are the two affixes synonymous? For the first question, previous work has focused on morphological and phonological properties of the bases, but not their semantics. For question 2, the literature fails to give a convincing answer, with some studies, faced with doublets like ethnicity/ethnicness, arguing for a semantic difference, but most assuming synonymy. Using pretrained distributional vectors, I show empirically first that the semantics of the bases plays a major role in affix selection and second that the two affixes induce similar meaning shifts.

This paper presents a cross-language study of lexical semantics within the framework of distributional semantics. We used a wide range of predefined semantic categories in Mandarin and English and compared the clusterings of these categories using FastText word embeddings. Three techniques of dimensionality reduction were applied to mapping 300-dimensional FastText vectors into two-dimensional planes: multidimensional scaling, principal components analysis, and t-distributed stochastic neighbor embedding. The results show that t-SNE provides the clearest clustering of semantic categories, improving markedly on PCA and MDS. In both languages, we observed similar differentiation between verbs, adjectives, and nouns as well as between concrete and abstract words. In addition, the methods applied in this study, especially Procrustes analysis, make it possible to trace subtle differences in the structure of the semantic lexicons of Mandarin and English.

Modelling semantic similarity plays a fundamental role in lexical semantic applications. A natural way of calculating semantic similarity is to access handcrafted semantic networks, but similarity prediction can also be anticipated in a distributional vector space. Similarity calculation continues to be a challenging task, even with the latest breakthroughs in deep neural language models. We first examined popular methodologies in measuring taxonomic similarity, including edge-counting that solely employs semantic relations in a taxonomy, as well as the complex methods that estimate concept specificity. We further extrapolated three weighting factors in modelling taxonomic similarity. To study the distinct mechanisms between taxonomic and distributional similarity measures, we ran head-to-head comparisons of each measure with human similarity judgements from the perspectives of word frequency, polysemy degree and similarity intensity. Our findings suggest that without fine-tuning the uniform distance, taxonomic similarity measures can depend on the shortest path length as a prime factor to predict semantic similarity; in contrast to distributional semantics, edge-counting is free from sense distribution bias in use and can measure word similarity both literally and metaphorically; the synergy of retrofitting neural embeddings with concept relations in similarity prediction may indicate a new trend to leverage knowledge bases on transfer learning. It appears that a large gap still exists on computing semantic similarity among different ranges of word frequency, polysemous degree and similarity intensity.

We study regional similarities and differences in language use on an anonymous mobile chat application in the German-speaking area. We use a neural network on 2.3 million online conversations to automatically learn representations of words and cities. These linguistic-use-based representations capture regional distinctions in a high-dimensional vector space that can be clustered and visualized to discover patterns in the data. We find that the resulting regional patterns are closely linked to the traditional division of German dialects, even though most of the conversations are written in standard German. The resulting maps correspond to traditional dialect divisions and language-external spatial structures, with a few notable exceptions that can be explained through external factors.

Our method also facilitates two qualitative analyses, allowing us to discover geographically-pertinent words for various regional levels, as well as creating regional group-specific style profiles based on various linguistic resources. The results of our study strongly suggest the existence of region-specific patterns of language use (“digital regiolects”) representing distinctive strategies of linguistic stylization in relation to linguistic resources and topics. As a methodological contribution, we show how linguistic theory can drive the application and direction of neural network-based representation learning, and how their judicious application provides the basis for qualitative analysis of large-scale data collections.

Most compositional distributional semantic models represent sentence meaning with a single vector. In this paper, we propose a structured distributional model (SDM) that combines word embeddings with formal semantics and is based on the assumption that sentences represent events and situations. The semantic representation of a sentence is a formal structure derived from discourse representation theory and containing distributional vectors. This structure is dynamically and incrementally built by integrating knowledge about events and their typical participants, as they are activated by lexical items. Event knowledge is modelled as a graph extracted from parsed corpora and encoding roles and relationships between participants that are represented as distributional vectors. SDM is grounded on extensive psycholinguistic research showing that generalized knowledge about events stored in semantic memory plays a key role in sentence comprehension.We evaluate SDMon two recently introduced compositionality data sets, and our results show that combining a simple compositionalmodel with event knowledge constantly improves performances, even with dif ferent types of word embeddings.

Over the last two decades, determining the similarity between words as well as between their meanings, that is, word senses, has been proven to be of vital importance in the field of Natural Language Processing. This paper provides the reader with an introduction to the tasks of computing word and sense similarity. These consist in computing the degree of semantic likeness between words and senses, respectively. First, we distinguish between two major approaches: the knowledge-based approaches and the distributional approaches. Second, we detail the representations and measures employed for computing similarity. We then illustrate the evaluation settings available in the literature and, finally, discuss suggestions for future research.