paper-with-me

홈 › Papers

Towards Table-to-Text Generation with Numerical Reasoning

2021-08-01 · ACL 2021 5 · Lya Hulliyyatus Suadaa, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura, Hiroya Takamura

Recent neural text generation models have shown significant improvement in generating descriptive text from structured data such as table formats. One of the remaining important challenges is generating more analytical descriptions that can be inferred from facts in a data source. The use of a template-based generator and a pointer-generator is among the potential alternatives for table-to-text generators. In this paper, we propose a framework consisting of a pre-trained model and a copy mechanism. The pre-trained models are fine-tuned to produce fluent text that is enriched with numerical reasoning. However, it still lacks fidelity to the table contents. The copy mechanism is incorporated in the fine-tuning step by using general placeholders to avoid producing hallucinated phrases that are not supported by a table while preserving high fluency. In summary, our contributions are (1) a new dataset for numerical table-to-text generation using pairs of a table and a paragraph of a table description with richer inference from scientific papers, and (2) a table-to-text generation framework enriched with numerical reasoning.

📄 PDF Abstract BibTeX

Code (1)

titech-nlp/numeric-nlg 공식 구현

Tasks

DescriptiveTable-to-Text GenerationText Generation

Similar Papers 제목 키워드 기반

FLAP: Table-to-Text Generation with Feature Indication and Numerical Reasoning Pretraining

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Recent neural models have shown success in table-to-text generation. However, the performance of content selection and content planning is still unsatisfactory. In this paper, we propose an effective framework with Featu…

Table-to-Text GenerationText Generation

DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data

2022-11-23 · Xiao Li, Yin Zhu, Sichen Liu, Jiangzhou Ju 외

Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community. To generate an executable reasoning program consisting of math and table operations to…

MathRerankingRetrieval

Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder

2022-09-16 · COLING 2022 10 · Fangyu Lei, Shizhu He, Xiang Li, Jun Zhao 외

In the real-world question answering scenarios, hybrid form combining both tabular and textual contents has attracted more and more attention, among which numerical reasoning problem is one of the most typical and challe…

DecoderModels AlignmentQuestion Answering

Document-Level Numerical Reasoning across Single and Multiple Tables in Financial Reports

2026-04-04 · Yi-Cheng Wang, Wei-An Wang, Chu-Song Chen arxiv

Despite the strong language understanding abilities of large language models (LLMs), they still struggle with reliable question answering (QA) over long, structured documents, particularly for numerical reasoning. Financ…

Question Answering

Learning to Reason for Text Generation from Scientific Tables

2021-04-16 · Nafise Sadat Moosavi, Andreas Rücklé, Dan Roth, Iryna Gurevych

In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions. Describing scientifi…

Arithmetic ReasoningArticlesData-to-Text GenerationText Generation