Table Cell Search for Question Answering

Abstract

Tables are pervasive on the Web. Informative web tables range across a large variety of topics, which can naturally serve as a significant resource to satisfy user information needs. Driven by such observations, in this paper, we investigate an important yet largely under-addressed problem: Given millions of tables, how to precisely retrieve table cells to answer a user question. This work proposes a novel table cell search framework to attack this problem. We first formulate the concept of a relational chain which connects two cells in a table and represents the semantic relation between them. With the help of search engine snippets, our framework generates a set of relational chains pointing to potentially correct answer cells. We further employ deep neural networks to conduct more fine-grained inference on which relational chains best match the input question and finally extract the corresponding answer cells. Based on millions of tables crawled from the Web, we evaluate our framework in the open-domain question answering (QA) setting, using both the well-known WebQuestions dataset and user queries mined from Bing search engine logs. On WebQuestions, our framework is comparable to state-of-the-art QA systems based on knowledge bases (KBs), while on Bing queries, it outperforms other systems with a 56.7% relative gain. Moreover, when combined with results from our framework, KB-based QA performance can obtain a relative improvement of 28.1% to 66.7%, demonstrating that web tables supply rich knowledge that might not exist or is difficult to be identified in existing KBs.

Web Table Extraction, Retrieval and Augmentation

“…They find that combining the deep features with some shallow features, like term-level similarity between query and table chains, achieve the best performance. Sun et al (2016) conclude that their method can complement KB-based QA methods by improving their coverage.…”

“…We organize relevant literature based on the task that is being addressed into six main categories. These are: ; Chen and Cafarella (2013); Cafarella et al (2008b); Balakrishnan et al (2015); Cafarella et al (2009); ; Bhagavatula et al (2015) Wang and Hu (2002b,a); ; Chen and Cafarella (2013); Cafarella et al (2008b); Crestan and Pantel (2011); Lautert et al (2013); Nishida et al (2017); Venetis et al (2011); Mulwad et al (2010); Fan et al (2014); Bhagavatula et al (2015); ; Efthymiou et al (2017); ; Hassanzadeh et al (2015); Mulwad et al (2013); Sekhavat et al (2014); Ibrahim et al (2016); Limaye et al (2010); Muñoz et al (2014); ; Ritze and Bizer (2017) Table search Query Ranked list of tables Cafarella et al (2009); Pimplikar and Sarawagi (2012); Cafarella et al (2008a); Bhagavatula et al (2013); ; ; Das Sarma et al (2012); Yakout et al (2012); Nguyen et al (2015); Zhang and Balog (2018a); Limaye et al (2010); Nargesian et al (2018); Zhang and Balog (2019b) Question Answering Natural language query Structured data Pasupat and Liang (2015); Sun et al (2016);…”

Auto-completion for Data Cells in Relational Tables

“…Facts found in tables can be used for question answering. For example, Sun et al [17] propose a deep matching model for matching question and table cells. The matched table cells are taken as the answers.…”

A Review on Neural Network Question Answering Systems

“…The proposed solutions identified for this problem were borrowing ideas from Machine Translation Evaluation (MTE) [41] by using a neural network to decide the quality of an answer comment by taking two comments and use ranking mechanisms to filter out bad (irrelevant) comments [13], and using a neural network to learn the joint semantic representation of a question-answer pair and use this representation to predict the quality of each answer in the comments sequence [19]. Table 11 summarizes the proposed methods mentioned above.…”