scholarly journals A novel framework for synthesizing nested queries in SQL from business requirements language

2021 ◽  
Vol 12 (2) ◽  
pp. 2680-2691
Author(s):  
Mathew George, Et. al.
Keyword(s):  
Natural Language ◽  
Query Language ◽  
Parallel Computations ◽  
Intermediate Language ◽  
Language Level ◽  
The Past ◽  
Language Constructs ◽  
Programming Techniques ◽  
Nested Queries ◽  
Business Requirements

Different methods and systems were proposed in the past for translating Natural Language (NL) statements in to Structured Query Language (SQL) queries. Translating statements resultingin‘nested’queries havealways been a challenge and was not effectively handled. This work proposes a framework for translating requirement statementsresulting inthe construction of nested Queries. While translating nested scenarios; often thereis a need to create sub-queriesthat execute inpipeline orin parallel or both operating together.Lambda Calculus is found to be effective in representing the intermediate expressions and helps in performing the transformations that are needed in translating specific predicates into SQL, but its inflexibility in combining parallel computations is a constraint. To represent clauses that are in parallel or arein pipeline,and to perform the required transformationson theintermediate expressions involving these,more advancedprogramming constructs are needed.This work recommends the use of advanced language constructs and adoptsfunctional programming techniques for performing the required transformation at the intermediate language level.

Methods for selecting authentic texts in accordance with the language level of students while teaching German

2021 ◽  
Vol 69 (08) ◽  
pp. 32-37
Author(s):  
Turan Şahin qızı Kərimbəyli ◽  
Keyword(s):  
Foreign Language ◽  
Natural Language ◽  
Key Words ◽  
Intercultural Communication ◽  
Selection Criteria ◽  
Foreign Languages ◽  
Authentic Texts ◽  
Language Level ◽  
Authentic Text ◽  
Communicative Teaching

Today our main goal is to use authentic texts, including the study of the peculiarities of intercultural communication in the environment of communicative teaching of foreign languages. Authentic text reflects the use of natural language. It should be noted that the teaching of authentic texts in teaching a foreign language should be determined by the language level of the students. The selection criteria for authentic texts in German differ depending on the language level of the students. Key words: authentic texts, intercultural communication, communicative learning

Graph analytics and visualization for cyber situational understanding

2021 ◽  
pp. 154851292110513
Author(s):  
Steven Noel ◽  
Stephen Purdy ◽  
Annie O’Rourke ◽  
Edward Overly ◽  
Brianna Chen ◽  
...  
Keyword(s):  
Natural Language ◽  
Detailed Analysis ◽  
Ad Hoc ◽  
Query Language ◽  
Software Components ◽  
Proof Of Concept ◽  
Graph Analytics ◽  
The Core ◽  
Interactive Visualizations ◽  
Graph Queries

This paper describes the Cyber Situational Understanding (Cyber SU) Proof of Concept (CySUP) software system for exploring advanced Cyber SU capabilities. CySUP distills complex interrelationships among cyberspace entities to provide the “so what” of cyber events for tactical operations. It combines a variety of software components to build an end-to-end pipeline for live data ingest that populates a graph knowledge base, with query-driven exploratory analysis and interactive visualizations. CySUP integrates with the core infrastructure environment supporting command posts to provide a cyber overlay onto a common operating picture oriented to tactical commanders. It also supports detailed analysis of cyberspace entities and relationships driven by ad hoc graph queries, including the conversion of natural language inquiries to formal query language. To help assess its Cyber SU capabilities, CySUP leverages automated cyber adversary emulation to carry out controlled cyberattack campaigns that impact elements of tactical missions.

