Quantifying the Semantic Core of Gender Systems

Williams, Adina; Blasí, Damián E.; Wolf-Sonkin, Lawrence; Wallach, Hanna; Cotterell, Ryan

doi:10.18653/v1/d19-1577

Cited by 17 publications

(11 citation statements)

References 13 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Grammatical gender has been found to interact with lexical semantics (Schwichtenberg and Schiller, 2004;Williams et al, 2019Williams et al, , 2020, and often can be determined from form (Brooks et al, 1993;Dobrin, 1998;Frigo and McDonald, 1998;Starreveld and La Heij, 2004). This means that it cannot be ignored in the present study.…”

Section: Controlling For Grammatical Gender?mentioning

confidence: 80%

Predicting Declension Class from Form and Meaning

Williams¹,

Pimentel²,

Blix³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

The noun lexica of many natural languages are divided into several declension classes with characteristic morphological properties. Class membership is far from deterministic, but the phonological form of a noun and its meaning can often provide imperfect clues. Here, we investigate the strength of those clues. More specifically, we operationalize "strength" as measuring how much information, in bits, we can glean about declension class from knowing the form and meaning of nouns. We know that form and meaning are often also indicative of grammatical gender-which, as we quantitatively verify, can itself share information with declension class-so we also control for gender. We find for two Indo-European languages (Czech and German) that form and meaning share a significant amount of information with class (and contribute additional information beyond gender). The three-way interaction between class, form, and meaning (given gender) is also significant. Our study is important for two reasons: First, we introduce a new method that provides additional quantitative support for a classic linguistic finding that form and meaning are relevant for the classification of nouns into declensions. Second, we show not only that individual declension classes vary in the strength of their clues within a language, but also that the variations between classes vary across languages.

show abstract

Section: Controlling For Grammatical Gender?mentioning

confidence: 80%

Predicting Declension Class from Form and Meaning

Williams¹,

Pimentel²,

Blix³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Particular attention has been paid to uncovering, analyzing, and removing gender biases in word embeddings (Basta et al, 2019;Kaneko and Bollegala, 2019;Zhao et al, , 2018bBolukbasi et al, 2016). This word embedding work has even extended to multilingual work on gender-marking Williams et al, 2019;Zhou et al, 2019;. Despite these efforts, many methods for debiasing embeddings have only succeeded in hiding word embedding biases as opposed to removing them -making gender debiasing still an open area of research.…”

Section: Related Workmentioning

confidence: 99%

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Dinan

Fan

Williams

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

102

View full text Add to dashboard Cite

Social biases present in data are often directly reflected in the predictions of models trained on that data. We analyze gender bias in dialogue data, and examine how this bias is not only replicated, but is also amplified in subsequent generative chit-chat dialogue models. We measure gender bias in six existing dialogue datasets before selecting the most biased one, the multi-player textbased fantasy adventure dataset LIGHT (Urbanek et al., 2019), as a testbed for bias mitigation techniques. We consider three techniques to mitigate gender bias: counterfactual data augmentation, targeted data collection, and bias controlled training. We show that our proposed techniques mitigate gender bias by balancing the genderedness of generated dialogue utterances, and find that they are particularly effective in combination. We evaluate model performance with a variety of quantitative methods-including the quantity of gendered words, a dialogue safety classifier, and human assessments-all of which show that our models generate less gendered, but equally engaging chit-chat responses.

show abstract

“…King et al (2020) and Gorman et al (2019) grouped sequence-to-sequence model errors into linguistically meaningful categories. Neural models have been used to estimate the information theoretic contribution of meaning to gender (Williams et al, 2019) and of meaning and form to gender and declension class . used grammatical gender classes to track phylogenetic relationships between related languages, while others used them to model morphological learnability (Elsner et al, 2019;Forster et al, 2021).…”

Section: Morphological Inflection In Neural Networkmentioning

confidence: 99%

Generalising to German Plural Noun Classes, from the Perspective of a Recurrent Neural Network

Dankers

Langedijk²,

McCurdy³

et al. 2021

Proceedings of the 25th Conference on Computational Natural Language Learning

Self Cite

View full text Add to dashboard Cite

Inflectional morphology has since long been a useful testing ground for broader questions about generalisation in language and the viability of neural network models as cognitive models of language. Here, in line with that tradition, we explore how recurrent neural networks acquire the complex German plural system and reflect upon how their strategy compares to human generalisation and rule-based models of this system. We perform analyses including behavioural experiments, diagnostic classification, representation analysis and causal interventions, suggesting that the models rely on features that are also key predictors in rule-based models of German plurals. However, the models also display shortcut learning, which is crucial to overcome in search of more cognitively plausible generalisation behaviour.

show abstract

Quantifying the Semantic Core of Gender Systems

Cited by 17 publications

References 13 publications

Predicting Declension Class from Form and Meaning

Predicting Declension Class from Form and Meaning

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Generalising to German Plural Noun Classes, from the Perspective of a Recurrent Neural Network

Contact Info

Product

Resources

About