Figure 4 - uploaded by Pinaki Mitra
Content may be subject to copyright.
Source publication
This paper concerns with the conversion of a Spoken English Language Query
into SQL for retrieving data from RDBMS. A User submits a query as speech
signal through the user interface and gets the result of the query in the text
format. We have developed the acoustic and language models using which a speech
utterance can be converted into English te...
Contexts in source publication
Context 1
... tokens lexical analyzer is invoked by parser. Both work in coordination until the complete parse tree is generated. The parse tree for the example query is shown in figure ...
Similar publications
Machine translation is the process of translating text from one language to
another. In this paper, Statistical Machine Translation is done on Assamese and
English language by taking their respective parallel corpus. A statistical
phrase based translation toolkit Moses is used here. To develop the language
model and to align the words we used two a...
The recently proposed neural network joint model (NNJM) (Devlin et al., 2014)
augments the n-gram target language model with a heuristically chosen source
context window, achieving state-of-the-art performance in SMT. In this paper,
we give a more systematic treatment by summarizing the relevant source
information through a convolutional architectu...
Generating a novel textual description of an image is an interesting problem
that connects computer vision and natural language processing. In this paper,
we present a simple model that is able to generate sentences given a sample
image. Our model learns to embed image representations (generated from a
previously trained Convolutional Neural Networ...
In this short note, we present an extension of LSTM to use a depth gate to
connect memory cells of adjacent layers. Doing so introduces a linear
dependence between lower and upper recurrent units. Importantly, the linear
dependence is gated through a gating function, which we call forget gate. This
gate is a function of lower layer memory cell, its...
In this paper we develop a recurrent neural network (TreeRNN), which is
designed to predict a tree rather than a linear sequence as is the case in
conventional recurrent neural networks. Our model defines the probability of a
sentence by estimating the generation probability of its dependency tree. We
construct the tree incrementally by generating...
Citations
... Therefore, to access the information from databases some basic training is needed about SQL and DBMS. Furthermore, the system can be inquired by a user utilizing natural language, such as English and that natural language is converted into structured query language which access the DBMS; finally, the translated system returns the result back to the end user with the natural language [9] [4]. Particularly for inexperienced users who are unfamiliar with complicated query languages like SQL, natural language queries are a very convenient and straightforward approach to access databases. ...
... The corpora are mainly used as a language source [8]. The empirical approach has been existing since the start of the NLP (e.g., early 1950s); but in the last 10 years, it has emerged as a significant alternative to rule-based NLP [9]. The corpus-based approach is another name for the empirical approach. ...
A database is a major source of information which plays an important role in our life. Information retrieval from the database requires formulating a querythatisunderstandablebythecomputerinordertoproducedesiredoutput. Generally, databases work with structured query language (SQL). But a naive user usually unfamiliar with the structured query language as well as structure of the table in the database. Hence, it becomes very difficult for the naïve-user to collect the desired information. This paper provides a solution to this problem and it enables users to retrieve information through natural language, such as English language. Being able to access information from the database by using natural language bridges the man-machine gap. Tokenization, lexical analysis, syntactic analysis, semantic analysis, and other complex stages are all involved in converting a natural language query into a SQL query. The purpose of this paper is to translate natural language queries into Structure Query Language queries, allowing non-technical people to get connected to databases and to gather the required information.
... Although text interfaces to databases [9] have been explored relatively more than voice interfaces [7], their use for teaching SQL is less explored [12]. While we can point to SQL teaching systems such as [3,6,8,11,12], we are unable to discuss them in this paper for the want of space except EchoQuery [10] as this framework has much in common with our approach in Cyrus. ...
Being declarative, SQL stands a better chance at being the programming language for conceptual computing next to natural language programming. We examine the possibility of using SQL as a back-end for natural language database programming. Distinctly from keyword based SQL querying, keyword dependence and SQL's table structure constraints are significantly less pronounced in our approach. We present a mobile device voice query interface, called Cyrus, to arbitrary relational databases. Cyrus supports a large type of query classes, sufficient for an entry level database class. Cyrus is also application independent, allows test database adaptation, and not limited to specific sets of keywords or natural language sentence structures. It's cooperative error reporting is more intuitive, and iOS based mobile platform is also more accessible compared to most contemporary mobile and voice enabled systems.
... Kumar et al. [6] proposed system which uses the knowledge of underlying database and generate lex file automatically, which will be used while tokenizing the words involved in English text query and since lex file contains underlying database information like column and table names. So, automatic generation of lex file helps in making the system database independent. ...
Recent developments in speech recognition system and natural language processing have given rise to a new generation of powerful voice-based interfaces. In this proposed system, a user interacts with the system through a voice-based user interface to fetch the desired results. To make the system smooth and interactive, the query is based on casual human speech / conversation. The spoken query undergoes many steps to arrive at the final results. It includes synonym table which is used to convert the spoken query into SQL keywords. The proposed work produce good results for simple and complex queries. The accuracy of the system depends on the complexity of the database. This system will show that the voice-based user interface is an effective means of querying and fetching data from the stored database.
... Although text interfaces to databases [9] have been explored relatively more than voice interfaces [7], their use for teaching SQL is less explored [12]. While we can point to SQL teaching systems such as [3,6,8,11,12], we are unable to discuss them in this paper for the want of space except Echo ery [10] as this framework has much in common with our approach in Cyrus. ...
Being declarative, SQL stands a better chance at being the programming language for conceptual computing next to natural language programming. We examine the possibility of using SQL as a back-end for natural language database programming. Distinctly from keyword based SQL querying, keyword dependence and SQL's table structure constraints are significantly less pronounced in our approach. We present a mobile device voice query interface, called Cyrus, to arbitrary relational databases. Cyrus supports a large type of query classes, sufficient for an entry level database class. Cyrus is also application independent, allows test database adaptation, and not limited to specific sets of keywords or natural language sentence structures. It's cooperative error reporting is more intuitive, and iOS based mobile platform is also more accessible compared to most contemporary mobile and voice enabled systems.
... VoiceXML is commonly used in many industries with a variety of successful commercial applications where information and dialogue is modeled as finite-state automata or form filling (frame-based dialogue model) [6]. In addition, knowledge sources for dialogue agents can also be any other forms such as relational database [7,8], First Order Predicate Logic [9], as long as they are expressive enough and suitable for these applications. ...
Knowledge base is a key component of a dialogue agent which determines its usability, performance as well as intelligence. Usually one type of knowledge source is tailored towards specific application or task. One challenge for developing multiple-domain dialogue agents is how to represent the domain knowledge in their respective ways for the best efficiency and easy construction of queries from natural language. There are a variety of knowledge sources available for building up dialogue agents such as relational database, ontology, knowledge base (KB), search index, artificial intelligence markup language (AIML) and the World Wide Web, etc. In this paper, we present a systematic way of configuring dialogue agents supported by multiple knowledge sources. With the proposed dialogue framework, we provide a complete solution for the development of various dialogue systems with the support of different dialogue management techniques, multiple protocols for cloud-enabled dialogue services, pluggable infrastructure for component reuse and service enhancement, strong scripting functions in both XML and Python. We have constructed various dialogue agents with this framework. Results show that these agents are robust and the development cycle can be considerably reduced.
