Composition in Distributional Models of Semantics

By Jeff Mitchell, Mirella Lapata. 2010

1,033 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank (2013, background): “Because they cannot capture the meaning of longer phrases properly, compositionality in semantic vector spaces has recently received a lot of attention (Mitchell and Lapata, 2010; Socher et al., 2010; Zanzotto et al., 2010; Yessenalina and Cardie, 2011; Socher et al., 2012; Grefenstette et al., 2013”
A Convolutional Neural Network for Modelling Sentences (2014, background): “In some cases, composition is defined by algebraic operations over word meaning vectors to produce sentence meaning vectors (Erk and Padó, 2008; Mitchell and Lapata, 2008; Mitchell and Lapata, 2010; Turney, 2012; Erk, 2012; Clarke, 2012).”
Grounded Compositional Semantics for Finding and Describing Images with Sentences (2014, methodology): “For instance, (Mitchell and Lapata, 2010) use twoword phrases and analyze similarities computed by vector addition, multiplication and others.”
From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions (2014, methodology): “Distributional word vectors can also be used to define the compositional similarity of longer strings (Mitchell and Lapata, 2010).”
A SICK cure for the evaluation of compositional distributional semantic models (2014, background): “…DSMs, or CDSMs) have been proposed, with the purpose of representing the meaning of phrases and sentences by composing the distributional representations of the words they contain (Mitchell and Lapata, 2010; Baroni and Zamparelli, 2010; Grefenstette and Sadrzadeh, 2011; Socher et al., 2012).”
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks (2015, background): “Following this success, there has been substantial interest in the area of learning distributed phrase and sentence representations (Mitchell and Lapata, 2010; Yessenalina and Cardie, 2011; Grefenstette et al., 2013; Mikolov et al., 2013), as well as distributed representations of longer bodies of…”
Towards Universal Paraphrastic Sentence Embeddings (2015, background): “…architectures have been proposed to model compositionality in such sequences, ranging from those based on simple operations like addition (Mitchell & Lapata, 2010; Yu & Dredze, 2015; Iyyer et al., 2015) to those based on richly-structured functions like recursive neural networks (Socher…”
SemEval-2014 Task 1: Evaluation of Compositional Distributional Semantic Models on Full Sentences through Semantic Relatedness and Textual Entailment (2014, background): “…of DSMs (CDSMs) have been proposed, with the purpose of representing the meaning of phrases and sentences by composing the distributional representations of the words they contain (Baroni and Zampar-elli, 2010; Grefenstette and Sadrzadeh, 2011; Mitchell and Lapata, 2010; Socher et al., 2012).”
Illinois-LH: A Denotational and Distributional Approach to Semantics (2014, background): “Since TE is a directional task and SR is symmetric, we express features that depend on sentence order twice: 1) f 1 are the features of s 1 and f 2 are the features of s 2 , 2) f 1 are the features of the longer sentence and f 2 are the features of the shorter sentence.”
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms (2018, methodology): “These methods range from simple operations like addition (Mitchell and Lapata, 2010; Iyyer et al., 2015), to more sophisticated compo-”
Document Modeling with Gated Recurrent Neural Network for Sentiment Classification (2015, background): “Another line of research concentrates on semantic composition (Mitchell and Lapata, 2010).”
Chinese Poetry Generation with Recurrent Neural Networks (2014, background): “In principle, any model that produces vector-based representations of phrases or sentences could be used (Mitchell and Lapata, 2010; Socher et al., 2012).”
Linguistic Regularities in Sparse and Explicit Word Representations (2014, background): “Arithmetic combination of explicit word vectors is extensively studied in the context of compositional semantics (Mitchell and Lapata, 2010), where a phrase composed of two or more words is represented by a single vector, computed by a function of its component word vectors.”
Recurrent Convolutional Neural Networks for Discourse Compositionality (2013, background): “Proceedings of the Workshop on Continuous Vector Space Models and their Compositionality, pages 119–126, Sofia, Bulgaria, August 9 2013. c©2013 Association for Computational Linguistics”
Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model (2015, background): “as simple as learning scalar weights for different words in a phrase (Mitchell and Lapata, 2010).”
Multi-Step Regression Learning for Compositional Distributional Semantics (2013, methodology): “ence similarity (e.g., similarity of mom sings and boy dances is approximated by the cosine of sing and dance). We adopt the widely used and generally successful multiplicative and additive models of Mitchell and Lapata (2010) and others. Composition with the Multiply and Add methods is achieved by,”