A Synopsis of Linguistic Theory, 1930-1955

By J. Firth. 1957

How researchers see this paper

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

In Linguistics

Citations in the corpus

Experience Grounds Language (2020, background): “The intuition of such embedding representations, that context lends meaning, has long been acknowledged (Firth, 1957; Turney and Pantel, 2010).”
Social Biases in NLP Models as Barriers for Persons with Disabilities (2020, background): “the idea that “you shall know a word by the company it keeps” (Firth, 1957).”
LINE: Large-scale Information Network Embedding (2015, background): “For example, “the degree of overlap of two people’s friend-ship networks correlates with the strength of ties between them,” in a social network [6]; and “You shall know a word by the company it keeps” (Firth, J. R. 1957:11) in text corpora [5].”
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).”
Fusion of Detected Objects in Text for Visual Question Answering (2019, background): “It has long been understood that the meaning of a word is systematically and predictably linked to the context in which it occurs (e.g., Firth 1957; Harris 1954; Deerwester et al. 1990; Mikolov et al. 2013).”
From Frequency to Meaning: Vector Space Models of Semantics (2010, background): “The documents are sorted in order of increasing distance (decreasing semantic similarity) from the query and then presented to the user.”
Word Association Norms, Mutual Information, and Lexicography (1989, background): “Running through the whole Firthian tradition, for example, is the theme that "You shall know a word by the company it keeps" (Firth, 1957).”
Machine Learning Methods That Economists Should Know About (2019, background): “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].”
PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks (2015, background): “The essential idea of these approaches comes from the distributional hypothesis that “you shall know a word by the company it keeps” (Firth, J.R. 1957:11) [7].”
code2vec: learning distributed representations of code (2018, background): “The idea of distributed representations of words date back to Deer-wester et al. [1990] and even Salton et al. [1975], and are commonly based on the distributional hypothesis of Harris [1954] and Firth [1957], which states that words in similar contexts have similar meaning.”
Experimental Support for a Categorical Compositional Distributional Model of Meaning (2011, background): “Compositional type-logical approaches (Mon-tague, 1974; Lambek, 2008) and distributional models of lexical semantics (Schutze, 1998; Firth, 1957) have provided two partial orthogonal solutions to the question.”
Multilingual Distributed Representations without Word Alignment (2013, background): “This follows the idea that the meaning of a word can be determined by “the company it keeps” [11], that is by the context it appears in.”
Good-Enough Compositional Data Augmentation (2019, background): “The observation that sentence context provides a strong signal about a constitutent’s category is in turn the foundation of distributional approaches to language processing (Firth, 1957).”
Multilingual Models for Compositional Distributed Semantics (2014, background): “Within a monolingual context, the distributional hypothesis (Firth, 1957) forms the basis of most approaches for learning word representations.”
Are Distributional Representations Ready for the Real World? Evaluating Word Vectors for Grounded Perceptual Meaning (2017, positive): “They center around a classic insight from at least as early as Harris (1954); Firth (1957):”