相关论文: TabGenie: A Toolkit for Table-to-Text Generation

In the 20th century, newly invented technical artifacts were connected to form large-scale complex engineering systems. Furthermore, the interactions found within these networked systems has grown in both degree as well as heterogeneity.…

This paper argues that generating output tokens is more effective than using pooled representations for prediction tasks because token-level generation retains more mutual information. Since LLMs are trained on massive text corpora using…

LLMs are vulnerable to hallucinations, and thus their outputs generally require laborious human verification for high-stakes applications. To this end, we propose symbolically grounded generation (SymGen) as a simple approach for enabling…

In the context of the Text-to-SQL task, table and column descriptions are crucial for bridging the gap between natural language and database schema. This report proposes a method for automatically generating effective database descriptions…

Exams are a fundamental test of expert-level intelligence and require integrated understanding, reasoning, and generation. Existing exam-style benchmarks mainly focus on understanding and reasoning tasks, and current generation benchmarks…

Tabular question answering (TQA) presents a challenging setting for neural systems by requiring joint reasoning of natural language with large amounts of semi-structured data. Unlike humans who use programmatic tools like filters to…

Generating questions along with associated answers from a text has applications in several domains, such as creating reading comprehension tests for students, or improving document search by providing auxiliary questions and answers based…

Precisely defining the terminology is the first step in scientific communication. Developing neural text generation models for definition generation can circumvent the labor-intensity curation, further accelerating scientific discovery.…

Text-to-video (T2V) generation technology holds potential to transform multiple domains such as education, marketing, entertainment, and assistive technologies for individuals with visual or reading comprehension challenges, by creating…

The evidence is growing that machine and deep learning methods can learn the subtle differences between the language produced by people with various forms of cognitive impairment such as dementia and cognitively healthy individuals.…

Imitation learning field requires expert data to train agents in a task. Most often, this learning approach suffers from the absence of available data, which results in techniques being tested on its dataset. Creating datasets is a…

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…

We present an open-source and extensible knowledge extraction toolkit DeepKE, supporting complicated low-resource, document-level and multimodal scenarios in the knowledge base population. DeepKE implements various information extraction…

Deep learning has achieved impressive performance in many domains, such as computer vision and natural language processing, but its advantage over classical shallow methods on tabular datasets remains questionable. It is especially…

Fine-tuning for large language models (LLMs) typically requires substantial amounts of high-quality supervised data, which is both costly and labor-intensive to acquire. While synthetic data generation has emerged as a promising solution,…

There is an ongoing need for scalable tools to aid researchers in both retrospective and prospective standardization of discrete entity types -- such as disease names, cell types or chemicals -- that are used in metadata associated with…

The information age has brought a deluge of data. Much of this is in text form, insurmountable in scope for humans and incomprehensible in structure for computers. Text mining is an expanding field of research that seeks to utilize the…

We introduce SPAGHETTI: Semantic Parsing Augmented Generation for Hybrid English information from Text Tables and Infoboxes, a hybrid question-answering (QA) pipeline that utilizes information from heterogeneous knowledge sources, including…

Neural data-to-text generation models have achieved significant advancement in recent years. However, these models have two shortcomings: the generated texts tend to miss some vital information, and they often generate descriptions that are…

End-to-end neural data-to-text (D2T) generation has recently emerged as an alternative to pipeline-based architectures. However, it has faced challenges in generalizing to new domains and generating semantically consistent text. In this…