Summarizing and Exploring Tabular Data in Conversational Search

Tabular data provide answers to a significant portion of search queries. However, reciting an entire result table is impractical in conversational search systems. We propose to generate natural language summaries as answers to describe the complex information contained in a table. Through crowdsourcing experiments, we build a new conversation-oriented, open-domain table summarization dataset. It includes annotated table summaries, which not only answer questions but also help people explore other information in the table. We utilize this dataset to develop automatic table summarization systems as SOTA baselines. Based on the experimental results, we identify challenges and point out future research directions that this resource will support.

[1]  Philip S. Yu,et al.  TabSum: a flexible and dynamic table summarization approach , 2000, Proceedings 20th IEEE International Conference on Distributed Computing Systems.

[2]  K. Selçuk Candan,et al.  AlphaSum: size-constrained table summarization using value lattices , 2009, EDBT '09.

[3]  Maguelonne Teisseire,et al.  Knowledge-Free Table Summarization , 2013, DaWaK.

[4]  Christos Faloutsos,et al.  TSum: fast, principled table summarization , 2013, ADKDD '13.

[5]  Percy Liang,et al.  Compositional Semantic Parsing on Semi-Structured Tables , 2015, ACL.

[6]  Hang Li,et al.  “ Tony ” DNN Embedding for “ Tony ” Selective Read for “ Tony ” ( a ) Attention-based Encoder-Decoder ( RNNSearch ) ( c ) State Update s 4 SourceVocabulary Softmax Prob , 2016 .

[7]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[8]  Mitesh M. Khapra,et al.  A Mixed Hierarchical Attention Based Encoder-Decoder Approach for Standard Table Summarization , 2018, NAACL.

[9]  Luke S. Zettlemoyer,et al.  AllenNLP: A Deep Semantic Natural Language Processing Platform , 2018, ArXiv.

[10]  Cong Yu,et al.  Generating Titles for Web Tables , 2018, WWW.

[11]  R'emi Louf,et al.  HuggingFace's Transformers: State-of-the-art Natural Language Processing , 2019, ArXiv.

[12]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[13]  Krisztian Balog,et al.  Web Table Extraction, Retrieval, and Augmentation: A Survey , 2020, ACM Trans. Intell. Syst. Technol..

[14]  Colin Raffel,et al.  Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer , 2019, J. Mach. Learn. Res..

[15]  Lysandre Debut,et al.  HuggingFace's Transformers: State-of-the-art Natural Language Processing , 2019, ArXiv.