General-purpose ontologies (e.g. WordNet) are convenient, but they are not always scientifically valid. We draw on techniques from semantic class learning to improve the scientific validity of WordNet’s physics forces hyponym (IS-A) hierarchy for use in an intelligent tutoring system. We demonstrate the promise of a web-based approach which gathers web statistics used to relabel the forces as s...

We present a new approach to extraction of hypernyms based on projection learning and word embeddings. In contrast to classification-based approaches, projection-based methods require no candidate hyponym-hypernym pairs. While it is natural to use both positive and negative training examples in supervised relation extraction, the impact of negative examples on hypernym prediction was not studie...

This paper describes the TU system that participated in the Entrance Exam Subtask of NTCIR-9 RITE. The system consists of two phases: alignment and entailment relation recognition. In the alignment phase, the system aligns words in the two sentences by exploiting diverse lexical resources such as entailment information, hypernym-hyponym relations and synonyms. Based on the alignments and relati...

In this project we formulate a methodology for extracting definitional contexts from corpus of biomedicine in Spanish, in order to generate the following products: (i) a list of candidate terms, (ii) a list of candidates for definitions, and (iii) a taxonomy of biomedical terms relationships based on hyponym/hyperonym. Our methodology allows the creation of a system capable of extracting such c...

This paper explores the application of the semantic field theory in English vocabulary learning. It first investigates classifications of various semantic relations, including hyponym, antonymy, synonymy, etc. Then it illustrates with abundant examples how to employ each sense relation in learning vocabulary with the application of the semantic field theory. The study is of non-neglectable sign...

In English, denominal verbs incorporate in varying degrees the meaning of the root noun as part of the verb’s meaning. For example, one can box a present in a gift box but not in a paper bag, shelve a book on the mantelpiece but not on a spike. Other verbs such as land and warehouse exhibit bleaching to a much greater degree; for example, one can land a hydroplane on water, or warehouse parts i...

We analyzed the details of aWeb-derived distributional data of Japanese nominal terms with two aims. One aim is to examine if distributionally similar terms can be in fact equated with “semantically similar” terms, and if so to what extent. The other is to investigate into what kind of semantic relations constitute (strongly) distributionally similar terms. Our results show that over 85% of the...

We aim to learn hypernymy present in distributed word representations using a deep LSTM neural network. We hypothesize that the semantic information of hypernymy is distributed differently across the components of the hyponym and hypernym vectors for varying examples of hypernymy. We use an LSTM cell with a replacement gate to adjust the state of the network as different examples of hypernymy a...

Automatic indexing is one of the important technologies used for Textual Data Analysis applications. Standard document indexing techniques usually identify the most relevant keywords in the documents. This paper presents an alternative approach that aims at performing document indexing by associating concepts with the document to index instead of extracting keywords out of it. The concepts are ...