Search for: All records

Knowledge bases traditionally require manual optimization to en- sure reasonable performance when answering queries. We build on previous work on training a deep learning model to learn heuristics for answering queries by comparing different representations of the sentences contained in knowledge bases. We decompose the problem into issues of representation, training, and control and propose solutions for each subproblem. We evaluate different con- figurations on three synthetic knowledge bases. In particular we compare a novel representation approach based on learning to max- imize similarity of logical atoms that unify and minimize similarity of atoms that do not unify, to two vectorization strategies taken from the automated theorem proving literature: a chain-based and a 3-term-walk strategy. We also evaluate the efficacy of pruning the search by ignoring rules with scores below a threshold. 

The increasing availability of data search tools brings opportunities for non-expert users. Among these users, interdisciplinary researchers and data journalists represent a growing population whose work can lead to societal benefit. Through in-depth interviews, we examine what strategies and approaches researchers and journalists adopt to search online data, how they apply current technology to facilitate dataset search, and the barriers and difficulties that they encounter in their work with data. Our findings reveal that with technological limitations in the aspects of searchability, interactivity and usability, dataset search for non-experts remains a challenge. We have found that little attention has been paid to non-experts’ emerging data need, significantly constraining the design and development of technological tools for supporting non-expert users. Our findings underline the critical impact of the design, development and deployment of technological tools to enable the meaningful use of today’s increasingly available data toward a civil society. 

A table is composed of data values that are organized in %a 2D matrix with rows and columns providing implicit structural information. A table is usually accompanied by secondary information such as the caption, page title, etc., that form the textual information. Understanding the connection between the textual and structural information is an important, yet neglected aspect in table retrieval, as previous methods treat each source of information independently. In this paper, we propose StruBERT, a structure-aware BERT model that fuses the textual and structural information of a data table to produce context-aware representations for both textual and tabular content of a data table. We introduce the concept of horizontal self-attention, which extends the idea of vertical self-attention introduced in TaBERT and allows us to treat both dimensions of a table equally. StruBERT features are integrated in a new end-to-end neural ranking model to solve three table-related downstream tasks: keyword- and content-based table retrieval, and table similarity. We evaluate our approach using three datasets, and we demonstrate substantial improvements in terms of retrieval and classification metrics over state-of-the-art methods. 

We present a novel approach to dataset search and exploration. Cell-centric indexing is a unique indexing strategy that enables a powerful, new interface. The strategy treats individual cells of a table as the indexed unit, and combining this with a number of structure-specific fields enables queries that cannot be answered by a traditional indexing approach. Our interface provides users with an overview of a dataset repository, and allows them to efficiently use various facets to explore the collection and identify datasets that match their interests. 

Abstract Ranking models are the main components of information retrieval systems. Several approaches to ranking are based on traditional machine learning algorithms using a set of hand-crafted features. Recently, researchers have leveraged deep learning models in information retrieval. These models are trained end-to-end to extract features from the raw data for ranking tasks, so that they overcome the limitations of hand-crafted features. A variety of deep learning models have been proposed, and each model presents a set of neural network components to extract features that are used for ranking. In this paper, we compare the proposed models in the literature along different dimensions in order to understand the major contributions and limitations of each model. In our discussion of the literature, we analyze the promising neural components, and propose future research directions. We also show the analogy between document retrieval and other retrieval tasks where the items to be ranked are structured documents, answers, images and videos. 

Table search aims to retrieve a list of tables given a user's query. Previous methods only consider the textual information of tables and the structural information is rarely used. In this paper, we propose to model the complex relations in the table corpus as one or more graphs and then utilize graph neural networks to learn representations of queries and tables. We show that the text-based table retrieval methods can be further improved by graph-based predictions which fuse multiple field-level information. 

Ad hoc table retrieval is the problem of identifying the most relevant datasets to a user's query. We present an approach to the problem that builds a knowledge graph by combining information about the collection of tables with external sources such as WordNet and pretrained Glove embeddings. We apply multi-relational graph convolutional networks to learn embeddings for the knowledge graph nodes and utilize three different methods to create vectors representing the tables and queries from these embeddings. We create a novel learning-to-rank neural architecture that incorporates the multiple embeddings in order to improve table retrieval results. We evaluate our approach using two large collections of tables from public WikiTables and Web tables data, demonstrating substantial improvements over state-of-the-art methods in table retrieval. 

We address the problem of ad hoc table retrieval via a new neural architecture that incorporates both semantic and relevance matching. Understanding the connection between the structured form of a table and query tokens is an important yet neglected problem in information retrieval. We use a learning- to-rank approach to train a system to capture semantic and relevance signals within interactions between the structured form of candidate tables and query tokens. Convolutional filters that extract contextual features from query/table interactions are combined with a feature vector based on the distributions of term similarity between queries and tables. We propose using row and column summaries to incorporate table content into our new neural model. We evaluate our approach using two datasets, and we demonstrate substantial improvements in terms of retrieval metrics over state-of-the-art methods in table retrieval and document retrieval, and neural architectures from sentence, document, and table type classification adapted to the table retrieval task. Our ablation study supports the importance of both semantic and relevance matching in the table retrieval.