An official website of the United States government
A natural language interface (NLI) to databases is an interface that translates a natural language question to a structured query that is executable by database management systems (DBMS). However, an NLI that is trained in the general domain is hard to apply in the spatial domain due to the idiosyncrasy and expressiveness of the spatial questions. Inspired by the machine comprehension model, we propose a spatial comprehension model that is able to recognize the meaning of spatial entities based on the semantics of the context. The spatial semantics learned from the spatial comprehension model is then injected to the natural language question to ease the burden of capturing the spatial-specific semantics. With our spatial comprehension model and information injection, our NLI for the spatial domain, named SpatialNLI, is able to capture the semantic structure of the question and translate it to the corresponding syntax of an executable query accurately. We also experimentally ascertain that SpatialNLI outperforms state-of-the-art methods.
more »
« less
Parsing Natural Language Queries for Extracting Data from Large-Scale Geospatial Transportation Asset Repositories
Recent advances in data and information technologies have enabled extensive digital datasets to be available to decision makers throughout the life cycle of a transportation project. However, most of these data are not yet fully reused due to the challenging and time-consuming process of extracting the desired data for a specific purpose. Digital datasets are presented only in computer-readable formats and they are mostly complicated. Extracting data from complex and large data sources is significantly time-consuming and requires considerable expertise. Thus, there is a need for a user-friendly data exploration framework that allows users to present their data interests in human language. To fulfill that demand, this study employs natural language processing (NLP) techniques to develop a natural language interface (NLI) which can understand users’ intent and automatically convert their inputs in the human language into formal queries. This paper presents the results of an important task of the development of such a NLI that is to establish a method for classifying the tokens of an ad-hoc query in accordance with their semantic contribution to the corresponding formal query. The method was validated on a small test set of 30 plain English questions manually annotated by an expert. The result shows an impressive accuracy of over 95%. The token classification presented in this paper is expected to provide a fundamental means for developing an effective NLI to transportation asset databases.
more »
« less
- Award ID(s):
- 1635309
- PAR ID:
- 10069438
- Date Published:
- Journal Name:
- Construction Research Congress 2018: Building Community Partnerships
- Page Range / eLocation ID:
- 70 to 79
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Nearly every artifact of the modern engineering design process is digitally recorded and stored, resulting in an overwhelming amount of raw data detailing past designs. Analyzing this design knowledge and extracting functional information from sets of digital documents is a difficult and time-consuming task for human designers. For the case of textual documentation, poorly written superfluous descriptions filled with jargon are especially challenging for junior designers with less domain expertise to read. If the task of reading documents to extract functional requirements could be automated, designers could actually benefit from the distillation of massive digital repositories of design documentation into valuable information that can inform engineering design. This paper presents a system for automating the extraction of structured functional requirements from textual design documents by applying state of the art Natural Language Processing (NLP) models. A recursive method utilizing Machine Learning-based question-answering is developed to process design texts by initially identifying the highest-level functional requirement, and subsequently extracting additional requirements contained in the text passage. The efficacy of this system is evaluated by comparing the Machine Learning-based results with a study of 75 human designers performing the same design document analysis task on technical texts from the field of Microelectromechanical Systems (MEMS). The prospect of deploying such a system on the sum of all digital engineering documents suggests a future where design failures are less likely to be repeated and past successes may be consistently used to forward innovation.more » « less
-
We present a large-scale collection of diverse natural language inference (NLI) datasets that help provide insight into how well a sentence representation captures distinct types of reasoning. The collection results from recasting 13 existing datasets from 7 semantic phenomena into a common NLI structure, resulting in over half a million labeled context-hypothesis pairs in total. We refer to our collection as the DNC: Diverse Natural Language Inference Collection. The DNC is available online at https://www.decomp.net, and will grow over time as additional resources are recast and added from novel sources.more » « less
-
A Natural Language Interface (NLI) enables the use of human languages to interact with computer systems, including smart phones and robots. Compared to other types of interfaces, such as command line interfaces (CLIs) or graphical user interfaces (GUIs), NLIs stand to enable more people to have access to functionality behind databases or APIs as they only require knowledge of natural languages. Many NLI applications involve structured data for the domain (e.g., applications such as hotel booking, product search, and factual question answering.) Thus, to fully process user questions, in addition to natural language comprehension, understanding of structured data is also crucial for the model. In this paper, we study neural network methods for building Natural Language Interfaces (NLIs) with a focus on learning structure data representations that can generalize to novel data sources and schemata not seen at training time. Specifically, we review two tasks related to natural language interfaces: i) semantic parsing where we focus on text-to-SQL for database access, and ii) task-oriented dialog systems for API access. We survey representative methods for text-to-SQL and task-oriented dialog tasks, focusing on representing and incorporating structured data. Lastly, we present two of our original studies on structured data representation methods for NLIs to enable access to i) databases, and ii) visualization APIs.more » « less
-
null (Ed.)Natural language inference (NLI) is the task of detecting the existence of entailment or contradiction in a given sentence pair. Although NLI techniques could help numerous information retrieval tasks, most solutions for NLI are neural approaches whose lack of interpretability prohibits both straightforward integration and diagnosis for further improvement. We target the task of generating token-level explanations for NLI from a neural model. Many existing approaches for token-level explanation are either computationally costly or require additional annotations for training. In this article, we first introduce a novel method for training an explanation generator that does not require additional human labels. Instead, the explanation generator is trained with the objective of predicting how the model’s classification output will change when parts of the inputs are modified. Second, we propose to build an explanation generator in a multi-task learning setting along with the original NLI task so the explanation generator can utilize the model’s internal behavior. The experiment results suggest that the proposed explanation generator outperforms numerous strong baselines. In addition, our method does not require excessive additional computation at prediction time, which renders it an order of magnitude faster than the best-performing baseline.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1061/9780784481295.008
