Lecture

Ethics in NLP

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Description

This lecture explores the ethical considerations in designing Natural Language Processing (NLP) systems, focusing on biases, toxicity, and privacy concerns. It delves into the potential harms of language models, such as leaking private information and spreading disinformation. The instructor discusses the classification of harms from language models, including discrimination, exclusion, and misinformation. Moreover, the lecture addresses the challenges of bias amplification, model training, and the implications of hidden biases in large-scale NLP models.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Official source

Related concepts (32)

Natural language processing

Natural language processing (NLP) is an interdisciplinary subfield of linguistics and computer science. It is primarily concerned with processing natural language datasets, such as text corpora or speech corpora, using either rule-based or probabilistic (i.e. statistical and, most recently, neural network-based) machine learning approaches. The goal is a computer capable of "understanding" the contents of documents, including the contextual nuances of the language within them.

Bias

Bias is a disproportionate weight in favor of or against an idea or thing, usually in a way that is closed-minded, prejudicial, or unfair. Biases can be innate or learned. People may develop biases for or against an individual, a group, or a belief. In science and engineering, a bias is a systematic error. Statistical bias results from an unfair sampling of a population, or from an estimation process that does not give accurate results on average. The word appears to derive from Old Provençal into Old French biais, "sideways, askance, against the grain".

Language model

A language model is a probabilistic model of a natural language that can generate probabilities of a series of words, based on text corpora in one or multiple languages it was trained on. Large language models, as their most advanced form, are a combination of feedforward neural networks and transformers. They have superseded recurrent neural network-based models, which had previously superseded the pure statistical models, such as word n-gram language model.

History of natural language processing

The history of natural language processing describes the advances of natural language processing (Outline of natural language processing). There is some overlap with the history of machine translation, the history of speech recognition, and the history of artificial intelligence. The history of machine translation dates back to the seventeenth century, when philosophers such as Leibniz and Descartes put forward proposals for codes which would relate words between languages.

Selection bias

Selection bias is the bias introduced by the selection of individuals, groups, or data for analysis in such a way that proper randomization is not achieved, thereby failing to ensure that the sample obtained is representative of the population intended to be analyzed. It is sometimes referred to as the selection effect. The phrase "selection bias" most often refers to the distortion of a statistical analysis, resulting from the method of collecting samples. If the selection bias is not taken into account, then some conclusions of the study may be false.

Related lectures (64)

Anonymity and Accountability

Explores the significance of anonymity in avoiding judgment based on personal characteristics and the need to balance it with accountability.

Ethical Considerations in Natural Language Processing

Explores ethical challenges in NLP systems, including biases, toxicity, privacy, and disinformation.

Prompting and Alignment

Explores prompting, alignment, and the capabilities of large language models for natural language processing tasks.

Ethics in Natural Language Processing: Addressing Bias and Misinformation

Covers ethical considerations in NLP, focusing on bias, toxicity, and misinformation.

Sequence to Sequence Models: Overview and Applications