Towards Lexical Chains for Knowledge-Graph-based Word Embeddings
Word vectors with varying dimensionalities and produced by different algorithms have been extensively used in NLP. The corpora that the algorithms are trained on can contain either natural language text (e.g. Wikipedia or newswire articles) or artificially-generated pseudo corpora due to natural data sparseness. We exploit Lexical Chain based templates over Knowledge Graph for generating pseudo-corpora with controlled linguistic value. These corpora are then used for learning word embeddings. A number of experiments have been conducted over the following test sets: WordSim353 Similarity, WordSim353 Relatedness and SimLex-999. The results show that, on the one hand, the incorporation of many-relation lexical chains improves results, but on the other hand, unrestricted-length chains remain difficult to handle with respect to their huge quantity.
Code (0)
등록된 구현이 없습니다.
Tasks
ArticlesLanguage ModelingLanguage ModellingLearning Word EmbeddingsWord EmbeddingsWord Sense DisambiguationSimilar Papers 제목 키워드 기반
Enhanced word embeddings using multi-semantic representation through lexical chains
The relationship between words in a sentence often tells us more about the underlying semantic content of a document than its actual words, individually. In this work, we propose two novel algorithms, called Flexible Lex…
Document ClassificationSentenceWord EmbeddingsLexical Chains meet Word Embeddings in Document-level Statistical Machine Translation
Currently under review for EMNLP 2017 The phrase-based Statistical Machine Translation (SMT) approach deals with sentences in isolation, making it difficult to consider discourse context in translation. This poses a chal…
DecoderDocument SummarizationInformation RetrievalMachine Translation+4Solving Hard Analogy Questions with Relation Embedding Chains
Modelling how concepts are related is a central topic in Lexical Semantics. A common strategy is to rely on knowledge graphs (KGs) such as ConceptNet, and to model the relation between two concepts as a set of paths. How…
Knowledge GraphsLanguage ModelingLanguage ModellingRelationSynthetic, yet natural: Properties of WordNet random walk corpora and the impact of rare words on embedding performance
Creating word embeddings that reflect semantic relationships encoded in lexical knowledge resources is an open challenge. One approach is to use a random walk over a knowledge graph to generate a pseudo-corpus and use th…
Word EmbeddingsWord SimilaritySemantic Feature Structure Extraction From Documents Based on Extended Lexical Chains
The meaning of a sentence in a document is more easily determined if its constituent words exhibit cohesion with respect to their individual semantics. This paper explores the degree of cohesion among a document’s words …
RetrievalSentence