Neural Approaches to Conversational Information Retrieval (神經網絡在對話式資訊檢索中的應用)

Gao, Jianfeng, Xiong, Chenyan, Bennett, Paul

Neural Approaches to Conversational Information Retrieval
  • 出版商: Springer
  • 出版日期: 2024-03-19
  • 售價: $6,400
  • 貴賓價: 9.5 折 $6,080
  • 語言: 英文
  • 頁數: 211
  • 裝訂: Quality Paper - also called trade paper
  • ISBN: 3031230825
  • ISBN-13: 9783031230820

    • 海外代購書籍(需單獨結帳)

相關主題

商品描述

This book surveys recent advances in Conversational Information Retrieval (CIR), focusing on neural approaches that have been developed in the last few years. Progress in deep learning has brought tremendous improvements in natural language processing (NLP) and conversational AI, leading to a plethora of commercial conversational services that allow naturally spoken and typed interaction, increasing the need for more human-centric interactions in IR.

The book contains nine chapters. Chapter 1 motivates the research of CIR by reviewing the studies on how people search and subsequently defines a CIR system and a reference architecture which is described in detail in the rest of the book. Chapter 2 provides a detailed discussion of techniques for evaluating a CIR system - a goal-oriented conversational AI system with a human in the loop. Then Chapters 3 to 7 describe the algorithms and methods for developing the main CIR modules (or sub-systems). In Chapter 3, conversational document search is discussed, which can be viewed as a sub-system of the CIR system. Chapter 4 is about algorithms and methods for query-focused multi-document summarization. Chapter 5 describes various neural models for conversational machine comprehension, which generate a direct answer to a user query based on retrieved query-relevant documents, while Chapter 6 details neural approaches to conversational question answering over knowledge bases, which is fundamental to the knowledge base search module of a CIR system. Chapter 7 elaborates various techniques and models that aim to equip a CIR system with the capability of proactively leading a human-machine conversation. Chapter 8 reviews a variety of commercial systems for CIR and related tasks. It first presents an overview of research platforms and toolkits which enable scientists and practitioners to build conversational experiences, and continues with historical highlights and recent trends in a range of application areas. Chapter 9eventually concludes the book with a brief discussion of research trends and areas for future work.

The primary target audience of the book are the IR and NLP research communities. However, audiences with another background, such as machine learning or human-computer interaction, will also find it an accessible introduction to CIR.

商品描述(中文翻譯)

本書調查了最近在對話式資訊檢索（Conversational Information Retrieval, CIR）方面的進展，重點介紹了過去幾年發展的神經網絡方法。深度學習的進步為自然語言處理（Natural Language Processing, NLP）和對話式人工智慧帶來了巨大的改善，促使出現了大量商業對話服務，這些服務允許自然的口語和打字互動，進一步增加了在資訊檢索中對以人為中心的互動的需求。

本書包含九個章節。第一章通過回顧人們如何搜尋的研究來激勵CIR的研究，並隨後定義了CIR系統及其參考架構，該架構在本書的其餘部分中將詳細描述。第二章詳細討論了評估CIR系統的技術——一個以目標為導向的對話式人工智慧系統，並且有人的參與。接下來的第三至第七章描述了開發主要CIR模組（或子系統）的算法和方法。在第三章中，討論了對話式文件搜尋，這可以被視為CIR系統的一個子系統。第四章則關於針對查詢的多文件摘要的算法和方法。第五章描述了各種對話式機器理解的神經模型，這些模型根據檢索到的與查詢相關的文件生成用戶查詢的直接答案，而第六章詳細介紹了針對知識庫的對話式問答的神經方法，這對CIR系統的知識庫搜尋模組至關重要。第七章闡述了各種技術和模型，旨在使CIR系統具備主動引導人機對話的能力。第八章回顧了各種商業CIR系統及相關任務。它首先介紹了研究平台和工具包的概述，這些平台和工具包使科學家和實踐者能夠構建對話體驗，並繼續介紹各個應用領域的歷史亮點和近期趨勢。第九章最終以對研究趨勢和未來工作的領域的簡要討論結束本書。

本書的主要目標讀者是資訊檢索和自然語言處理的研究社群。然而，具有其他背景的讀者，如機器學習或人機互動，也會發現這是對CIR的易於理解的介紹。

作者簡介

Jianfeng Gao is a Distinguished Scientist and Vice President of Microsoft. He is the head of the Deep Learning group at Microsoft Research, leading the development of AI systems for natural language processing, Web search, vision language understanding, dialogue, and business applications. He is an affiliate professor of Computer Science & Engineering at University of Washington, an IEEE fellow, and a Distinguished Member of ACM.

Chenyan Xiong is a Principal Researcher at Microsoft Research at Redmond. His research area is in the intersection of information retrieval, natural language processing, and deep learning. Chenyan is a co-founder of the TREC Conversational Assistance Track (CAsT) and has developed a series of neural approaches for conversational systems with award winning publications, covering various aspects of conversational IR systems, including conversational search, system initiatives, dialog modeling, and few-shot learning.

Paul Bennett is a Partner Research Manager for the Productivity+Intelligence area in Microsoft Research. His published research has focused on a variety of topics surrounding the use of machine learning in information retrieval - including deep learning for ranking and retrieval, ensemble methods and the combination of information sources, calibration, consensus methods for noisy supervision labels, active learning and evaluation, supervised classification and ranking, crowdsourcing, behavioral modeling and analysis, and personalization. Some of his work has been recognized with awards at SIGIR, CHI, ECIR, and ACM UMAP.

Nick Craswell is a Principal Architect developing Search and related functionality in Microsoft Teams, Outlook and Sharepoint. His research is on the evaluation and optimization of information retrieval systems, particularly in Web search, and more recently relating to conversational interfaces, and deep learning.

作者簡介(中文翻譯)

Jianfeng Gao 是微軟的傑出科學家及副總裁。他是微軟研究院深度學習團隊的負責人，領導自然語言處理、網路搜尋、視覺語言理解、對話及商業應用的 AI 系統開發。他是華盛頓大學計算機科學與工程的兼任教授，IEEE 會士，以及 ACM 的傑出成員。

Chenyan Xiong 是微軟研究院的首席研究員，位於雷德蒙德。他的研究領域位於資訊檢索、自然語言處理和深度學習的交集。Chenyan 是 TREC 對話輔助追蹤 (CAsT) 的共同創辦人，並開發了一系列針對對話系統的神經方法，並發表了多篇獲獎的論文，涵蓋對話資訊檢索系統的各個方面，包括對話搜尋、系統倡議、對話建模和少量學習。

Paul Bennett 是微軟研究院生產力與智慧領域的合作研究經理。他的發表研究專注於機器學習在資訊檢索中的各種主題，包括用於排名和檢索的深度學習、集成方法和資訊來源的組合、標定、對於噪音監督標籤的共識方法、主動學習和評估、監督分類和排名、眾包、行為建模與分析，以及個人化。他的一些工作在 SIGIR、CHI、ECIR 和 ACM UMAP 獲得了獎項。

Nick Craswell 是微軟 Teams、Outlook 和 SharePoint 中開發搜尋及相關功能的首席架構師。他的研究專注於資訊檢索系統的評估和優化，特別是在網路搜尋方面，最近則與對話介面和深度學習相關。

類似商品