I. INTRODUCTION:

Natural Language Processing (NLP) is the computerized approach to analyzing text that is based on both a set of theories and a set of technologies. And, being a very active area of research and development, there is not a single agreed-upon definition that would satisfy everyone, but there are some aspects, which would be part of any knowledgeable person’s definition. Natural Language Processing is a theoretically motivated range of computational techniques for analyzing and representing naturally occurring texts at one or more levels of linguistic analysis for the purpose of achieving human-like language processing for a range of tasks or applications¹.

Several elements of this definition can be further detailed[14]. Firstly the imprecise notion of ‘range of computational techniques’ is necessary because there are multiple methods or techniques from which to choose to accomplish a particular type of language analysis. ‘Naturally occurring texts’ can be of any language, mode, genre, etc. The texts can be oral or written. The only requirement is that they be in a language used by humans to communicate to one another². Also, the text being analyzed should not be specifically constructed for the purpose of the analysis, but rather that the text be gathered from actual usage.

The notion of ‘levels of linguistic analysis’ (to be further explained in Section 2) refers to the fact that there are multiple types of language processing known to be at work when humans produce or comprehend language. It is thought that humans normally utilize all of these levels since each level conveys different types of meaning. But various NLP systems utilize different levels, or combinations of levels of linguistic analysis, and this is seen in the differences amongst various NLP applications. This also leads to much confusion on the part of non-specialists as to what NLP really is, because a system that uses any subset of these levels of analysis can be said to be an NLP-based system. The difference between them, therefore, may actually be whether the system uses ‘weak’ NLP or ‘strong’ NLP. ‘Human-like language processing’ reveals that NLP is considered a discipline within Artificial Intelligence (AI). And while the full lineage of NLP does depend on a number of other disciplines, since NLP strives for human-like performance, it is appropriate to consider it an AI discipline. ‘For a range of tasks or applications’ points out that NLP is not usually considered a goal in and of itself, except perhaps for AI researchers. For others, NLP is the means for accomplishing a particular task. Therefore, you have Information Retrieval (IR) systems that utilize NLP, as well as Machine Translation (MT), Question-Answering, etc.

The goal of NLP as stated above is “to accomplish human-like language processing”.

The choice of the word ‘processing’ is very deliberate, and should not be replaced with ‘understanding’. For although the field of NLP was originally referred to as Natural Language Understanding (NLU) in the early days of AI, it is well agreed today that while the goal of NLP is true NLU, that goal has not yet been accomplished. A full NLU System would be able to:

1. Paraphrase an input text

2. Translate the text into another language

3. Answer questions about the contents of the text

4. Draw inferences from the text

While NLP has made serious inroads into accomplishing goals 1 to 3, the fact that NLP systems cannot, of themselves, draw inferences from text, NLU still remains the goal of NLP⁴.

There are more practical goals for NLP, many related to the particular application for which it is being utilized. For example, an NLP-based IR system has the goal of providing more precise, complete information in response to a user’s real information need⁵. The goal of the NLP system here is to represent the true meaning and intent of the user’s query, which can be expressed as naturally in everyday language as if they were speaking to a reference librarian. Also, the contents of the documents that are being searched will be represented at all their levels of meaning so that a true match between need and response can be found, no matter how either are expressed in their surface form.

II. LEVELS OF NLP:

Phonology: This level deals with the interpretation of speech sounds within and across words. There are, in fact, three types of rules used in phonological analysis: 1) phonetic rules – for sounds within words; 2) phonemic rules – for variations of pronunciation when words are spoken together, and; 3) prosodic rules – for fluctuation in stress and intonation across a sentence. In an NLP system that accepts spoken input, the sound waves are analyzed and encoded into a digitized signal for interpretation by various rules or by comparison to the particular language model being utilized.

Morphology: This level deals with the componential nature of words, which are composed of morphemes – the smallest units of meaning. For example, the word preregistration can be morphologically analyzed into three separate morphemes: the prefix pre, the root registration, and the suffix. Since the meaning of each morpheme remains the same across words, humans can break down an unknown word into its constituent morphemes in order to understand its meaning. Similarly, an NLP system can recognize the meaning conveyed by each morpheme in order to gain and represent meaning. For example, adding the suffix –ed to a verb, conveys that the action of the verb took place in the past. This is a key piece of meaning, and in fact, is frequently only evidenced in a text by the use of the -ed morpheme.

