Related papers: Challenges in Data-to-Document Generation

Teaching neural models to generate narrative coherent texts is a critical problem. Recent pre-trained language models have achieved promising results, but there is still a gap between human written texts and machine-generated outputs. In…

In the last two decades, the landscape of text generation has undergone tremendous changes and is being reshaped by the success of deep learning. New technologies for text generation ranging from template-based methods to neural…

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…

We present a novel approach for structured data-to-text generation that addresses the limitations of existing methods that primarily focus on specific types of structured data. Our proposed method aims to improve performance in multi-task…

With a neural sequence generation model, this study aims to develop a method of writing the patient clinical texts given a brief medical history. As a proof-of-a-concept, we have demonstrated that it can be workable to use medical concept…

Neural text generation models are often autoregressive language models or seq2seq models. These models generate text by sampling words sequentially, with each word conditioned on the previous word, and are state-of-the-art for several…

Charts are commonly used for exploring data and communicating insights. Generating natural language summaries from charts can be very helpful for people in inferring key insights that would otherwise require a lot of cognitive and…

In this tutorial, we focus on text-to-text generation, a class of natural language generation (NLG) tasks, that takes a piece of text as input and then generates a revision that is improved according to some specific criteria (e.g.,…

Recent advances in large pre-trained language models have demonstrated strong results in generating natural languages and significantly improved performances for many natural language generation (NLG) applications such as machine…

We classify and re-examine some of the current approaches to improve the performance-computes trade-off of language models, including (1) non-causal models (such as masked language models), (2) extension of batch length with efficient…

Recently, neural models led to significant improvements in both machine translation (MT) and natural language generation tasks (NLG). However, generation of long descriptive summaries conditioned on structured data remains an open…

Document grounded generation is the task of using the information provided in a document to improve text generation. This work focuses on two different document grounded generation tasks: Wikipedia Update Generation task and Dialogue…

Expressing natural language descriptions of structured facts or relations -- data-to-text generation (D2T) -- increases the accessibility of structured knowledge repositories. Previous work shows that pre-trained language models(PLMs)…

The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively,…

Traditional approaches to extractive summarization rely heavily on human-engineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a general framework for…

We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from "neighbor" source-target pairs. Unlike recent work that conditions on retrieved neighbors but generates text token-by-token,…

We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for…

Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent…

Search typically relies on keyword queries, but these are often semantically ambiguous. We propose to overcome this by offering users natural language questions, based on their keyword queries, to disambiguate their intent. This…

Large language models have shown unprecedented abilities in generating linguistically coherent and syntactically correct natural language output. However, they often return incorrect and inconsistent answers to input questions. Due to the…