Most word embedding models typically represent each word using a single vector, which makes these models indiscriminative for ubiquitous homonymy and polysemy. In order to enhance discriminativeness, we employ latent topic models to assign topics for each word in the text corpus, and learn topical word embeddings (TWE) based on both words and their topics. In this way, contextual word embedding...

An intensional logic with dynamic interpretation is presented in order to provide a formal semantics for sense extension, lexical ambiguity and metaphoricity. Intensionality is required in order to provide the right account of polysemy and homonymy. The dynamics are required in order to allow the interpretation of a sentence to impact the interpretation of subsequent sentences by adding any ext...

The terminology used in Biomedicine shows lexical peculiarities that have required the elaboration of terminological resources and information retrieval systems with specific functionalities. The main characteristics are the high rates of synonymy and homonymy, due to phenomena such as the proliferation of polysemic acronyms and their interaction with common language. Information retrieval syst...

One of the problems of e-Business is to find relevant documents for making correct decisions. The main problem of the Internet is the huge amount of documents that makes it difficult to find the relevant ones, hence the importance of the methods allowing for improving the quality of document retrieval. We discuss some linguistic problems of document retrieval on the Internet related to the foll...

A Cantonese Chinese transcription system to automatically convert stenograph code to Chinese characters is reported. The major challenge in developing such a system is the critical homocode problem because of homonymy. The statistical N-gram model is used to compute the best combination of characters. Supplemented with a 0.85 million character corpus of domain-specific training data and enhance...

Event-related potentials (ERPs) were used to investigate the time-course of meaning activation of different types of ambiguous words. Unbalanced homonymous ("pen"), balanced homonymous ("panel"), metaphorically polysemous ("lip"), and metonymically polysemous words ("rabbit") were used in a visual single-word priming delayed lexical decision task. The theoretical distinction between homonymy an...

Human languages are naturally ambiguous, which makes it difficult to automatically understand the semantics of text. Most vector space models (VSM) treat all occurrences of a word as the same and build a single vector to represent the meaning of a word, which fails to capture any ambiguity. We present sense-aware semantic analysis (SaSA), a multi-prototype VSM for word representation based on W...

This thesis will talk about ambiguity by classifying it into sound ambiguity and meaning ambiguity. In the first part, the author will discuss the theories in ambiguity namely the Q-and R-principle and IC-analysis which are the most basic and important in the analysis of ambiguity. In the following part, the author will analyze the sound ambiguity and meaning ambiguity in detail. Polysemy and h...

Full citations of animal specific or generic names ultimately derived from unpublished manuscripts should commemorate the work of the person who described the new species as well as the person who eventually validly published the name. We suggest that biologists should use the following authorships when citing these names: Terebella infundibulum Renier in Meneghini, 1847 (now used in the genus ...

Despite the structured nature of metadata associated with geospatial resources, the discovery functionality implemented by geoportals is primarily based on the syntactic matching of users’ search pattern against descriptive metadata, such as title, abstract, or keywords. As a consequence, the retrieval process is often hampered by linguistic issues related to multilingualism, semantic heterogen...