Lexical: At this level, humans, as well as NLP systems, interpret the meaning of individual words. Several types of processing contribute to word-level understanding – the first of these being assignment of a single part-of-speech tag to each word. In this processing, words that can function as more than one part-of-speech are assigned the most probable part-of speech tag based on the context in which they occur. Additionally at the lexical level, those words that have only one possible sense or meaning can be replaced by a semantic representation of that meaning. The nature of the representation varies according to the semantic theory utilized in the NLP system. The following representation of the meaning of the word launch is in the form of logical predicates. As can be observed, a single lexical unit is decomposed into its more basic properties. Given that there is a set of semantic primitives used across all words, these simplified lexical representations make it possible to unify meaning across words and to produce complex interpretations, much the same as humans do.

Ex. “Large boat used for carrying people on rivers, lakes harbors, etc.) ((CLASS BOAT) (PROPERTIES (LARGE) (PURPOSE (PREDICATION (CLASS CARRY) (OBJECT PEOPLE))))”

Syntactic: This level focuses on analyzing the words in a sentence so as to uncover the grammatical structure of the sentence. This requires both a grammar and a parser. The output of this level of processing is a (possibly delinearized) representation of the sentence that reveals the structural dependency relationships between the words. There are various grammars that can be utilized, and which will, in turn, impact the choice of a parser. Not all NLP applications require a full parse of sentences, therefore the remaining challenges in parsing of prepositional phrase attachment and conjunction scoping no longer stymie those applications for which phrasal and clausal dependencies are sufficient. Syntax conveys meaning in most languages because order and dependency contribute to meaning. For example the two sentences: ‘The dog chased the cat.’ and ‘The cat chased the dog.’ differ only in terms of syntax, yet convey quite different meanings.

Semantic: This is the level at which most people think meaning is determined, however, as we can see in the above defining of the levels, it is all the levels that contribute to meaning. Semantic processing determines the possible meanings of a sentence by focusing on the interactions among word-level meanings in the sentence. This level of processing can include the semantic disambiguation of words with multiple senses; in an analogous way to how syntactic disambiguation of words that can function as multiple parts-of-speech is accomplished at the syntactic level. Semantic disambiguation permits one and only one sense of polysemous words to be selected and included in the semantic representation of the sentence. For example, amongst other meanings, ‘file’ as a noun can mean either a folder for storing papers, or a tool to shape one’s fingernails, or a line of individuals in a queue. If information from the rest of the sentence were required for the disambiguation, the semantic, not the lexical level, would do the disambiguation. A wide range of methods can be implemented to accomplish the disambiguation, some which require information as to the frequency with which each sense occurs in a particular corpus of interest, or in general usage, some which require consideration of the local context, and others which utilize pragmatic knowledge of the domain of the document[6].

Discourse: While syntax and semantics work with sentence-length units, the discourse level of NLP works with units of text longer than a sentence. That is, it does not interpret multisentence texts as just concatenated sentences, each of which can be interpreted singly. Rather, discourse focuses on the properties of the text as a whole that convey meaning by making connections between component sentences. Several types of discourse processing can occur at this level, two of the most common being anaphora resolution and discourse/text structure recognition. Anaphora resolution is the replacing of words such as pronouns, which are semantically vacant, with the appropriate entity to which they refer [7]. Discourse/text structure recognition determines the functions of sentences in the text, which, in turn, adds to the meaningful representation of the text. For example, newspaper articles can be deconstructed into discourse components such as: Lead, Main Story, Previous Events, Evaluation, Attributed Quotes, and Expectation[17] .

Pragmatic: This level is concerned with the purposeful use of language in situations and utilizes context over and above the contents of the text for understanding The goal is to explain how extra meaning is read into texts without actually being encoded in them[15]. This requires much world knowledge, including the understanding of intentions, plans, and goals. Some NLP applications may utilize knowledge bases and inferencing modules. For example, the following two sentences require resolution of the anaphoric term ‘they’, but this resolution requires pragmatic or world knowledge[16].

