Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Interpretability & Analysis: Modern NLP

Description

This lecture covers the importance of model interpretability in modern Natural Language Processing (NLP). It delves into methods like model probing, local explanations, and model-generated explanations to understand how models make predictions. The lecture also explores the use of linguistic probes to interpret model behavior and the challenges of faithful explanations. Additionally, it discusses the limitations of interpretability methods and the need to differentiate between plausibility and faithfulness in model explanations.

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.

Natural-language understanding

Natural-language understanding (NLU) or natural-language interpretation (NLI) is a subtopic of natural-language processing in artificial intelligence that deals with machine reading comprehension. Natural-language understanding is considered an AI-hard problem. There is considerable commercial interest in the field because of its application to automated reasoning, machine translation, question answering, news-gathering, text categorization, voice-activation, archiving, and large-scale content analysis.

Natural language generation

Natural language generation (NLG) is a software process that produces natural language output. A widely-cited survey of NLG methods describes NLG as "the subfield of artificial intelligence and computational linguistics that is concerned with the construction of computer systems than can produce understandable texts in English or other human languages from some underlying non-linguistic representation of information". While it is widely agreed that the output of any NLG process is text, there is some disagreement about whether the inputs of an NLG system need to be non-linguistic.

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.

Natural language

In neuropsychology, linguistics, and philosophy of language, a natural language or ordinary language is any language that occurs naturally in a human community by a process of use, repetition, and change without conscious planning or premeditation. It can take different forms, namely either a spoken language or a sign language. Natural languages are distinguished from constructed and formal languages such as those used to program computers or to study logic. Natural language can be broadly defined as different from artificial and constructed languages, e.

Related lectures (33)

Deep Learning for Question Answering

Explores deep learning for question answering, analyzing neural networks and model robustness to noise.

Word Embeddings: Introduction and Applications

Introduces word embeddings, explaining how they capture word meanings based on context and their applications in natural language processing tasks.

Coreference Resolution

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

Classical Language Models: Foundations and Applications

Introduces classical language models, their applications, and foundational concepts like count-based modeling and evaluation metrics.

Introduction to Modern Natural Language Processing