Semantic Coherence Facilitates Distributional Learning [PDF]
AbstractComputational models have shown that purely statistical knowledge about words’ linguistic contexts is sufficient to learn many properties of words, including syntactic and semantic category. For example, models can infer that “postman” and “mailman” are semantically similar because they have quantitatively similar patterns of association with ...
Long, Ouyang +2 more
openaire +2 more sources
Vector spaces for historical linguistics : using distributional semantics to study syntactic productivity in diachrony [PDF]
This paper describes an application of dis- tributional semantics to the study of syn- tactic productivity in diachrony, i.e., the property of grammatical constructions to attract new lexical items over time.
Perek, Florent
core +1 more source
Modelling brain representations of abstract concepts.
conceptual representations are critical for human cognition. Despite their importance, key properties of these representations remain poorly understood. Here, we used computational models of distributional semantics to predict multivariate fMRI activity ...
Daniel Kaiser +2 more
doaj +1 more source
Using Sparse Semantic Embeddings Learned from Multimodal Text and Image Data to Model Human Conceptual Knowledge [PDF]
Distributional models provide a convenient way to model semantics using dense embedding spaces derived from unsupervised learning algorithms. However, the dimensions of dense embedding spaces are not designed to resemble human semantic knowledge ...
Derby, Steven +3 more
core +2 more sources
Gaussianity and typicality in matrix distributional semantics [PDF]
Constructions in type-driven compositional distributional semantics associate large collections of matrices of size $D$ to linguistic corpora. We develop the proposal of analysing the statistical characteristics of this data in the framework of ...
S. Ramgoolam, M. Sadrzadeh, Lewis Sword
semanticscholar +1 more source
Distributional Semantics Meets Multi-Label Learning
We present a label embedding based approach to large-scale multi-label learning, drawing inspiration from ideas rooted in distributional semantics, specifically the Skip Gram Negative Sampling (SGNS) approach, widely used to learn word embeddings ...
Vivek Gupta +5 more
semanticscholar +1 more source
Disentangling modal meanings with distributional semantics
This article investigates the collocational behavior of English modal auxiliaries such as may and might with the aim of finding corpus-based measures that distinguish between different modal expressions and that allow insights into why speakers may ...
M. Hilpert, S. Flach
semanticscholar +1 more source
Linked Disambiguated Distributional Semantic Networks [PDF]
We present a new hybrid lexical knowledge base that combines the contextual information of distributional models with the conciseness and precision of manually constructed lexical networks. The computation of our count-based distributional model includes the induction of word senses for single-word and multi-word terms, the disambiguation of word ...
Faralli S. +3 more
openaire +2 more sources
Refining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification
Several unsupervised methods for hypernym detection have been investigated in distributional semantics. Here we present a new approach based on a smoothed version of the distributional inclusion hypothesis.
Ludovica Pannitto +2 more
doaj +1 more source
Towards Compositional Distributional Discourse Analysis [PDF]
Categorical compositional distributional semantics provide a method to derive the meaning of a sentence from the meaning of its individual words: the grammatical reduction of a sentence automatically induces a linear map for composing the word vectors ...
Bob Coecke +3 more
doaj +1 more source

