iTBLS: A Dataset of Interactive Conversations Over Tabular Information
This work addresses the challenge of interactive tabular data processing for researchers and practitioners in natural language processing, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of natural-language manipulation of tabular information by introducing the iTBLS dataset for interactive conversations and a novel framework that reformulates tabular operations as question-answering, resulting in up to 13% improvement in Exact-Match accuracy and up to 16% improvement in BERTScores compared to prior state-of-the-art on text-to-table tasks.
This paper introduces Interactive Tables (iTBLS), a dataset of interactive conversations that focuses on natural-language manipulation of tabular information sourced from academic pre-prints on ArXiv. The iTBLS dataset consists of three types of tabular tasks -- interpretation, modification, and generation. Interpretation focuses on tabular understanding, modification focuses on manipulating tabular information, and generation focuses on the addition of new natural-language evidence. In addition, the paper presents a novel framework that reformulates tabular operations as question-answering, where an appropriate question is formulated based on the nature of interaction and the question is answered using the user request as evidence. The developed approach results in an improvement on all tasks on a sequence-to-sequence modeling baseline on iTBLS. In addition, the question-answering-based reformulation is applied to datasets from prior work for the text-to-table task where textual paragraphs are summarized into tables. The novel approach results in up to 13% improvement in Exact-Match accuracy and up to 16% improvement in BERTScores compared to the prior state-of-the-art.