String data is common in real-world datasets: 67.6% of values in a sample of 1.8 million real Excel spreadsheets from the web were represented as text. Automatically cleaning such string data can have a significant impact on users. Previous approaches are limited to error detection, require that the user provides annotations, examples, or constraints to fix the errors, and focus independently on syntactic errors or semantic errors in strings, but ignore that strings often contain both syntactic and semantic substrings. We introduce DataVinci, a fully unsupervised string data error detection and repair system. DataVinci learns regular-expression-based patterns that cover a majority of values in a column and reports values that do not satisfy such majority patterns as data errors. DataVinci can automatically derive edits to the data error based on the majority patterns and using row tuples associated with majority values as examples. To handle strings with both syntactic and semantic substrings, DataVinci uses an LLM to abstract (and re-concretize) portions of strings that are semantic. Because not all data columns can result in majority patterns, when available, DataVinci can leverage execution information from an existing data program (which uses the target data as input) to identify and correct data repairs that would not otherwise be identified. DataVinci outperforms eleven baseline systems on both data error detection and repair as demonstrated on four existing and new benchmarks.

Modern email clients support predicate-based folder assignment rules that can automatically organize emails. Unfortunately, users still need to write these rules manually. Prior machine learning approaches have framed automatically assigning email to folders as a classification task and do not produce symbolic rules. Prior inductive logic programming (ILP) approaches, which generate symbolic rules, fail to learn efficiently in the online environment needed for email management. To close this gap, we present EmFORE, an online system that learns symbolic rules for email classification from observations. Our key insights to do this successfully are: (1) learning rules over a folder abstraction that supports quickly determining candidate predicates to add or replace terms in a rule, (2) ensuring that rules remain consistent with historical assignments, (3) ranking rule updates based on existing predicate and folder name similarity, and (4) building a rule suppression model to avoid surfacing low-confidence folder predictions while keeping the rule for future use. We evaluate on two popular public email corpora and compare to 13 baselines, including state-of-the-art folder assignment systems, incremental machine learning, ILP and transformer-based approaches. We find that EmFORE performs significantly better, updates four orders of magnitude faster, and is more robust than existing methods and baselines.

Formatting is an important property in tables for visualization, presentation, and analysis. Spreadsheet software allows users to automatically format their tables by writing data-dependent conditional formatting (CF) rules. Writing such rules is often challenging for users as it requires understanding and implementing the underlying logic. We present FormaT5, a transformer-based model that can generate a CF rule given the target table and a natural language description of the desired formatting logic. We find that user descriptions for these tasks are often under-specified or ambiguous, making it harder for code generation systems to accurately learn the desired rule in a single step. To tackle this problem of under-specification and minimise argument errors, FormaT5 learns to predict placeholders though an abstention objective. These placeholders can then be filled by a second model or, when examples of rows that should be formatted are available, by a programming-by-example system. To evaluate FormaT5 on diverse and real scenarios, we create an extensive benchmark of 1053 CF tasks, containing real-world descriptions collected from four different sources. We release our benchmarks to encourage research in this area. Abstention and filling allow FormaT5 to outperform 8 different neural approaches on our benchmarks, both with and without examples. Our results illustrate the value of building domain-specific learning systems.

Spreadsheets are widely used for table manipulation and presentation. Stylistic formatting of these tables is an important property for presentation and analysis. As a result, popular spreadsheet software, such as Excel, supports automatically formatting tables based on rules. Unfortunately, writing such formatting rules can be challenging for users as it requires knowledge of the underlying rule language and data logic. We present Cornet, a system that tackles the novel problem of automatically learning such formatting rules from user-provided formatted cells. Cornet takes inspiration from advances in inductive programming and combines symbolic rule enumeration with a neural ranker to learn conditional formatting rules. To motivate and evaluate our approach, we extracted tables with over 450K unique formatting rules from a corpus of over 1.8M real worksheets. Since we are the first to introduce the task of automatically learning conditional formatting rules, we compare Cornet to a wide range of symbolic and neural baselines adapted from related domains. Our results show that Cornet accurately learns rules across varying setups. Additionally, we show that in some cases Cornet can find rules that are shorter than those written by users and can also discover rules in spreadsheets that users have manually formatted. Furthermore, we present two case studies investigating the generality of our approach by extending Cornet to related data tasks (e.g., filtering) and generalizing to conditional formatting over multiple columns.

Data management and analysis tasks are often carried out using spreadsheet software. A popular feature in most spreadsheet platforms is the ability to define data-dependent formatting rules. These rules can express actions such as "color red all entries in a column that are negative" or "bold all rows not containing error or failure". Unfortunately, users who want to exercise this functionality need to manually write these conditional formatting (CF) rules. We introduce Cornet, a system that automatically learns such conditional formatting rules from user examples. Cornet takes inspiration from inductive program synthesis and combines symbolic rule enumeration, based on semi-supervised clustering and iterative decision tree learning, with a neural ranker to produce accurate conditional formatting rules. In this demonstration, we show Cornet in action as a simple add-in to Microsoft's Excel. After the user provides one or two formatted cells as examples, Cornet generates formatting rule suggestions for the user to apply to the spreadsheet.

Data profiling refers to the task of extracting technical metadata or profiles and has numerous applications such as data understanding, validation, integration, and cleaning. While a number of data profiling primitives exist in the literature, most of them are limited to categorical attributes. A few techniques consider numerical attributes; but, they either focus on simple relationships involving a pair of attributes (e.g., correlations) or convert the continuous semantics of numerical attributes to a discrete semantics, which results in information loss. To capture more complex relationships involving the numerical attributes, we developed a new data-profiling primitive called conformance constraints, which can model linear arithmetic relationships involving multiple numerical attributes. We present CoCo, a system that allows interactive discovery and exploration of Conformance Constraints for understanding trends involving the numerical attributes of a dataset, with a particular focus on the application of data cleaning. Through a simple interface, CoCo enables the user to guide conformance constraint discovery according to their preferences. The user can examine to what extent a new, possibly dirty, dataset satisfies or violates the discovered conformance constraints. Further, CoCo provides useful suggestions for cleaning dirty data tuples, where the user can interactively alter cell values, and verify by checking change in conformance constraint violation due to the alteration. We demonstrate how CoCo can help in understanding trends in the data and assist the users in interactive data cleaning, using conformance constraints.

