Semantic Mapping between Natural Language Questions and SQL Queries via Syntactic Pairing

Giordani, Alessandra; Moschitti, Alessandro

doi:10.1007/978-3-642-12550-8_17

Cited by 32 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The previous results, although interesting, show that syntactic information plays a minor role and that complex kernels do not significantly improve our question translator (similar findings were derived in the preliminary experiments in [14] To verify such hypothesis, we experimented with the second dataset whose results, reported in tables Table 3 and Table 4, provide more interesting data.…”

Section: Results On Rest Datasetsupporting

confidence: 70%

See 1 more Smart Citation

Syntactic Structural Kernels for Natural Language Interfaces to Databases

Giordani

Moschitti

2009

Machine Learning and Knowledge Discovery in Databases

Self Cite

View full text Add to dashboard Cite

A core problem in data mining is to retrieve data in a easy and human friendly way. Automatically translating natural language questions into SQL queries would allow for the design of effective and useful database systems from a user viewpoint. Interesting previous work has been focused on the use of machine learning algorithms for automatically mapping natural language (NL) questions to SQL queries. In this paper, we present many structural kernels and their combinations for inducing the relational semantics between pairs of NL questions and SQL queries. We measure the effectiveness of such kernels by using them in Support Vector Machines to select the queries that correctly answer to NL questions. Experimental results on two different datasets show that our approach is viable and that syntactic information under the form of pairs of syntactic tree fragments (from queries and questions) plays a major role in deriving the relational semantics between the two languages.

show abstract

Section: Results On Rest Datasetsupporting

confidence: 70%

“…The new contributions with respect to our previous research on Natural Language Interface to Databases [14] are the following:…”

Section: Introductionmentioning

confidence: 99%

Syntactic Structural Kernels for Natural Language Interfaces to Databases

Giordani

Moschitti

2009

Machine Learning and Knowledge Discovery in Databases

Self Cite

View full text Add to dashboard Cite

show abstract

“…To the best of our knowledge, no research has been carried out on CL question re-ranking before. Regarding cross-language tree kernels, the only previous study relates to mapping natural language to an arti cial language (SQL) [11,12]. We use a similar cross-language tree kernel along with the new idea of deriving relational links [25] using cross-language dictionaries.…”

Section: Related Workmentioning

confidence: 99%

“…related ) questions are only compared to new (resp. related ) questions: this produces the kernel space of tree fragment pairs as shown in [11,12], where the pair members are in di erent languages. Moreover, the de nition of t(x, x ) is more complicated in case x and x are in di erent languages as, in addition to using separate Arabic and English parsers, we need to de ne methods for matching words in di erent languages.…”

Section: Tree Kernelsmentioning

confidence: 99%

Cross-Language Question Re-Ranking

Martino

Romeo

Barroón-Cedeño

et al. 2017

Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval

Self Cite

View full text Add to dashboard Cite

We study how to nd relevant questions in community forums when the language of the new questions is di erent from that of the existing questions in the forum. In particular, we explore the Arabic-English language pair. We compare a kernel-based system with a feed-forward neural network in a scenario where a large parallel corpus is available for training a machine translation system, bilingual dictionaries, and cross-language word embeddings. We observe that both approaches degrade the performance of the system when working on the translated text, especially the kernel-based system, which depends heavily on a syntactic kernel. We address this issue using a cross-language tree kernel, which compares the original Arabic tree to the English trees of the related questions. We show that this kernel almost closes the performance gap with respect to the monolingual system. On the neural network side, we use the parallel corpus to train cross-language embeddings, which we then use to represent the Arabic input and the English related questions in the same space. e results also improve to close to those of the monolingual neural network. Overall, the kernel system shows a be er performance compared to the neural network in all cases.

show abstract

“…However almost all the work that has been done uses process of applying semantic and syntactic analysis to get an logical representation of the sentence followed by a conversion of the representation into a database query [3,7,9]. However all these approaches do require a detailed syntactic and semantic analysis of the sentence which is computationally expensive.…”

Section: Related Workmentioning

confidence: 99%

Natural Language Statement to SQL Query Translator

Chaudhari¹

2013

IJCA

View full text Add to dashboard Cite

A Database is an organized collection of data. It is created to store large amount of data and retrieve it efficiently in less amount of time. To retrieve data from the database Structured Query Language (SQL) is used. SQL has its own syntax of query. To retrieve correct data from the database this query should be written in proper or correct syntax. Thus users should have sufficient knowledge of SQL to retrieve data. In this paper a light weight technique of converting a natural language statement into equivalent SQL statement is highlighted which when executed on database provides us with the accurate results. The main advantage of this technique is the users which are unknown to the syntax of SQL can also use the system and retrieve data. General TermsNatural Language Processing

show abstract

Semantic Mapping between Natural Language Questions and SQL Queries via Syntactic Pairing

Cited by 32 publications

References 20 publications

Syntactic Structural Kernels for Natural Language Interfaces to Databases

Syntactic Structural Kernels for Natural Language Interfaces to Databases

Cross-Language Question Re-Ranking

Natural Language Statement to SQL Query Translator

Contact Info

Product

Resources

About