Related papers: DocuT5: Seq2seq SQL Generation with Table Document…

Text-to-SQL semantic parsing has made significant progress in recent years, with various models demonstrating impressive performance on the challenging Spider benchmark. However, it has also been shown that these models often struggle to…

Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS (Herzig et al., 2020). A major limitation of these architectures is that they are constrained to classification-like tasks…

Structured (dictionary-like) data presents challenges for left-to-right language models, as they can struggle with structured entities for a wide variety of reasons such as formatting and sensitivity to the order in which attributes are…

Large Language Models (LLMs) have shown remarkable success in supporting a wide range of knowledge-intensive tasks. In specialized domains, there is growing interest in leveraging LLMs to assist subject matter experts with domain-specific…

Scientific document understanding is challenging as the data is highly domain specific and diverse. However, datasets for tasks with scientific text require expensive manual annotation and tend to be small and limited to only one or a few…

Recently, generative retrieval emerges as a promising alternative to traditional retrieval paradigms. It assigns each document a unique identifier, known as DocID, and employs a generative model to directly generate the relevant DocID for…

Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set generation. Seq2Seq models, a popular choice for set…

Large ground-truth datasets and recent advances in deep learning techniques have been useful for layout detection. However, because of the restricted layout diversity of these datasets, training on them requires a sizable number of…

NoSQL databases have become increasingly popular due to their outstanding performance in handling large-scale, unstructured, and semi-structured data, highlighting the need for user-friendly interfaces to bridge the gap between…

Document-grounded dialogue systems aim to answer user queries by leveraging external information. Previous studies have mainly focused on handling free-form documents, often overlooking structured data such as lists, which can represent a…

There is currently a significant gap between the performance of fine-tuned models and prompting approaches using Large Language Models (LLMs) on the challenging task of text-to-SQL, as evaluated on datasets such as Spider. To improve the…

Enterprises commonly deploy heterogeneous database systems, each of which owns a distinct SQL dialect with different syntax rules, built-in functions, and execution constraints. However, most existing NL2SQL methods assume a single dialect…

Code generation aims to generate a code snippet automatically from natural language descriptions. Generally, the mainstream code generation methods rely on a large amount of paired training data, including both the natural language…

Medical dialogue generation aims to generate responses according to a history of dialogue turns between doctors and patients. Unlike open-domain dialogue generation, this requires background knowledge specific to the medical domain.…

Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challenging. However, most existing benchmarks evaluate models only at…

With the recent advancements in deep learning, neural solvers have gained promising results in solving math word problems. However, these SOTA solvers only generate binary expression trees that contain basic arithmetic operators and do not…

While unsupervised domain adaptation methods based on deep architectures have achieved remarkable success in many computer vision tasks, they rely on a strong assumption, i.e. labeled source data must be available. In this work we overcome…

Efficient querying and analysis of large tabular datasets remain significant challenges, especially for users without expertise in programming languages like SQL. Text-to-SQL approaches have shown promising performance on benchmark data;…

We propose a novel framework to facilitate the on-demand design of data-centric systems by exploiting domain knowledge from an existing ontology. Its key ingredient is a process that we call focusing, which allows to obtain a schema for a…

Multi-document Multi-entity Question Answering inherently demands models to track implicit logic between multiple entities across scattered documents. However, existing Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG)…