相关论文: Investigating grammatical abstraction in language …

LSTMs trained on next-word prediction can accurately perform linguistic tasks that require tracking long-distance syntactic dependencies. Notably, model accuracy approaches human performance on number agreement tasks (Gulordava et al.,…

Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications. However, embeddings trained on human-generated corpora have been demonstrated to inherit strong gender stereotypes…

Does the grammatical gender of a language interfere when measuring the semantic gender information captured by its word embeddings? A number of anomalous gender bias measurements in the embeddings of gendered languages suggest this…

Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent. Cross-lingual embeddings circumvent some of these limitations,…

Recent studies have shown that word embeddings exhibit gender bias inherited from the training corpora. However, most studies to date have focused on quantifying and mitigating such bias only in English. These analyses cannot be directly…

Categorization is a core component of human linguistic competence. We investigate how a transformer-based language model (LM) learns linguistic categories by comparing its behaviour over the course of training to behaviours which…

Numerous studies have demonstrated the ability of neural language models to learn various linguistic properties without direct supervision. This work takes an initial step towards exploring the less researched topic of how neural models…

Speakers of different languages must attend to and encode strikingly different aspects of the world in order to use their language correctly (Sapir, 1921; Slobin, 1996). One such difference is related to the way gender is expressed in a…

Abstract grammatical knowledge - of parts of speech and grammatical patterns - is key to the capacity for linguistic generalization in humans. But how abstract is grammatical knowledge in large language models? In the human literature,…

Detecting and mitigating harmful biases in modern language models are widely recognized as crucial, open problems. In this paper, we take a step back and investigate how language models come to be biased in the first place. We use a…

Language models are typically evaluated on their success at predicting the distribution of specific words in specific contexts. Yet linguistic knowledge also encodes relationships between contexts, allowing inferences between word…

Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We assess the ability of modern neural language models to reproduce…

Word embeddings have been shown to produce remarkable results in tackling a vast majority of NLP related tasks. Unfortunately, word embeddings also capture the stereotypical biases that are prevalent in society, affecting the predictive…

The vector representation of words, known as word embeddings, has opened a new research approach in linguistic studies. These representations can capture different types of information about words. The grammatical gender of nouns is a…

Large language models (LLMs) have been shown to propagate and even amplify gender bias, in English and other languages, in specific or constrained contexts. However, no studies so far have focused on gender biases conveyed by LLMs'…

Previous studies investigating the syntactic abilities of deep learning models have not targeted the relationship between the strength of the grammatical generalization and the amount of evidence to which the model is exposed during…

Neural machine translation (NMT) models often suffer from gender biases that harm users and society at large. In this work, we explore how bridging the gap between languages for which parallel data is not available affects gender bias in…

Neural Machine Translation (NMT) has been shown to struggle with grammatical gender that is dependent on the gender of human referents, which can cause gender bias effects. Many existing approaches to this problem seek to control gender…

Gender bias is largely recognized as a problematic phenomenon affecting language technologies, with recent studies underscoring that it might surface differently across languages. However, most of current evaluation practices adopt a…

This paper investigates biases of Large Language Models (LLMs) through the lens of grammatical gender. Drawing inspiration from seminal works in psycholinguistics, particularly the study of gender's influence on language perception, we…