Semantic Composition via Probabilistic Model Theory
Semantic composition remains an open problem for vector space models of semantics. In this paper, we explain how the probabilistic graphical model used in the framework of Functional Distributional Semantics can be interpreted as a probabilistic version of model theory. Building on this, we explain how various semantic phenomena can be recast in terms of conditional probabilities in the graphical model. This connection between formal semantics and machine learning is helpful in both directions: it gives us an explicit mechanism for modelling context-dependent meanings (a challenge for formal semantics), and also gives us well-motivated techniques for composing distributed representations (a challenge for distributional semantics). We present results on two datasets that go beyond word similarity, showing how these semantically-motivated techniques improve on the performance of vector models.
Code (0)
등록된 구현이 없습니다.
Tasks
modelSemantic CompositionWord SimilaritySimilar Papers 제목 키워드 기반
A probabilistic framework for analysing the compositionality of conceptual combinations
Conceptual combination performs a fundamental role in creating the broad range of compound phrases utilized in everyday language. This article provides a novel probabilistic framework for assessing whether the semantics …
PhilosophyFrom compositional semantics to Bayesian pragmatics via logical inference
Formal semantics in the Montagovian tradition provides precise meaning characterisations, but usually without a formal theory of the pragmatics of contextual parameters and their sensitivity to background knowledge. Mean…
World KnowledgeBayesian Classification and Inference in a Probabilistic Type Theory with Records
We propose a probabilistic account of semantic inference and classification formulated in terms of probabilistic type theory with records, building on Cooper et. al. (2014) and Cooper et. al. (2015). We suggest probabili…
ClassificationVocal Bursts Type PredictionExplaining a probabilistic prediction on the simplex with Shapley compositions
Originating in game theory, Shapley values are widely used for explaining a machine learning model's prediction by quantifying the contribution of each feature's value to the prediction. This requires a scalar prediction…
Binary ClassificationPredictionThe Bussgang Decomposition of Non-Linear Systems: Basic Theory and MIMO Extensions
Many of the systems that appear in various signal processing applications are non-linear, for example, due to hardware impairments such as non-linear amplifiers and finite-resolution quantization. The Bussgang decomposit…
MisconceptionsQuantization