Grammatical Gender's Influence on Distributional Semantics: A Causal
Perspective
- URL: http://arxiv.org/abs/2311.18567v1
- Date: Thu, 30 Nov 2023 13:58:13 GMT
- Title: Grammatical Gender's Influence on Distributional Semantics: A Causal
Perspective
- Authors: Karolina Sta\'nczak, Kevin Du, Adina Williams, Isabelle Augenstein,
Ryan Cotterell
- Abstract summary: How much meaning influences gender assignment across languages is an active area of research in modern linguistics and cognitive science.
We offer a novel, causal graphical model that jointly represents the interactions between a noun's grammatical gender, its meaning, and adjective choice.
We find that grammatical gender has a near-zero effect on adjective choice, thereby calling the neo-Whorfian hypothesis into question.
- Score: 100.47362690469669
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: How much meaning influences gender assignment across languages is an active
area of research in modern linguistics and cognitive science. We can view
current approaches as aiming to determine where gender assignment falls on a
spectrum, from being fully arbitrarily determined to being largely semantically
determined. For the latter case, there is a formulation of the neo-Whorfian
hypothesis, which claims that even inanimate noun gender influences how people
conceive of and talk about objects (using the choice of adjective used to
modify inanimate nouns as a proxy for meaning). We offer a novel, causal
graphical model that jointly represents the interactions between a noun's
grammatical gender, its meaning, and adjective choice. In accordance with past
results, we find a relationship between the gender of nouns and the adjectives
which modify them. However, when we control for the meaning of the noun, we
find that grammatical gender has a near-zero effect on adjective choice,
thereby calling the neo-Whorfian hypothesis into question.
Related papers
- Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words [85.48043537327258]
Existing machine translation gender bias evaluations are primarily focused on male and female genders.
This study presents a benchmark AmbGIMT (Gender-Inclusive Machine Translation with Ambiguous attitude words)
We propose a novel process to evaluate gender bias based on the Emotional Attitude Score (EAS), which is used to quantify ambiguous attitude words.
arXiv Detail & Related papers (2024-07-23T08:13:51Z) - What an Elegant Bridge: Multilingual LLMs are Biased Similarly in Different Languages [51.0349882045866]
This paper investigates biases of Large Language Models (LLMs) through the lens of grammatical gender.
We prompt a model to describe nouns with adjectives in various languages, focusing specifically on languages with grammatical gender.
We find that a simple classifier can not only predict noun gender above chance but also exhibit cross-language transferability.
arXiv Detail & Related papers (2024-07-12T22:10:16Z) - Investigating grammatical abstraction in language models using few-shot learning of novel noun gender [0.0]
We conduct a noun learning experiment to assess whether an LSTM and a decoder-only transformer can achieve human-like abstraction of grammatical gender in French.
We find that both language models effectively generalise novel noun gender from one to two learning examples and apply the learnt gender across agreement contexts.
While the generalisation behaviour of models suggests that they represent grammatical gender as an abstract category, like humans, further work is needed to explore the details.
arXiv Detail & Related papers (2024-03-15T14:25:59Z) - MISGENDERED: Limits of Large Language Models in Understanding Pronouns [46.276320374441056]
We evaluate popular language models for their ability to correctly use English gender-neutral pronouns.
We introduce MISGENDERED, a framework for evaluating large language models' ability to correctly use preferred pronouns.
arXiv Detail & Related papers (2023-06-06T18:27:52Z) - Wikigender: A Machine Learning Model to Detect Gender Bias in Wikipedia [0.0]
We use a machine learning model to prove that there is a difference in how women and men are portrayed on Wikipedia.
Using only adjectives as input to the model, we show that the adjectives used to portray women have a higher subjectivity than the ones used to describe men.
arXiv Detail & Related papers (2022-11-14T16:49:09Z) - An exploration of the encoding of grammatical gender in word embeddings [0.6461556265872973]
The study of grammatical gender based on word embeddings can give insight into discussions on how grammatical genders are determined.
It is found that there is an overlap in how grammatical gender is encoded in Swedish, Danish, and Dutch embeddings.
arXiv Detail & Related papers (2020-08-05T06:01:46Z) - On the Relationships Between the Grammatical Genders of Inanimate Nouns
and Their Co-Occurring Adjectives and Verbs [57.015586483981885]
We use large-scale corpora in six different gendered languages.
We find statistically significant relationships between the grammatical genders of inanimate nouns and the verbs that take those nouns as direct objects, indirect objects, and as subjects.
arXiv Detail & Related papers (2020-05-03T22:49:44Z) - Predicting Declension Class from Form and Meaning [70.65971611552871]
Class membership is far from deterministic, but the phonological form of a noun and/or its meaning can often provide imperfect clues.
We operationalize this by measuring how much information, in bits, we can glean about declension class from knowing the form and/or meaning of nouns.
We find for two Indo-European languages (Czech and German) that form and meaning respectively share significant amounts of information with class.
arXiv Detail & Related papers (2020-05-01T21:48:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.