Related papers: SpreadsheetCoder: Formula Prediction from Semi-str…

Spreadsheets are widely used, and studies have shown that most end-user spreadsheets contain nontrivial errors. To improve end-users productivity, recent research proposes the use of a model-driven engineering approach to spreadsheets. In…

Spreadsheets are powerful tools which play a business-critical role in many organizations. However, many bad decisions taken due to faulty spreadsheets show that these tools need serious quality assurance. Furthermore, while collaboration…

This paper describes a new type of spreadsheet which mitigates the errors caused by incorrect range referencing in formulae. This spreadsheet is composed of structured worksheets called tables which contain a hierarchical organization of…

Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods. Training the hierarchical encoder…

Numerous knowledge workers utilize spreadsheets in business, accounting, and finance. However, a lack of systematic documentation methods for spreadsheets hinders automation, collaboration, and knowledge transfer, which risks the loss of…

Hierarchical neural architectures are often used to capture long-distance dependencies and have been applied to many document-level tasks such as summarization, document segmentation, and sentiment analysis. However, effective usage of such…

Winograd Schema Challenge (WSC) was proposed as an AI-hard problem in testing computers' intelligence on common sense representation and reasoning. This paper presents the new state-of-theart on WSC, achieving an accuracy of 71.1%. We…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…

Causal inference, a critical tool for informing business decisions, traditionally relies heavily on structured data. However, in many real-world scenarios, such data can be incomplete or unavailable. This paper presents a framework that…

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…

The accuracy of prosodic structure prediction is crucial to the naturalness of synthesized speech in Mandarin text-to-speech system, but now is limited by widely-used sequence-to-sequence framework and error accumulation from previous word…

Accurate question answering over real spreadsheets remains difficult due to multirow headers, merged cells, and unit annotations that disrupt naive chunking, while rigid SQL views fail on files lacking consistent schemas. We present SQuARE,…

Context of data points, which is usually defined as the other data points in a data set, has been found to play important roles in data representation and classification. In this paper, we study the problem of using context of a data point…

A large amount of information is stored in data tables. Users can search for data tables using a keyword-based query. A table is composed primarily of data values that are organized in rows and columns providing implicit structural…

Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…

We introduce SCDE, a dataset to evaluate the performance of computational models through sentence prediction. SCDE is a human-created sentence cloze dataset, collected from public school English examinations. Our task requires a model to…

Data integration between web sources and relational data is a key challenge faced by data scientists and spreadsheet users. There are two main challenges in programmatically joining web data with relational data. First, most websites do not…

Understanding tables is an important aspect of natural language understanding. Existing models for table understanding require linearization of the table structure, where row or column order is encoded as an unwanted bias. Such spurious…

Accurate recommendation and reliable explanation are two key issues for modern recommender systems. However, most recommendation benchmarks only concern the prediction of user-item ratings while omitting the underlying causes behind the…

In this work we propose a simple and efficient framework for learning sentence representations from unlabelled data. Drawing inspiration from the distributional hypothesis and recent work on learning sentence representations, we reformulate…