Related papers: Top-Down Tree Structured Text Generation
Generating sports game reports from structured tables is a complex table-to-text task that demands both precise data interpretation and fluent narrative generation. Traditional model-based approaches require large, annotated datasets, while…
Story generation is a task that aims to automatically produce multiple sentences to make up a meaningful story. This task is challenging because it requires high-level understanding of semantic meaning of sentences and causality of story…
Recent approaches to data-to-text generation have adopted the very successful encoder-decoder architecture or variants thereof. These models generate text which is fluent (but often imprecise) and perform quite poorly at selecting…
The dominant language modeling paradigm handles text as a sequence of discrete tokens. While that approach can capture the latent structure of the text, it is inherently constrained to sequential dynamics for text generation. We propose a…
Extractive compression is a challenging natural language processing problem. This work contributes by formulating neural extractive compression as a parse tree transduction problem, rather than a sequence transduction task. Motivated by…
Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines which use (externally provided) syntax trees to drive the…
Transcribing structured data into natural language descriptions has emerged as a challenging task, referred to as "data-to-text". These structures generally regroup multiple elements, as well as their attributes. Most attempts rely on…
Automatically generating debates is a challenging task that requires an understanding of arguments and how to negate or support them. In this work we define debate trees and paths for generating debates while enforcing a high level…
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.,…
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…
An important component of achieving language understanding is mastering the composition of sentence meaning, but an immediate challenge to solving this problem is the opacity of sentence vector representations produced by current neural…
Text generation has become more accessible than ever, and the increasing interest in these systems, especially those using large language models, has spurred an increasing number of related publications. We provide a systematic literature…
Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents…
Neural text generation metamorphosed into several critical natural language applications ranging from text completion to free form narrative generation. In order to progress research in text generation, it is critical to absorb the existing…
Writers generally rely on plans or sketches to write long stories, but most current language models generate word by word from left to right. We explore coarse-to-fine models for creating narrative texts of several hundred words, and…
Data-to-text generation can be conceptually divided into two parts: ordering and structuring the information (planning), and generating fluent language describing the information (realization). Modern neural generation systems conflate…
With a growing need for robust and general discourse structures in many downstream tasks and real-world applications, the current lack of high-quality, high-quantity discourse trees poses a severe shortcoming. In order the alleviate this…
Nowadays, the behavior tree is gaining popularity as a representation for robot tasks due to its modularity and reusability. Designing behavior-tree tasks manually is time-consuming for robot end-users, thus there is a need for…
Recently, the text-to-table generation task has attracted increasing attention due to its wide applications. In this aspect, the dominant model formalizes this task as a sequence-to-sequence generation task and serializes each table into a…
Neural language models are a critical component of state-of-the-art systems for machine translation, summarization, audio transcription, and other tasks. These language models are almost universally autoregressive in nature, generating…