Sentence Similarity Algorithm Based on Fused Bi-Channel Dependency Matching Feature

2019 ◽  
Vol 34 (07) ◽  
pp. 2050019
Author(s):  
Xiaohan Guan ◽  
Jianhui Han ◽  
Zhi Liu ◽  
Mengmeng Zhang
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Question Answering ◽  
Calculation Methods ◽  
Matching Problem ◽  
Position Information ◽  
The Past ◽  
Vector Interaction ◽  
Sentence Similarity ◽  
Similarity Algorithm

Many tasks of natural language processing such as information retrieval, intelligent question answering, and machine translation require the calculation of sentence similarity. The traditional calculation methods used in the past could not solve semantic understanding problems well. First, the model structure based on Siamese lack of interaction between sentences; second, it has matching problem which contains lacking position information and only using partial matching factor based on the matching model. In this paper, a combination of word and word’s dependence is proposed to calculate the sentence similarity. This combination can extract the word features and word’s dependency features. To extract more matching features, a bi-directional multi-interaction matching sequence model is proposed by using word2vec and dependency2vec. This model obtains matching features by convolving and pooling the word-granularity (word vector, dependency vector) interaction sequences in two directions. Next, the model aggregates the bi-direction matching features. The paper evaluates the model on two tasks: paraphrase identification and natural language inference. The experimental results show that the combination of word and word’s dependence can enhance the ability of extracting matching features between two sentences. The results also show that the model with dependency can achieve higher accuracy than these models without using dependency.

Automatic Extraction of Valency Information

1995 ◽  
Vol 107-108 ◽  
pp. 89-111
Author(s):  
Jan Daugaard ◽  
Sabine Kirchmeier-Andersen ◽  
Lene Schøsler
Keyword(s):  
Natural Language ◽  
Research Team ◽  
Corpus Analysis ◽  
Automatic Extraction ◽  
The Past ◽  
Natural Language Parsing ◽  
Theoretical Assumptions ◽  
The Creation

Abstract The above research team has for the past 4 years been working on a database of valency schemes for 4,000 Danish verbs. First we present the underlying theoretical assumptions for the creation of valency schemes. Then the tools to perform automatic extraction of valency information from corpora are described. Finally, the results are presented. Keywords: natural language parsing, Danish, lexical valency, the Pronominal Approach, corpus analysis.

scholarly journals Methodological modifications when testing machine learning-enabled products: A preliminary framework

2019 ◽  
Vol 63 (1) ◽  
pp. 2236-2238
Author(s):  
Linda Huber ◽  
Rebecca Williamson
Keyword(s):  
Machine Learning ◽  
Natural Language ◽  
Testing Machine ◽  
Product Concept ◽  
The Past ◽  
System Output ◽  
Inputs And Outputs

Machine-learning (ML) enabled products and features allow for an expanded set of user inputs and system outputs. In the case of consumer-facing ML-enabled products, examples of this include the ability to take natural language as an input, or to generate personalized feeds or recommendations (system output) based on the behavior of a user. Based on our experience conducting UX research on ML-enabled products, we propose that this expanded set of inputs and outputs requires that we modify our usual methodologies in a few ways, depending on the product & research objectives. Specifically, we propose that researching ML- enabled products may require 1) more time for the user to explore or experiment with the product 2) talking to more user types and/or 3) more comprehensive prototypes or presentation of the product concept. To flesh this framework out, we present three examples of ML-enabled products we tested in the past few years and the methodological modifications required.

scholarly journals Spanish participios activos are adjectival antipassives

2019 ◽  
Vol 34 (1) ◽  
pp. 1-37
Author(s):  
Grant Armstrong
Keyword(s):  
Natural Language ◽  
Word Formation ◽  
Linguistic Theory ◽  
External Argument ◽  
The Past ◽  
Linguistic Inquiry ◽  
Adjectival Passives ◽  
The Right ◽  
Semantic Properties