III. PREVIOUS WORK:

The very first attempts at NLP database interfaces are just as old as any other NLP research. In fact database NLP may be one of the most important successes in NLP since it began. Asking questions to databases in natural language is a very convenient and easy method of data access, especially for casual users who do not understand complicated database query languages such as SQL. The success in this area is partly because of the real-world benefits that can come from database NLP systems, and partly because NLP works very well in a single-database domain. Databases usually provide small enough domains that ambiguity problems in natural language can be resolved successfully. Here are some examples of database NLP systems[8]:

LUNAR (Woods, 1973) involved a system that answered questions about rock samples brought back from the moon. Two databases were used, the chemical analyses and the literature references. The program used an Augmented Transition Network

(ATN) parser and Woods' Procedural Semantics. The system was informally demonstrated at the Second Annual Lunar Science Conference in 1971. [1] LIFER/LADDER was one of the first good database NLP systems. It was designed as a natural language interface to a database of information about US Navy ships. This system, as described in a paper by Hendrix, used a semantic grammar to parse questions and query a distributed database. The LIFER/LADDER system could only support simple one-table queries or multiple table queries with easy join conditions. [4]

IV. PROPOSED APPROACH

Fig 1: Architecture of NLDBI System.

To process a query, the first step is speech tagging; followed by word tagging. The second step is parsing the tagged sentence by a grammar. The grammar parser analyzes the query sentence according to the tag of each word and generates the grammar tree/s. Finally, the SQL translator processes the grammar tree to obtain the SQL query[8].

Consider a sentence w1m which is a sequence of words w1 w2 w3…wm (ignoring punctuations), and each string wi in the sequence stands for a word in the sentence. The grammar tree of w1m can be generated by a set of predefined grammar rules; usually more than one grammar tree may be generated. The formalizing capability of grammar help in describing most sentence structures and built efficient sentence parsers.

A parser is one of the components in an interpreter or compiler, which checks for correct syntax and builds a data structure (often some kind of parse tree, abstract syntax tree or other hierarchical structure) implicit in the input tokens[11]. The parser often uses a separate lexical analysis to create tokens from the sequence of input characters. Parsers may be programmed by hand or may be semi automatically generated (in some programming language) by a tool (such as Yacc) from a grammar written in Backus-Naur form.

The SQL translator generates query in SQL[9]. Using grammar the parse tree is obtained from the input statement. The leaves of the parse tree are translated to corresponding SQL. Fig. 2 depicts the processing of English input statement to generate SQL query. The entire process involves tagging of input statement, apply grammar and semantic representation to generate parse tree, analyze the parse tree using grammar and translating the leaves of the tree to generate corresponding SQL query [10].

Fig. 2 Generation of SQL query from English Statement.

The database tables considered are EMP (empid, empname, salary, edepid, address, post, mobileno), DEPT (deptid, deptname, deptloc, dcapacity) and PROJECT (pid, pname, epid). From the input NL statement, to generate parse tree the grammar written based on database tables is:

WhatKeyBank → for | of | with | is | where | whose | having | in | on

AAnTheBank → a | an | the

empid → integer | id | number

empname → string | name

salary → integer | salary | income | earning

mgrid → integer | manager | boss | superior

edeptid → integer | id | number

deptid → integer | id | number

deptname → string | name

deptloc → string | location

dcapacity → integer | capacity

EmpTable → employee | worker | person | emp |

employees | emps | workers |persons

ProjectTable → project | projects

The experimental work is to design an interface for generating queries from natural language statements/ questions. It also consists of designing a parser for the natural language statements, which will parse the input statement, generate the query and fire it on the database. The experimental work will understand the exact meaning the end user wants to go for, generate a what- type sentence and then convert it into a query and handover it to the interface. The interface further processes the query and searches for the database. The database gives the result to the system which is displayed to the user. The following modules were developed [12]

· An Interface: It allows the user to enter the query in NL, interact with the system during ambiguities and display the query results.

· Parsing: Derives the Semantics of the statement given by the user and parses it into its internal representation, to convert NL input statement into what- type question for selection of data.

· Query Generation: It generates a query against the user statement in SQL and passes on to the database.

The structure of an algorithm is given below

Step 1:

Take i/p of natural language sentence

Call NLP ENGINE

Receive array from NLP engine

If array not null

Display

Else

no record is found

Step 2.

