Compositional-ly Derived Representations of Morphologically Complex Words in Distributional Semantics

By Angeliki Lazaridou, Marco Marelli, Roberto Zamparelli, Marco Baroni. 2013

115 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning, Computational Linguistics & Semantics

How researchers see this paper

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

In Representation & Self-Supervised Learning

In Computational Linguistics & Semantics

Citations in the corpus

Compositional Morphology for Word Representations and Language Modelling (2014, methodology): “Our additive composition function can be regarded as an in-stantiation of the weighted addition strategy that performed well in a distributional compositional approach to derivational morphology (Lazaridou et al., 2013).”
Better Word Representations with Recursive Neural Networks for Morphology (2013, background): “To the best of our knowledge, the work closest to ours in terms of handing unseen words are the factored NLMs (Alexandrescu and Kirchhoff, 2006) and the compositional distributional semantic models (DSMs) (Lazaridou et al., 2013).”
Unsupervised Morphology Induction Using Word Embeddings (2015, methodology): “…POS, etc., and used models such as factored NLMs (Alexandrescu and Kirchhoff, 2006) to obtain representations for unseen words, or compositional distributional semantic models (Lazaridou et al., 2013) to derive representations for morphologically-inflected words, based on the composing morphemes.”
Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts (2014, background): “Lazaridou et al. (Lazaridou et al., 2013) use compositional distributional semantic models, originally designed to learn meanings of phrases, to derive representations for complex words, in which the base unit is the morpheme.”
Learning Character-level Representations for Part-of-Speech Tagging (2014, unknown): “They show that the quality of the embeddings they propose is improved when they combine the RNNs with a language model neural network that utilizes surrounding words context, creating what they call a context-sensitive morphological RNN. Previously, (Lazaridou et al., 2013) had used compositional di”
Learning Semantic Representations for Novel Words: Leveraging Both Form and Context (2018, background): “Similarly, Lazaridou et al. (2013) try several simple composition functions such as summation and multiplication to acquire word embeddings from morphemes.”
High-risk learning: acquiring new word vectors from tiny data (2017, methodology): “One way to deal with data sparsity issues when learning word vectors is to use morphological structure as a way to overcome the lack of primary data (Lazaridou et al., 2013; Luong et al., 2013; Kisselew et al., 2015; Pad´o et al., 2016).”
Memory, Show the Way: Memory Based Few Shot Word Representation Learning (2018, background): “Note that several rare word learning methods (Long et al., 2017; Xu et al., 2014; Lazaridou et al., 2013) that rely on auxiliary information don’t apply with most of our task settings.”