Distributional Structure

By Z. Harris. 1954

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

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

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Learning Distributed Representations of Sentences from Unlabelled Data (2016, background): “The model could be said to exploit a type of sentence-level Distributional Hypothesis (Harris, 1954; Polajnar et al., 2015).”
Distributed Representations of Sentences and Documents (2014, background): “Perhaps the most common ﬁxed-length vector representation for texts is the bag-of-words or bag-of-n-grams (Harris, 1954) due to its simplicity, efﬁciency and often surprising accuracy.”
Experience Grounds Language (2020, background): “the beginning of corpus linguistics (Zipf, 1932; Harris, 1954), to the formation of the Penn Treebank (Marcus et al.”
Pretrained Transformers Improve Out-of-Distribution Robustness (2020, methodology): “We use a bag-ofwords model (Harris, 1954), which is high-bias but low-variance, so it may exhibit performance stability.”
From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions (2014, background): “Figure 1: Two images from our data set and their ﬁve captions similar meaning (Harris, 1954).”
Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change (2016, methodology): “These methods operationalize the ‘distributional hypothesis’ that word semantics are implicit in co-occurrence relationships (Harris, 1954; Firth, 1957).”
From Frequency to Meaning: Vector Space Models of Semantics (2010, methodology): “The distributional hypothesis in linguistics is that words that occur in similar contexts tend to have similar meanings (Harris, 1954).”
Word Translation Without Parallel Data (2017, methodology): “ Most successful methods for learning distributed representations of words (e.g. Mikolov et al. (2013c;a); Pennington et al. (2014); Bojanowski et al. (2017)) rely on the distributional hypothesis of Harris (1954), which states that words occurring in similar contexts tend to have similar meanings. ”
Learning Deep Representations of Fine-Grained Visual Descriptions (2016, methodology): “For instance on the Caltech-UCSD birds database (CUB) [46], previous zero-shot learning approaches [13, 2, 3] have used human-encoded attributes [24], or simplified language models such as bag-of-words [16], WordNet-hierarchyderived features [29], and neural word embeddings such as Word2Vec [28] and”
Machine Learning Methods That Economists Should Know About (2019, methodology): “Vector representations of words (also known as “distributed representations”) can incorporate ideas about word usage and meaning [Harris, 1954, Firth, 1957, Bengio et al., 2003, Mikolov et al., 2013b].”
SHOPPER: A Probabilistic Model of Consumer Choice with Substitutes and Complements (2017, background): “(2003), Firth (1957), Harris (1954), Mikolov et al.”
Improving Distributional Similarity with Lessons Learned from Word Embeddings (2015, background): “The second-order terms measure the extent to which the two words are replaceable based on their tendencies to appear in similar contexts, and are the manifestation of Harris’s (1954) distributional hypothesis.”
Matching the Blanks: Distributional Similarity for Relation Learning (2019, background): “of Harris’ distributional hypothesis (Harris, 1954) to relations, as well as recent advances in learning word representations from observations of their contexts (Mikolov et al.”