NLP ENGINE

Parse the sentence

Call name entity reorganization

Extract noun form the sentence

Stored in the array of variable

Step 3:

Call semantic processing

Extract the possible meaning from the sentence

Make syntax from the array of noun and semantic mining

Convert into sql query

Execute the query in sql engine

Store in array

Return array

V. CONCLUSION:

Natural Language Processing can bring powerful enhancements to virtually any computer program interface. This system is currently capable of handling simple queries with standard join conditions. Because not all forms of SQL queries are supported, further development would be required before the system can be used within NLDBI. Alternatives for integrating a database NLP

Component into the NLDBI were considered and assessed.

VI. REFERENCES:

1. Huangi,Guiang Zangi, Phillip C-Y Sheu “A Natural Language database Interface based on probabilistic context free grammar”, IEEE International workshop on Semantic Computing and Systems 2008

2. Akama, S. (Ed.) Logic, language and computation, Kulwer Academic publishers, pp. 7-11, 1997.

3. ELF Software CO. Natural-Language Database Interfaces from ELF Software Co, cited November 1999, available from Internet: http://hometown.aol.com/elfsoft/

4. Hendrix, G.G., Sacerdoti, E.D., Sagalowicz, D., Slocum, J.

“Developing a natural language interface to complex data”, in ACM Transactions on database systems, 3(2), pp. 105- 147, 1978.

5. Joseph, S.W., Aleliunas, R. “A knowledge-based subsystem for a natural language interface to a database that predicts and explains query failures”, in IEEE CH, pp. 80-87, 1991.

6. Mitrovic, A. A knowledge-based teaching system for SQL, University of Canterbury, 1998. Moore, J.D. “Discourse generation for instructional applications: making computer tutors more like humans”, in Proceedings AI-ED, pp.36-42, 1995.

7. Suh, K.S., Perkins, W.C., “The effects of a system echo in a restricted natural language database interface for novice users”, in IEEE System sciences, 4, pp. 594-599, 1994.

8. Whenhua, W., Dilts, D.M. “Integrating diverse CIM data bases: the role of natural language interface”, in IEEE Transactions on systems, man, and cybernetics, 22(6), pp. 1331-1347, 1992.

9. Dan Klein, Christopher D. Manning: Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency. ACL 2004: 478-485.

10. In-Su Kang, Jae-Hak J. Bae, Jong-Hyeok Lee “Database Semantics Representation for Natural Language Access.” Department of Com Computer Science and Engineering, Electrical and Computer Engineering Division Pohang University of Science and Technology (POSTECH) and Advanced Information Technology Research Center (AITrc), 2002.

11. Woods, W., Kaplan, R. “Lunar rocks in natural English: Explorations in natural language question answering.” Linguistic Structures Processing. In Fundamental Studies in Computer Science, 5:521-569, 1977.

12. Androutsopoulos, I., Richie, G.D., Thanisch, P. “Natural Language Interface to Database – An Introduction.” Journal of Natural Language Engineering, Cambridge University Press. 1(1), 29-81, 1995.

13. Linguistic Technology. English Wizard – Dictionary Administrator's Guide. Linguistic Technology Corp., Littleton, MA, USA, 1997.

14. Dan Klein, Christopher D. Manning: Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency. ACL 2004: 478-485.

15. M-C.de Marneffe, B. MacCartney, and C. D. Manning. “Generating Typed Dependency Parses from Phrase Structure Parses.” In Proceedings of the IEEE /ACL 2006 Workshop on Spoken Language Technology. The Stanford Natural Language Processing Group. 2006.

16. Dan Klein and Christopher D. Manning. 2003. Fast Exact Inference with a Factored Model for Natural Language Parsing. In Advances in Neural Information Processing Systems 15 (NIPS 2002), Cambridge, MA: MIT Press, pp. 3-10.

17. Marie-Catherine de Marneffe, Bill MacCartney, and Christopher D. Manning. Generating Typed Dependency Parses from Phrase Structure Parses. In LREC 2006

Received on 30.10.2011 Accepted on 24.12.2011

Int. J. Tech. 1(2): July-Dec. 2011; Page 96-100