INTEGRATOR logo

INTEGRATOR

INTEGRATOR logo

INTEGRATOR

Dirk Hovy, scientific director of DMI and Professor of computer science, has won an ERC starting grant of 1.5mln euros. His project INTEGRATOR, funded under grant agreement 949944, introduces demographic factors into language processing systems, which will improve algorithmic performance, avoid racism, sexism, and ageism, and open up new applications. What if I wrote that “winning an ERC Grant, Dirk Hovy got a sick result?”. Those familiar with the use of “sick” as a synonym for “great” or “awesome” among teenagers would think that Bocconi Knowledge hired a very young writer (or someone posing as such). The rest would think I went crazy. Current artificial intelligence-based language systems wouldn’t have a clue. “Natural language processing (NLP) technologies,” Prof. Hovy says, “fail to account for demographics both in understanding language and in generating it. And this failure prevents us from reaching human-like performance. It limits possible future applications and it introduces systematic bias against underrepresented demographic groups”.

🗞️🗞️ Related articles featured in Corriere Innovazione and Bocconi News.

Publications

Emotions play important epistemological and cognitive roles in our lives, revealing our values and guiding our actions. Previous work …

As diverse linguistic communities and users adopt large language models (LLMs), assessing their safety across languages becomes …

The open-ended nature of language generation makes the evaluation of autoregressive large language models (LLMs) challenging. One …

Without proper safeguards, large language models will readily follow malicious instructions and generate toxic content. This risk …

Using large language models (LLMs) for educational applications like dialogue-based teaching is a hot topic. Effective teaching, …

The last two years have seen a rapid growth in concerns around the safety of large language models (LLMs). Researchers and …

Large language models (LLMs) reflect societal norms and biases, especially about gender. While societal biases and stereotypes have …

Open conversations are one of the most engaging forms of teaching. However, creating those conversations in educational software is a …

Emotions are a central aspect of communication. Consequently, emotion analysis (EA) is a rapidly growing field in natural language …

Since the foundational work of William Labov on the social stratification of language (Labov, 1964), linguistics has made concentrated …

Since Labov’s (1964) foundational work on the social stratification of language, linguistics has dedicated concerted efforts …

Large Language Models (LLMs) exhibit remarkable text classification capabilities, excelling in zero- and few-shot learning (ZSL and …

We present the system proposed by the MilaNLP team for the Explainable Detection of Online Sexism (EDOS) shared task. We propose an …

Hate speech detection faces two significant challenges: 1) the limited availability of labeled data and 2) the high variability of hate …

Much work in natural language processing (NLP) relies on human annotation. The majority of this implicitly assumes that annotator’s …

Many NLP tasks exhibit human label variation, where different annotators give different labels to the same texts. This variation is …

Work on hate speech has made considering rude and harmful examples in scientific publications inevitable. This situation raises various …

As 3rd-person pronoun usage shifts to include novel forms, e.g., neopronouns, we need more research on identity-inclusive NLP. …

As 3rd-person pronoun usage shifts to include novel forms, e.g., neopronouns, we need more research on identity-inclusive NLP. …

Demographic factors (e.g., gender or age) shape our language. Previous work showed that incorporating demographic factors can …

Large language models (LLMs) offer a range of new possibilities, including adapting the text to different audiences and their reading …

Artificial Intelligence (AI) is at a crucial point in its development: stable enough to be used in production systems, and increasingly …

Twitter data have become essential to Natural Language Processing (NLP) and social science research, driving various scientific …

Fairness and environmental impact are important research directions for the sustainable development of artificial intelligence. …

Pre-trained language models (PLMs) have outperformed other NLP models on a wide range of tasks. Opting for a more thorough …

Hate speech is a global phenomenon, but most hate speech datasets so far focus on English-language content. This hinders the …

Language is constantly changing and evolving, leaving language models to quickly become outdated, both factually and linguistically. …

The world of pronouns is changing – from a closed word class with few members to an open set of terms to reflect identities. However, …

Over the last several years, end-to-end neural conversational agents have vastly improved their ability to carry unrestricted, …

Natural Language Processing (NLP) ‘s applied nature makes it necessary to select the most effective and robust models. Producing …

Transformer-based Natural Language Processing models have become the standard for hate speech detection. However, the unconscious use …

Current language technology is ubiquitous and directly influences individuals’ lives worldwide. Given the recent trend in AI on …

The maturity level of language models is now at a stage in which many companies rely on them to solve various tasks. However, while …

Labelled data is the foundation of most natural language processing tasks. However, labelling data is difficult and there often are …

Detecting emotion in text allows social and computational scientists to study how people behave and react to online events. However, …

Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, …

The social impact of natural language processing and its applications has received increasing attention. In this position paper, we …

Recently, there has been an increased interest in demographically grounded bias in natural language processing (NLP) applications. Much …

Language models have revolutionized the field of NLP. However, language models capture and proliferate hurtful stereotypes, especially …

Natural language processing (NLP) applications are now more powerful and ubiquitous than ever before. With rapidly developing (neural) …