A Structured Vector Space Model for Word Meaning in Context
نویسندگان
چکیده
We address the task of computing vector space representations for the meaning of word occurrences, which can vary widely according to context. This task is a crucial step towards a robust, vector-based compositional account of sentence meaning. We argue that existing models for this task do not take syntactic structure sufficiently into account. We present a novel structured vector space model that addresses these issues by incorporating the selectional preferences for words’ argument positions. This makes it possible to integrate syntax into the computation of word meaning in context. In addition, the model performs at and above the state of the art for modeling the contextual adequacy of paraphrases.
منابع مشابه
Paraphrase Assessment in Structured Vector Space: Exploring Parameters and Datasets
The appropriateness of paraphrases for words depends often on context: “grab” can replace “catch” in “catch a ball”, but not in “catch a cold”. Structured Vector Space (SVS) (Erk and Padó, 2008) is a model that computes word meaning in context in order to assess the appropriateness of such paraphrases. This paper investigates “best-practice” parameter settings for SVS, and it presents a method ...
متن کاملMulti-Prototype Vector-Space Models of Word Meaning
Current vector-space models of lexical semantics create a single “prototype” vector to represent the meaning of a word. However, due to lexical ambiguity, encoding word meaning with a single vector is problematic. This paper presents a method that uses clustering to produce multiple “sense-specific” vectors for each word. This approach provides a context-dependent vector representation of word ...
متن کاملتحقق مفهوم قرآنی «قسط» در فضای شهری
Studies of urban space is expanding but what is important is explanation of it in national and local scales, according to the context of society and culture. The main book of Islam, which is associated with Iranian's culture, is "Quran". Therefore, the use of theoretical concepts of indigenous issues on the ballot in the Quran can be helpful in urban management. One of the aspects of the soc...
متن کاملLatent Vector Weighting for Word Meaning in Context
This paper presents a novel method for the computation of word meaning in context. We make use of a factorization model in which words, together with their window-based context words and their dependency relations, are linked to latent dimensions. The factorization model allows us to determine which dimensions are important for a particular context, and adapt the dependency-based feature vector...
متن کاملEncoding syntactic dependencies by vector permutation
Distributional approaches are based on a simple hypothesis: the meaning of a word can be inferred from its usage. The application of that idea to the vector space model makes possible the construction of a WordSpace in which words are represented by mathematical points in a geometric space. Similar words are represented close in this space and the definition of “word usage” depends on the defin...
متن کامل