Airbnb开发了LAEP系统，利用机器学习和自然语言处理技术从非结构化文本数据中提取有用的房源信息。LAEP系统包括命名实体识别、实体映射和实体评分组件，能够从文本中提取房源属性并将其映射到标准实体名称。该系统应用于下游应用程序，帮助团队发现新的房源类别和重要的房源属性，提升房源理解和服务质量。

在这篇文章中，我们将讨论如何通过使用 HTTP 流式传输，将 Airbnb.com 的字节流尽可能快地传输到你的浏览器中。

首先让我们了解一下什么是流式传输。想象一下我们手头有一个水龙头和两种选择：

• 先将一个大杯子装满，然后一次性全部倒入管道（“缓冲”策略）
• 将水龙头直接接到管道上（“流式”策略）

在缓冲策略中，所有的事情都是按顺序进行的：服务器首先生成整个响应并存入缓冲区（装满杯子），然后用更多的时间通过网络把响应发送到客户端（倒入管道）。而流式策略则是并行进行的，我们将响应分解成多个块，一旦某块准备好就立即发送出去。在前一个块仍在发送的同时，服务器就可以开始处理下一个块，而客户端（如浏览器）也可以在响应还未完全接收到之前就开始处理响应。

How Airbnb adopted SwiftUI in our iOS app.

爱彼迎（Airbnb）每天根据搜索结果将数百万位房客和房东连接在一起，搜索结果通常由一个基于神经网络的排序算法决定，这个算法原本只擅长为房客选择单个房源，最近我们改进了这个算法的神经网络，更好地提供包含多个房源的搜索结果，增强搜索结果中的房源多样性。

How Airbnb evolved our data catalog into a platform for managing and governing our data warehouse at scale.

现代人工智能（AI）中增长最快的领域之一是 AI 文本生成模型。顾名思义，这些模型的作用就是可以生成自然语言。在此之前，大多数工业级自然语言处理（NLP）模型都是分类器，或者在机器学习（ML）文献中可能被称为的判别模型。然而，在最近几年中，基于大规模语言模型的生成模型正在迅速获得关注，并且从根本上改变了我们制定 ML 问题的方式。这些生成模型现在可以通过大规模的预训练获得一些领域知识，然后生成高质量的文本 - 例如回答问题或复述一段内容。

在爱彼迎 (Airbnb)，我们在把文本生成模型应用到社区支持产品中投入了大量的精力，这让我们的产品具备了许多新的功能和使用场景。本文将详细讨论其中三个用例。但首先，让我们先讨论一下为什么文本生成模型非常适合我们的产品。

Journey Platform: Low-code notification workflow platform that allows technical and non-technical users to create complex workflows through a simple drag and drop user interface.

How Airbnb leverages AWS, Packer, and Terraform to update macOS on hundreds of Cl machines in hours instead of days.

A case study in service mesh performance optimization.

Airbnb 2022 release introduced Categories, a browse focused product that allows the user to seek inspiration by browsing collections of homes revolving around a common theme, such as Lakefront, Countryside, Golf, Desert, National Parks, Surfing, etc. In Part I of our Categories Blog Series we covered the high level approach to creating Categories and showcasing them in the product. In this Part II we will describe the ML Categorization work in more detail.

Throughout the post we use the Lakefront category as a running example to showcase the ML-powered category development process. Similar process was applied for other categories, with category specific nuances. For example, some categories rely more on points of interests, while others more on structured listing signals, image data, etc.

Airbnb connects millions of guests and Hosts everyday. Most of these connections are forged through search, the results of which are determined by a neural network–based ranking algorithm. While this neural network is adept at selecting individual listings for guests, we recently improved the neural network to better select the overall collection of listings that make up a search result. In this post, we dive deeper into this recent breakthrough that enhances the diversity of listings in search results.

At Airbnb, we have been consciously designing and building products to be equally usable by all users. Making our mobile apps and websites more accessible not only aligns with our company’s mission of creating a world where people can belong anywhere, but also supports the civil rights of people with disabilities and complies with the law.

In this article, we highlight some of the efforts we have made to make the app more accessible, for example, labeling UI elements, grouping related content, supporting large font scale, providing heading and page names. The Airbnb app is one of the most popular travel apps with millions of users and supports many features. Making such a complex app more accessible is a huge endeavor that we are continuously working on.

在 2020 年 Hasura 的企业 GraphQL 会议上，Airbnb爱彼迎 展示了 Viaduct，一个面向数据的服务网格（Service Mesh） ，其为爱彼迎基于微服务的 SOA（Service-Oriented Architecture）的模块化带来了阶梯性的提升。我们将在这篇文章中介绍 Viaduct 背后的思想及大致运作原理。

How Airbnb is applying declarative design patterns to rapidly build fluid transition animations.

How Airbnb uses visual attributes to enhance the Guest and Host experience.

Leveraging text generation models to build more effective, scalable customer support products.