The reliability of inferences made by data-driven systems hinges on the data's continued conformance to the systems' initial settings and assumptions. When serving data (on which we want to apply inference) deviates from the profile of the initial training data, the outcome of inference becomes unreliable. We introduce conformance constraints, a new data profiling primitive tailored towards quantifying the degree of non-conformance, which can effectively characterize if inference over that tuple is untrustworthy. Conformance constraints are constraints over certain arithmetic expressions (called projections) involving the numerical attributes of a dataset, which existing data profiling primitives such as functional dependencies and denial constraints cannot model. Our key finding is that projections that incur low variance on a dataset construct effective conformance constraints. This principle yields the surprising result that low-variance components of a principal component analysis, which are usually discarded for dimensionality reduction, generate stronger conformance constraints than the high-variance components. Based on this result, we provide a highly scalable and efficient technique--linear in data size and cubic in the number of attributes--for discovering conformance constraints for a dataset. To measure the degree of a tuple's non-conformance with respect to a dataset, we propose a quantitative semantics that captures how much a tuple violates the conformance constraints of that dataset. We demonstrate the value of conformance constraints on two applications: trusted machine learning and data drift. We empirically show that conformance constraints offer mechanisms to (1) reliably detect tuples on which the inference of a machine-learned model should not be trusted, and (2) quantify data drift more accurately than the state of the art.

In data-driven systems, we often encounter tuples on which the predictions of a machine-learned model are untrustworthy. A key cause of such untrustworthiness is non-conformance of a new tuple with respect to the training dataset. To check conformance, we introduce a novel concept of data invariant, which captures a set of implicit constraints that all tuples of a dataset satisfy: a test tuple is non-conforming if it violates the data invariants. Data invariants model complex relationships among multiple attributes; but do not provide interpretable explanations of non-conformance. We present ExTuNe, a system for Explaining causes of Tuple Non-conformance. Based on the principles of causality, ExTuNe assigns responsibility to the attributes for causing non-conformance. The key idea is to observe change in invariant violation under intervention on attribute-values. Through a simple interface, ExTuNe produces a ranked list of the test tuples based on their degree of non-conformance and visualizes tuple-level attribute responsibility for non-conformance through heat maps. ExTuNe further visualizes attribute responsibility, aggregated over the test tuples. We demonstrate how ExTuNe can detect and explain tuple non-conformance and assist the users to make careful decisions towards achieving trusted machine learning.

Automatic synthesis of web data extraction programs has been explored in a variety of settings, but in practice there remain various robustness and usability challenges. In this work we present a novel program synthesis approach which combines the benefits of deductive and enumerative synthesis strategies, yielding a semi-supervised technique with which concise programs expressible in standard languages can be synthesized from very few examples. We demonstrate improvement over existing techniques in terms of overall accuracy, number of examples required, and program complexity. Our method has been deployed as a web extraction feature in the mass market Microsoft Power BI product.

We show how to programmatically model processes that humans use when extracting answers to queries (e.g., "Who invented typewriter?", "List of Washington national parks") from semi-structured Web pages returned by a search engine. This modeling enables various applications including automating repetitive search tasks, and helping search engine developers design micro-segments of factoid questions.

Millions of computer end users need to perform tasks over tabular spreadsheet data, yet lack the programming knowledge to do such tasks automatically. This paper describes the design and implementation of a robust natural language based interface to spreadsheet programming. Our methodology involves designing a typed domain-specific language (DSL) that supports an expressive algebra of map, filter, reduce, join, and formatting capabilities at a level of abstraction appropriate for non-expert users. The key algorithmic component of our methodology is a translation algorithm for converting a natural language specification in the context of a given spreadsheet to a ranked set of likely programs in the DSL. The translation algorithm leverages the spreadsheet spatial and temporal context to assign interpretations to specifications with implicit references, and is thus robust to a variety of ways in which end users can express the same task. The translation algorithm builds over ideas from keyword programming and semantic parsing to achieve both high precision and high recall. We implemented the system as an Excel add-in called NLyze that supports a rich user interaction model including annotating the user's natural language specification and explaining the synthesized DSL programs by paraphrasing them into structured English. We collected a total of 3570 English descriptions for 40 spreadsheet tasks and our system was able to generate the intended interpretation as the top candidate for 94% (97 for the top 3) of those instances.

We address the problem of performing semantic transformations on strings, which may represent a variety of data types (or their combination) such as a column in a relational table, time, date, currency, etc. Unlike syntactic transformations, which are based on regular expressions and which interpret a string as a sequence of characters, semantic transformations additionally require exploiting the semantics of the data type represented by the string, which may be encoded as a database of relational tables. Manually performing such transformations on a large collection of strings is error prone and cumbersome, while programmatic solutions are beyond the skill-set of end-users. We present a programming by example technology that allows end-users to automate such repetitive tasks. We describe an expressive transformation language for semantic manipulation that combines table lookup operations and syntactic manipulations. We then present a synthesis algorithm that can learn all transformations in the language that are consistent with the user-provided set of input-output examples. We have implemented this technology as an add-in for the Microsoft Excel Spreadsheet system and have evaluated it successfully over several benchmarks picked from various Excel help-forums.