Word Grammar 理論の研究

2005 marks the 31st SIGMOD conference, preceded by 5 workshops sponsored by SIGMOD's predecessor organization, SIGFIDET. The field has grown and evolved significantly over these 36 years, but the SIGMOD conference has remained throughout as one of the foremost annual events for exchanging the latest ideas and advances in data management.The SIGMOD conference is sponsored by the Association for Computing Machinery (ACM) and its Special Interest Group on Management of Data (SIGMOD). Two days of the conference overlap with the Symposium on Principles of Database System (PODS), and several workshops and other events are co-located with SIGMOD.This year 455 research papers were submitted to SIGMOD for consideration, of which 431 were reviewed. (The remaining papers were eliminated due to double-blind or length violations, overlap with other papers, or author withdrawal.) There has been much discussion in recent years of improving the overall conference reviewing process, as our field grows and evolves, and demands on researchers increase. Two innovations were added to this year's reviewing process on an experimental basis for SIGMOD:•There was no limit on the number of accepted papers -- decisions were based on suitable quality alone. Nevertheless, the tally of 65 accepted papers constitutes an acceptance ratio (15%) similar to recent years.•An "author feedback" phase was added, in which authors could read their reviews and provide feedback to be used in the final decision process. Reactions to this new feature ran the spectrum from frustration to joy, but most felt it to be a worthwhile experiment.

Proceedings of the 2005 ACM SIGMOD international conference on Management of data

Information is playing an important role in our lives. One of the major sources of information is databases. Databases and database technology are having major impact on the growing use of computers. In order to retrieve information from a database, one needs to formulate a query in such way that the computer will understand and produce the desired output. Generally, query processing is handled by the Structured Query Language (SQL). But the non IT people cannot be able to write SQL queries as they may not be aware of the SQL as well as structure of the database. So there is a need for non-expert users to query the databases in their natural language instead of working with the values of the attributes. This paper proposes an approach for accessing the database easily using natural language without having any knowledge about the query language. The approach is a rule based approach. The obvious advantage is that it makes a great promise for computer interfaces easier for the use of general people. Because of this, people will be able to communicate to the computer in their own language instead of learning a specialized language or commands. In order to test our approach in an actual computer environment, we have developed a prototype system. We obtained promising results using our system.

A rule based approach for NLP based query processing

Attribute information in a natural language query is one of the key features for converting a natural language query into a Structured Query Language 1 (SQL) in Natural Language Interface to Database systems. In this paper, we explore the task of classifying the attributes present in a natural language query into different SQL clauses in a SQL query. In particular, we investigate the effectiveness of various features and Conditional Random Fields for this task. Our system uses a statistical classifier trained on manually prepared data. We report our results on three different domains and also show how our system can be used for generating a complete SQL query.

Classification of Attributes in a Natural Language Query into Different SQL Clauses

Natural Language Interfaces to Database is a type of database interface that allows the user to access the data using natural language. Recent development used as the base of mis paper was made by Wibisono in 2013. Wibisono developed a domain-independent NLIDB using Stanford Dependency Parser as a tool in processing user input. This paper presents a solution to two of Wibisono's NLIDB problems, which are inability to process question-type queries and unit conversion. User input will first be identified, whether it is a question-type query or a directive-type query. Methods from Wibisono's NLIDB are then modified in order to be able to process question-type query. Unit conversion is done using a library called JScience in two phases of the process, before the SQL is produced (if necessary), and before the data is shown to the user. The proposed system was tested and was able to process some questions that follow a pattern and also to convert data in measurement units and some currency units.

Natural Language Interfaces to Database (NLIDB): Question handling and unit conversion

This paper presents a novel approach to building natural language interface to databases (NLIDB) based on Computational Paninian Grammar (CPG). It uses two distinct stages of processing, namely, syntactic processing followed by semantic processing. Syntactic processing makes the processing more general and robust. CPG is a dependency framework in which the analysis is in terms of syntactico-semantic relations. The closeness of these relations makes semantic processing easier and more accurate. It also makes the systems more portable.

A Novel Approach Towards Building a Portable NLIDB System Using the Computational Paninian Grammar Framework

In this paper, we describe our experiments on applying combination of Malt, MST and Turbo Parsers for Hindi dependency parsing as part of a shared task at MTPIL 2012 Workshop, COLING 2012. We explore the usage and adoption of the recently released Turbo Parser for parsing Indian languages. Various configurations of each parser are explored before combination in order to adjust them for two different settings of the data (with gold-standard and automatic Part-Of-Speech tags). We achieved a best result of 96.50% unlabeled attachment score (UAS), 92.90% labeled accuracy (LA), 91.49% labeled attachment score (LAS) using voting method on data with gold POS tags. In case of data with automatic POS tags, we achieved a best result of 93.99% UAS, 90.04% LA and 87.84% LAS respectively.

Deepak Malladi

Papers

A Novel Approach Towards Building a Portable NLIDB System Using the Computational Paninian Grammar Framework

Ensembling Various Dependency Parsers: Adopting Turbo Parser for Indian Languages