Connecting Large Language Models (LLMs) with the ability to leverage APIs (Web Search, Charting, Calculators, Calendar, Flight Search, Hotel Search, Data Lookup, etc. ) is likely to allow us to solve a variety of new hard problems.Several research efforts have made this observation and suggested recipes for LLMs to emit API calls, and proposed mechanisms by which they can generate additional text conditioned on the output for the API call.However, in practice, the focus has been on relatively simple slot-filling tasks that make an API call rather unlocking novel capabilities by combining different tools, reasoning over the response from a tool, making multiple invocations, or complex planning.In this paper, we pose the following question: what does it mean to say that an LLM is proficient at using a set of APIs?We answer this question in the context of structured APIs by defining seven capabilities for API-use.We provide an approach for generating synthetic tasks that exercise each of these capabilities given only the description of an API 1 .We argue that this provides practitioners with a principled way to construct a dataset to evaluate an LLM's ability to use a given set of APIs.Through human evaluations, we show that our approach produces high-quality tasks for each of the seven capabilities.We also describe how we used this approach to on-board new API and create principled evaluation sets for multiple LLM-based products.

Given a web page, extracting an object along with various attributes of interest (e.g. price, publisher, author, and genre for a book) can facilitate a variety of downstream applications such as large-scale knowledge base construction, e-commerce product search, and personalized recommendation. Prior approaches have either relied on computationally expensive visual feature engineering or required large amounts of training data to get to an acceptable precision. In this paper, we propose a novel method, LeArNing TransfErable node RepresentatioNs for Attribute Extraction (LANTERN), to tackle the problem. We model the problem as a tree node tagging task. The key insight is to learn a contextual representation for each node in the DOM tree where the context explicitly takes into account the tree structure of the neighborhood around the node. Experiments on the SWDE public dataset show that LANTERN outperforms the previous state-of-the-art (SOTA) by 1.44% (F1 score) with a dramatically simpler model architecture. Furthermore, we report that utilizing data from a different domain (for instance, using training data about web pages with cars to extract book objects) is surprisingly useful and helps beat the SOTA by a further 1.37%.

Abstract Semantic markup, such as , allows providers on the Web to describe content using a shared controlled vocabulary. This markup is invaluable in enabling a broad range of applications, from vertical search engines, to rich snippets in search results, to actions on emails, to many others. In this paper, we focus on semantic markup for datasets, specifically in the context of developing a vertical search engine for datasets on the Web, Google’s Dataset Search. Dataset Search relies on to identify pages that describe datasets. While was the core enabling technology for this vertical search, we also discovered that we need to address the following problem: pages from 61% of internet hosts that provide markup do not actually describe datasets. We analyze the veracity of dataset markup for Dataset Search’s Web-scale corpus and categorize pages where this markup is not reliable. We then propose a way to drastically increase the quality of the dataset metadata corpus by developing a deep neural-network classifier that identifies whether or not a page with markup is a dataset page. Our classifier achieves 96.7% recall at the 95% precision point. This level of precision enables Dataset Search to circumvent the noise in semantic markup and to use the metadata to provide high quality results to users.

Extracting structured data from HTML documents is a long-studied problem with a broad range of applications like augmenting knowledge bases, supporting faceted search, and providing domain-specific experiences for key verticals like shopping and movies. Previous approaches have either required a small number of examples for each target site or relied on carefully handcrafted heuristics built over visual renderings of websites. In this paper, we present a novel two-stage neural approach, named FreeDOM, which overcomes both these limitations. The first stage learns a representation for each DOM node in the page by combining both the text and markup information. The second stage captures longer range distance and semantic relatedness using a relational neural network. By combining these stages, FreeDOM is able to generalize to unseen sites after training on a small number of seed sites from that vertical without requiring expensive hand-crafted features over visual renderings of the page. Through experiments on a public dataset with 8 different verticals, we show that FreeDOM beats the previous state of the art by nearly 3.7 F1 points on average without requiring features over rendered pages or expensive hand-crafted features.

Recent studies show that an overwhelming majority of emails are machine-generated and sent by businesses to consumers. Many large email services are interested in extracting structured data from such emails to enable intelligent assistants. This allows experiences like being able to answer questions such as “What is the address of my hotel in New York?” or “When does my flight leave?”. A high-quality email classifier is a critical piece in such a system. In this paper, we argue that the rich formatting used in business-to-consumer emails contains valuable information that can be used to learn better representations. Most existing methods focus only on textual content and ignore the rich HTML structure of emails. We introduce RiSER (Richly Structured Email Representation) - an approach for incorporating both the structure and content of emails. RiSER projects the email into a vector representation by jointly encoding the HTML structure and the words in the email. We then use this representation to train a classifier. To our knowledge, this is the first description of a neural technique for combining formatting information along with the content to learn improved representations for richly formatted emails. Experimenting with a large corpus of emails received by users of Gmail, we show that RiSER outperforms strong attention-based LSTM baselines. We expect that these benefits will extend to other corpora with richly formatted documents. We also demonstrate with examples where leveraging HTML structure leads to better predictions.

Extracting structured data from emails can enable several assistive experiences, such as reminding the user when a bill payment is due, answering queries about the departure time of a booked flight, or proactively surfacing an emailed discount coupon while the user is at that store. This paper presents Juicer, a system for extracting information from email that is serving over a billion Gmail users daily. We describe how the design of the system was informed by three key principles: scaling to a planet-wide email service, isolating the complexity to provide a simple experience for the developer, and safeguarding the privacy of users (our team and the developers we support are not allowed to view any single email). We describe the design tradeoffs made in building this system, the challenges faced and the approaches used to tackle them. We present case studies of three extraction tasks implemented on this platform---bill reminders, commercial offers, and hotel reservations---to illustrate the effectiveness of the platform despite challenges unique to each task. Finally, we outline several areas of ongoing research in large-scale machine-learned information extraction from email.