相关论文: A theoretical model of dynamical grammatical gende…

Language model is one of the most important modules in statistical machine translation and currently the word-based language model dominants this community. However, many translation models (e.g. phrase-based models) generate the target…

Third-person singular pronouns have long been used to study stereotypical biases in language models and to test their abilities to reason about reference. More recently, the interplay between reasoning and bias has been investigated with…

Human languages use a wide range of grammatical categories to constrain which words or phrases can fill certain slots in grammatical patterns and to express additional meanings, such as tense or aspect, through morpho-syntactic means. These…

Language has a profound impact on our thoughts, perceptions, and conceptions of gender roles. Gender-inclusive language is, therefore, a key tool to promote social inclusion and contribute to achieving gender equality. Consequently,…

The use of language is subject to variation over time as well as across social groups and knowledge domains, leading to differences even in the monolingual scenario. Such variation in word usage is often called lexical semantic change…

As large language models become integral to high-stakes applications, ensuring their robustness and fairness is critical. Despite their success, large language models remain vulnerable to adversarial attacks, where small perturbations, such…

Functional Distributional Semantics is a recently proposed framework for learning distributional semantics that provides linguistic interpretability. It models the meaning of a word as a binary classifier rather than a numerical vector. In…

We propose using automatically generated natural language definitions of contextualised word usages as interpretable word and word sense representations. Given a collection of usage examples for a target word, and the corresponding…

Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems. Since a variety of biases have previously been found in standard word embeddings, it is crucial to…

Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic expression of prompts affect these models. This study…

In social science, formal and quantitative models, such as ones describing economic growth and collective action, are used to formulate mechanistic explanations, provide predictions, and uncover questions about observed phenomena. Here, we…

Much like sentences are composed of words, words themselves are composed of smaller units. For example, the English word questionably can be analyzed as question+able+ly. However, this structural decomposition of the word does not directly…

Word embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the down-stream NLP applications that use those word embeddings.…

Many text corpora exhibit socially problematic biases, which can be propagated or amplified in the models trained on such data. For example, doctor cooccurs more frequently with male pronouns than female pronouns. In this study we (i)…

Formal/symbolic semantics can provide canonical, rigid controllability and interpretability to sentence representations due to their \textit{localisation} or \textit{composition} property. How can we deliver such property to the current…

Lexical semantic change detection (also known as semantic shift tracing) is a task of identifying words that have changed their meaning over time. Unsupervised semantic shift tracing, focal point of SemEval2020, is particularly challenging.…

This thesis advances semantic representation learning to render language representations or models more semantically and geometrically interpretable, and to enable localised, quasi-symbolic, compositional control through deliberate shaping…

Within the common LLM use case of text revision, we study LLMs' revision of gendered role nouns (e.g., outdoorsperson/woman/man) and their justifications of such revisions. We evaluate their alignment with feminist and trans-inclusive…

Reporting and providing test sets for harmful bias in NLP applications is essential for building a robust understanding of the current problem. We present a new observation of gender bias in a downstream NLP application: marked attribute…

Facts are subject to contingencies and can be true or false in different circumstances. One such contingency is time, wherein some facts mutate over a given period, e.g., the president of a country or the winner of a championship.…