Lecture

Ethical Considerations in Natural Language Processing

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 delves into the ethical aspects of Natural Language Processing (NLP) systems, focusing on issues such as biases, toxicity, privacy, and disinformation. The instructor discusses real-world examples like the Tay chatbot and the implications of biased language models. The lecture explores the classification of harms from language models, the amplification of biases, and the challenges in coreference resolution. It also covers the risks of leaking private information and inferring sensitive data from NLP models. The session concludes with a critical examination of the potential dangers of deploying language models for disinformation purposes and the importance of considering ethical implications in NLP development.

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.

Privacy

Privacy (UK, US) is the ability of an individual or group to seclude themselves or information about themselves, and thereby express themselves selectively. The domain of privacy partially overlaps with security, which can include the concepts of appropriate use and protection of information. Privacy may also take the form of bodily integrity. There have been many different conceptions of privacy throughout history. Most cultures recognize the right of an individual to withhold aspects of their personal lives from public record.

Ethics

Ethics or moral philosophy is a branch of philosophy that "involves systematizing, defending, and recommending concepts of right and wrong behavior". The field of ethics, along with aesthetics, concerns matters of value; these fields comprise the branch of philosophy called axiology. Ethics seeks to resolve questions of human morality by defining concepts such as good and evil, right and wrong, virtue and vice, justice and crime. As a field of intellectual inquiry, moral philosophy is related to the fields of moral psychology, descriptive ethics, and value theory.

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.

Large language model

A large language model (LLM) is a language model characterized by its large size. Their size is enabled by AI accelerators, which are able to process vast amounts of text data, mostly scraped from the Internet. The artificial neural networks which are built can contain from tens of millions and up to billions of weights and are (pre-)trained using self-supervised learning and semi-supervised learning. Transformer architecture contributed to faster training.

Related lectures (64)

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.

The Human Body and Legal Rights

Explores legal and ethical aspects of the human body, detached parts, and organ harvesting, including ownership and research implications.

Coreference Resolution

Delves into coreference resolution, discussing challenges, advancements, and evaluation methods.

Neuro-symbolic Representations: Commonsense Knowledge & Reasoning