Neural data-to-text generation: A comparison between pipeline and end-to-end architectures
Traditionally, most data-to-text applications have been designed using a modular pipeline architecture, in which non-linguistic input data is converted into natural language through several intermediate transformations. In contrast, recent neural models for data-to-text generation have been proposed as end-to-end approaches, where the non-linguistic input is rendered in natural language with much less explicit intermediate representations in-between. This study introduces a systematic comparison between neural pipeline and end-to-end data-to-text approaches for the generation of text from RDF triples. Both architectures were implemented making use of state-of-the art deep learning methods as the encoder-decoder Gated-Recurrent Units (GRU) and Transformer. Automatic and human evaluations together with a qualitative analysis suggest that having explicit intermediate steps in the generation process results in better texts than the ones generated by end-to-end approaches. Moreover, the pipeline models generalize better to unseen inputs. Data and code are publicly available.
Code (1)
Tasks
Data-to-Text GenerationDecoderText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Lights, Camera, Consistency: A Multistage Pipeline for Character-Stable AI Video Stories
Generating long, cohesive video stories with consistent characters is a significant challenge for current text-to-video AI. We introduce a method that approaches video generation in a filmmaker-like manner. Instead of cr…
Video GenerationCan LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA
LLM-as-a-Judge and self-evaluation pipelines implicitly assume that evaluation is easier than generation. We test this in a controlled in-context QA setting where a context passage is the sole information source and each…
Joint Transcription and Decryption of Images of Encrypted Handwritten Documents: A Comparison with the Traditional Pipeline
Historical encrypted manuscripts present a challenging problem at the intersection of cryptology, linguistics, paleography, and computer vision. Current automatic decipherment approaches usually rely on a two-stage pipel…
Synthetic Data GenerationDoes Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs
In this work, our aim is to provide a structured answer in natural language to a complex information need. Particularly, we envision using generative models from the perspective of data-to-text generation. We propose the…
Data-to-Text GenerationRetrievalText GenerationCreating a Real-Time, Reproducible Event Dataset
The generation of political event data has remained much the same since the mid-1990s, both in terms of data acquisition and the process of coding text into data. Since the 1990s, however, there have been significant imp…