Extracting Social Networks from Language Statistics

Hutchinson, Sterling; Louwerse, Max M.

doi:10.1080/0163853x.2017.1332446

Cited by 6 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other proposals argue that the meaning of proper names is determined socially (Jeshion, 2009 ). Neither type of information is easy to extract from text alone, although much research on multimodal models can be seen as providing a framework for the direct reference issue (Bruni et al, 2014 ), and selected types of text, such as social media posts and novels, may provide enough data for the extraction of social networks from word distributions (Dunbar et al, 2015 ; Hutchinson and Louwerse, 2018 ).…”

Section: Discussionmentioning

confidence: 99%

Exploring the Representations of Individual Entities in the Brain Combining EEG and Distributional Semantics

Bruera

Poesio

2022

Front. Artif. Intell.

View full text Add to dashboard Cite

Semantic knowledge about individual entities (i.e., the referents of proper names such as Jacinta Ardern) is fine-grained, episodic, and strongly social in nature, when compared with knowledge about generic entities (the referents of common nouns such as politician). We investigate the semantic representations of individual entities in the brain; and for the first time we approach this question using both neural data, in the form of newly-acquired EEG data, and distributional models of word meaning, employing them to isolate semantic information regarding individual entities in the brain. We ran two sets of analyses. The first set of analyses is only concerned with the evoked responses to individual entities and their categories. We find that it is possible to classify them according to both their coarse and their fine-grained category at appropriate timepoints, but that it is hard to map representational information learned from individuals to their categories. In the second set of analyses, we learn to decode from evoked responses to distributional word vectors. These results indicate that such a mapping can be learnt successfully: this counts not only as a demonstration that representations of individuals can be discriminated in EEG responses, but also as a first brain-based validation of distributional semantic models as representations of individual entities. Finally, in-depth analyses of the decoder performance provide additional evidence that the referents of proper names and categories have little in common when it comes to their representation in the brain.

show abstract

Section: Discussionmentioning

confidence: 99%

Exploring the Representations of Individual Entities in the Brain Combining EEG and Distributional Semantics

Bruera

Poesio

2022

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Louwerse and Zwaan (2009) demonstrated that LSA predicted the geographic location and population size of the 50 largest cities in the United States, and its accuracy was on a par with human prediction. Hutchinson and Louwerse (2018) reported that social relationships between fictional characters in three novels could be derived from language statistics. Furthermore, social or cultural biases toward gender or race (e.g., European‐Americans are pleasant vs. African‐Americans are unpleasant) that result in prejudiced decisions have recently been found to be encoded in word vectors (e.g., Bolukbasi, Chang, Zou, Saligrama, & Kalai, 2016; Caliskan, Bryson, & Narayanan, 2017).…”

Section: Related Workmentioning

confidence: 99%

“…Despite the fact that an extensive number of studies have applied word vectors to a variety of tasks in many research fields, relatively little effort has been made to explore what type of information or knowledge is encoded in word vectors. Previous studies that have addressed this question have demonstrated that text‐based word vectors reflect perceptual (Louwerse & Connell, 2011; Riordan & Jones, 2011), emotional (Passaro, Bondielli, & Lenci, 2017; Recchia & Louwerse, 2015; Tillmand & Louwerse, 2018), and social (Hutchinson & Louwerse, 2018) information. Although these studies have focused on specific information, some recent studies (Grand, Blank, Pereira, & Fedorenko, 2018; Sommerauer & Fokkens, 2018) have compared various types of knowledge in terms of the representational ability of word vectors.…”

Section: Introductionmentioning

confidence: 99%

Exploring What Is Encoded in Distributional Word Vectors: A Neurobiologically Motivated Analysis

Utsumi¹

2020

Cognitive Science

View full text Add to dashboard Cite

The pervasive use of distributional semantic models or word embeddings for both cognitive modeling and practical application is because of their remarkable ability to represent the meanings of words. However, relatively little effort has been made to explore what types of information are encoded in distributional word vectors. Knowing the internal knowledge embedded in word vectors is important for cognitive modeling using distributional semantic models. Therefore, in this paper, we attempt to identify the knowledge encoded in word vectors by conducting a computational experiment using Binder et al.'s (2016) featural conceptual representations based on neurobiologically motivated attributes. In an experiment, these conceptual vectors are predicted from text‐based word vectors using a neural network and linear transformation, and prediction performance is compared among various types of information. The analysis demonstrates that abstract information is generally predicted more accurately by word vectors than perceptual and spatiotemporal information, and specifically, the prediction accuracy of cognitive and social information is higher. Emotional information is also found to be successfully predicted for abstract words. These results indicate that language can be a major source of knowledge about abstract attributes, and they support the recent view that emphasizes the importance of language for abstract concepts. Furthermore, we show that word vectors can capture some types of perceptual and spatiotemporal information about concrete concepts and some relevant word categories. This suggests that language statistics can encode more perceptual knowledge than often expected.

show abstract

“…Some exceptions are Herbelot (2015), which analyzes the properties of distributional representations of person names extracted from novels; work on extracting entity attributes (Gupta et al. 2015; Guu, Miller, & Liang 2015; Hutchinson & Louwerse 2018; Louwerse & Zwaan 2009); building entity representations from annotations and knowledge bases (Bianchi & Palmonari 2017); and the relation between entities and the categories that they instantiate (i.e., instantiation, Boleda, Gupta, & Padó 2017).…”

Section: Introductionmentioning

confidence: 99%

Distributional Models of Category Concepts Based on Names of Category Members

et al. 2021

View full text Add to dashboard Cite

Cognitive scientists have long used distributional semantic representations of categories. The predominant approach uses distributional representations of category‐denoting nouns, such as “city” for the category city. We propose a novel scheme that represents categories as prototypes over representations of names of its members, such as “Barcelona,” “Mumbai,” and “Wuhan” for the category city. This name‐based representation empirically outperforms the noun‐based representation on two experiments (modeling human judgments of category relatedness and predicting category membership) with particular improvements for ambiguous nouns. We discuss the model complexity of both classes of models and argue that the name‐based model has superior explanatory potential with regard to concept acquisition.

show abstract

Extracting Social Networks from Language Statistics

Cited by 6 publications

References 20 publications

Exploring the Representations of Individual Entities in the Brain Combining EEG and Distributional Semantics

Exploring the Representations of Individual Entities in the Brain Combining EEG and Distributional Semantics

Exploring What Is Encoded in Distributional Word Vectors: A Neurobiologically Motivated Analysis

Distributional Models of Category Concepts Based on Names of Category Members

Contact Info

Product

Resources

About