J B Juan González

Natural Language Interfaces to Databases: An Analysis of the State of the Art

People constantly make decisions based on information, most of which is stored in databases. Accessing this information requires the use of query languages to databases such as SQL. In order to avoid the difficulty of using these languages for users who are not computing experts, Natural Language Interfaces for Databases (NLIDB) have been developed, which permit to query databases through queries formulated in natural language. Although since the 60s many NLIDBs have been developed, their performance has not been satisfactory, there still remain very difficult problems that have not been solved by NLIDB technology, and there does not yet exist a standardized method of evaluation that permits to compare the performance of different NLIDBs. This chapter presents an analysis of NLIDBs, which includes their classification, techniques, advantages, disadvantages, and a proposal for a proper evaluation of them.

Issues in translating from natural language to SQL in a domain-independent natural language interface to databases

This paper deals with a domain-independent natural language interface to databases (NLIDB) for the Spanish language. This NLIDB had been previously tested for the Northwind and Pubs domains and had attained good performance (86% success rate). However, domain independence complicates the task of achieving high translation success, and to this end the ATIS (Air Travel Information System) database, which has been used by several natural language interfaces, was selected to conduct a new evaluation. The purpose of this evaluation was to asses the efficiency of the interface after the reconfiguration for another domain and to detect the problems that affect translation success. For the tests a corpus of queries was gathered and the results obtained showed that the interface can easily be reconfigured and that attained a 50% success rate. When the found problems concerning query translation were analyzed, wording deficiencies of some user queries and several errors in the synonym dictionary were discovered. After correcting these problems a second test was conducted, in which the interface attained a 61.4% success rate. These experiments showed that user training is necessary as well as a dialogue system that permits to clarify a query when it is deficiently formulated.

Features and Pitfalls that Users Should Seek in Natural Language Interfaces to Databases

Natural Language Interfaces to Databases (NLIDBs) are tools that can be useful in making decisions, allowing different types of users to get information they need using natural language communication. Despite their important features and that for more than 50 years NLIDBs have been developed, their acceptance by end users is very low due to extremely complex problems inherent to natural language, their customization and internal operation, which has produced poor performance regarding queries correctly translated. This chapter presents a study on the main desirable features that NLIDBs should have as well as their pitfalls, describing some study cases that occur in some interfaces to illustrate the flaws of their approach.

Semantic model for improving the performance of natural language interfaces to databases

Despite the fact that since the late 60s many Natural Language Interfaces to Databases (NLIDBs) have been developed, up to now many problems continue, which prevent the translation process from natural language to SQL to be totally successful. Some of the main problems that have been encountered relate to 1) achieving domain independence, 2) the use of words or phrases of different syntactic categories for referring to tables and columns, and 3) semantic ellipsis. This paper introduces a new method for modeling databases that includes relevant information for improving the performance of NLIDBs. This method will be useful for solving many problems found in the translation from natural language to SQL, using a database model that contains linguistic information that provides more semantic information than that found in conventional database models (such as the extended entity-relationship model) and those used in previous NLIDBs.Despite the fact that since the late 60s many Natural Language Interfaces to Databases (NLIDBs) have been developed, up to now many problems continue, which prevent the translation process from natural language to SQL to be totally successful. Some of the main problems that have been encountered relate to 1) achieving domain independence, 2) the use of words or phrases of different syntactic categories for referring to tables and columns, and 3) semantic ellipsis. This paper introduces a new method for modeling databases that includes relevant information for improving the performance of NLIDBs. This method will be useful for solving many problems found in the translation from natural language to SQL, using a database model that contains linguistic information that provides more semantic information than that found in conventional database models (such as the extended entity-relationship model) and those used in previous NLIDBs.

Dialogue manager for a NLIDB for solving the semantic ellipsis problem in query formulation

A query written in natural language (NL) may involve several linguistic problems that cause a query not being interpreted or translated correctly into SQL. One of these problems is implicit information or semantic ellipsis, which can be understood as the omission of important words in the wording of a query written in NL. An exhaustive survey on NLIDB works has revealed that most of these works has not systematically dealt with semantic ellipsis. In experiments conducted on commercial NLIDBs, very poor results have been obtained (7% to 16.9%) when dealing with query corpora that involve semantic ellipsis. In this paper we propose a dialogue manager (DM) for a NLIDB for solving semantic ellipsis problems. The operation of this DM is based on a typification of elliptical problems found in queries, which permits to systematically deal with this problem. Additionally, the typification has two important characteristics: domain independence, which permits the typification to be applied to queries of different databases, and generality, which means that it holds for different languages such as English, French, Italian, Spanish, etc. These characteristics are inherited to the dialogue processes implemented in the DM, since they are based on this typification. In experiments conducted with this DM and a NLIDB on a corpus of elliptical queries, an increase of correctly answered queries of 30-35% was attained.

