Lecture

Reading Comprehension: Question Answering Systems

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 covers the fundamentals of question answering systems, focusing on tasks, models, and limitations. It delves into the complexity of question types, answer types, and classical QA methods. The instructor explores the evolution from classical QA to modern approaches like Extractive QA and Generative QA, discussing their pros and cons. The lecture also touches on QA datasets like SQuaD and the evaluation metrics used in assessing QA systems. Additionally, it examines challenges such as synonymity, ambiguity, and multi-hop reasoning that remain in the field of question answering.

Official source

Related concepts (32)

Question answering

Question answering (QA) is a computer science discipline within the fields of information retrieval and natural language processing (NLP) that is concerned with building systems that automatically answer questions that are posed by humans in a natural language. A question-answering implementation, usually a computer program, may construct its answers by querying a structured database of knowledge or information, usually a knowledge base. More commonly, question-answering systems can pull answers from an unstructured collection of natural language documents.

Reading comprehension

Reading comprehension is the ability to process written text, understand its meaning, and to integrate with what the reader already knows. Reading comprehension relies on two abilities that are connected to each other: word reading and language comprehension. Comprehension specifically is a "creative, multifaceted process" dependent upon four language skills: phonology, syntax, semantics, and pragmatics.

Information retrieval

Information retrieval (IR) in computing and information science is the process of obtaining information system resources that are relevant to an information need from a collection of those resources. Searches can be based on full-text or other content-based indexing. Information retrieval is the science of searching for information in a document, searching for documents themselves, and also searching for the metadata that describes data, and for databases of texts, images or sounds.

Reading for special needs

Reading for special needs has become an area of interest as the understanding of reading has improved. Teaching children with special needs how to read was not historically pursued due to perspectives of a Reading Readiness model. This model assumes that a reader must learn to read in a hierarchical manner such that one skill must be mastered before learning the next skill (e.g., a child might be expected to learn the names of the letters in the alphabet in the correct order before being taught how to read his or her name).

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.

Related lectures (17)

Deep Learning for Question Answering

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

[2024] - 29+30. Question Answering & Reading Comprehension

Classical Language Models: Foundations and Applications

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

Foundations of Information Systems: Course Overview and Key Concepts

Introduces the course on information systems, covering its structure, objectives, and foundational concepts essential for understanding data management and decision-making.

How to Read a Research Article in Social Sciences