Table to text generation with accurate content copying

Abstract

Generating fluent, coherent, and informative text from structured data is called table-to-text generation. Copying words from the table is a common method to solve the “out-of-vocabulary” problem, but it’s difficult to achieve accurate copying. In order to overcome this problem, we invent an auto-regressive framework based on the transformer that combines a copying mechanism and language modeling to generate target texts. Firstly, to make the model better learn the semantic relevance between table and text, we apply a word transformation method, which incorporates the field and position information into the target text to acquire the position of where to copy. Then we propose two auxiliary learning objectives, namely table-text constraint loss and copy loss. Table-text constraint loss is used to effectively model table inputs, whereas copy loss is exploited to precisely copy word fragments from a table. Furthermore, we improve the text search strategy to reduce the probability of generating incoherent and repetitive sentences. The model is verified by experiments on two datasets and better results are obtained than the baseline model. On WIKIBIO, the result is improved from 45.47 to 46.87 on BLEU and from 41.54 to 42.28 on ROUGE. On ROTOWIRE, the result is increased by 4.29% on CO metric, and 1.93 points higher on BLEU.

Natural Language Explanations for Machine Learning Classification Decisions

“…Structured data-to-text generation is an NLG task where descriptive texts are generated in natural language, verbalizing the information from source data such as graphs and tables [17]- [19]. The ML algorithms and techniques employed for generating text from structured data can be classified into two main groups: pipelined and end-to-end techniques [20]- [22]. Earlier NLG works predominantly employed pipeline-based techniques where the text generation process was divided into different stages: content determination, text planning, sentence planning, and surface realization modules [23], [24].…”

ReTAG: Reasoning Aware Table to Analytic Text Generation

“…In the task of Table to Text Generation (Yang et al, 2021), the output summaries usually are of two types: Descriptive and Analytical. A descriptive summary is formed with only information contained within the selected cells of the table and nothing else (Refer Table 1).…”