A New Approach to Improve the Ant Colony System Performance: Learning Levels

In this paper a hybrid ant colony system algorithm is presented. A new approach to update the pheromone trails, denominated learning levels, is incorporated. Learning levels is based on the distributed Q-learning algorithm, a variant of reinforcement learning, which is incorporated to the basic ant colony algorithm. The hybrid algorithm is used to solve the Vehicle Routing Problem with Time Windows. Experimental results with the Solomons dataset of instances reveal that learning levels improve execution time and quality, respect to the basic ant colony system algorithm, 0.15% for traveled distance and 0.6% in vehicles used. Now we are applying the hybrid ant colony system in other domains.

Dynamic Allocation of Data-Objects in the Web, Using Self-tuning Genetic Algorithms

In this paper, a new mechanism for automatically obtaining some control parameter values for Genetic Algorithms is presented, which is independent of problem domain and size. This approach differs from the traditional methods which require knowing the problem domain first, and then knowing how to select the parameter values for solving specific problem instances. The proposed method uses a sample of problem instances, whose solution allows to characterize the problem and to obtain the parameter values. To test the method, a combinatorial optimization model for data-object allocation in the Web (known as DFAR) was solved using Genetic Algorithms. We show how the proposed mechanism allows to develop a set of mathematical expressions that relates the problem instance size to the control parameters of the algorithm. The expressions are then used, in on-line process, to control the parameter values. We show the last experimental results with the self-tuning mechanism applied to solve a sample of random instances that simulates a typical Web workload. We consider that the proposed method principles must be extended to the self-tuning of control parameters for other heuristic algorithms.

Modeling Facial Expression of Intelligent Virtual Agents

An intelligent virtual agent is an intelligent agent with a digital representation and endowed with conversational capabilities; this interactive character exhibits human-like behavior and communicates with humans or virtual interlocutors using verbal and nonverbal modalities such as gesture and speech. Building credible characters requires a multidisciplinary approach, the behaviors that must be reproduced are very complex and must be decoded by their interlocutors. In this paper we introduce a kinesics model in order to select the nonverbal expression of intelligent virtual agents able to express their emotions and purposes using gestures and face expressions. Our model select the nonverbal expressions based on causal analysis, and data mining algorithms applied to perceptual studies in order to identify significant attributes in emotional face expressions.

Analysis of Some Database Schemas Used to Evaluate Natural Language Interfaces to Databases

Most research work about the development of Natural Language Interface to Databases (NLIDB) has been focused on the study of the interpretation and translation from natural language queries to SQL queries. For this purpose and in order to improve the performance in a NLIDB, researchers have addressed different issues related to natural language processing. In addition to this, we consider that the performance of a NLIDB also depends on its ability to adapt to a database schema. For this reason, we analyzed the Geobase, ATIS and Northwind database schemas, commonly used to evaluate NLIDBs. As a result of this analysis, we present in this paper some issues arising from the three database schemas analyzed, which they should be considered in the implementation of a NLIDB to improve its performance.

Automatic Extraction of Hyponymy-Hypernymy Lexical Relations between Nouns from a Spanish Dictionary

In this paper a method is presented which permits to automatically extract lexical-semantic relations between nouns (specifically for concrete nouns since they have a well structured taxonomy). From the definitions of the entries in a Spanish dictionary, the hypernym of an entry is extracted from the entry definition according to the basic assumption that the first noun in the definition is the entry hypernym. After obtaining the hypernym for each entry, multilayered hyponymy-hyperonymy relations are generated from a noun, which is considered the root of the domain. The domains for which this approach was tested were zoology and botany. Five levels of hyponymy-hypernymy relations were generated for each domain. For the zoology domain a total of 1,326 relations was obtained with an average percentage of correctly generated relations (precision) of 84.31% for the five levels. 91.32% of all the relations of this domain were obtained in the first three levels, and for each of these levels the precision exceeds 96%. For the botany domain a total of 1,199 relations was obtained, with an average precision of 71.31% for the five levels. 90.76% of all the relations of this domain were obtained in the first level, and for this level the precision exceeds 99%.