Abstract In many languages a set of adjectives are characterized by their “past/passive” participial morphology. Lexicalist and syntactic approaches to word formation converge on the claim that such adjectives can be derived from verbal inputs with no external argument but never from verbal inputs with an external argument. That is, there are “adjectival passives” but no “adjectival antipassives” marked with the same morphology. I argue that a sub-class of adjectives marked with the “past/passive” participial morpheme –do in Spanish, labeled participios activos in descriptive grammars, should be treated as adjectival antipassives in precisely this sense. I propose that Spanish has an Asp head that (i) is spelled out with “past/passive” participial morphology and (ii) selects an unergative verbal input creating a state/property whose argument corresponds to the external argument of that verbal source. If on the right track, the proposal supports the existence of a typology of adjectivizing heads that are spelled out uniformly with “past/passive” participial morphology but must be distinguished in terms of selectional and semantic properties (Bruening 2014, Word formation is syntactic: Adjectival passives in English. Natural Language and Linguistic Theory 32. 363–422; Embick 2004, On the structure of resultative participles in English. Linguistic Inquiry 35. 355–392). It differs from previous approaches in claiming that such a typology must include root-derived adjectives, as well as ‘active (=unergative)’ and ‘passive’ deverbal adjectives.

scholarly journals Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation

2018 ◽  
Vol 61 ◽  
pp. 65-170 ◽  
Author(s):  
Albert Gatt ◽  
Emiel Krahmer
Keyword(s):  
Natural Language ◽  
State Of The Art ◽  
Natural Language Generation ◽  
Data Driven ◽  
Research Topics ◽  
Language Generation ◽  
The Past ◽  
Current State ◽  
Linguistic Input ◽  
New Applications

This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input. A survey of NLG is timely in view of the changes that the field has undergone over the past two decades, especially in relation to new (usually data-driven) methods, as well as new applications of NLG technology. This survey therefore aims to (a) give an up-to-date synthesis of research on the core tasks in NLG and the architectures adopted in which such tasks are organised; (b) highlight a number of recent research topics that have arisen partly as a result of growing synergies between NLG and other areas of artificial intelligence; (c) draw attention to the challenges in NLG evaluation, relating them to similar challenges faced in other areas of NLP, with an emphasis on different evaluation methods and the relationships between them.

scholarly journals Product Programs in the Wild: Retrofitting Program Verifiers to Check Information Flow Security

2021 ◽  
pp. 718-741
Author(s):  
Marco Eilers ◽  
Severin Meier ◽  
Peter Müller
Keyword(s):  
Programming Languages ◽  
Information Flow ◽  
Three Dimensions ◽  
Information Flow Security ◽  
Intermediate Language ◽  
Language Level ◽  
Product Construction ◽  
In The Wild ◽  
Verification Tools ◽  
Functional Correctness

AbstractMost existing program verifiers check trace properties such as functional correctness, but do not support the verification of hyperproperties, in particular, information flow security. In principle, product programs allow one to reduce the verification of hyperproperties to trace properties and, thus, apply standard verifiers to check them; in practice, product constructions are usually defined only for simple programming languages without features like dynamic method binding or concurrency and, consequently, cannot be directly applied to verify information flow security in a full-fledged language. However, many existing verifiers encode programs from source languages into simple intermediate verification languages, which opens up the possibility of constructing a product program on the intermediate language level, reusing the existing encoding and drastically reducing the effort required to develop new verification tools for information flow security. In this paper, we explore the potential of this approach along three dimensions: (1) Soundness: We show that the combination of an encoding and a product construction that are individually sound can still be unsound, and identify a novel condition on the encoding that ensures overall soundness. (2) Concurrency: We show how sequential product programs on the intermediate language level can be used to verify information flow security of concurrent source programs. (3) Performance: We implement a product construction in Nagini, a Python verifier built upon the Viper intermediate language, and evaluate it on a number of challenging examples. We show that the resulting tool offers acceptable performance, while matching or surpassing existing tools in its combination of language feature support and expressiveness.

scholarly journals MQALD: Evaluating the impact of modifiers in question answering over knowledge graphs

Semantic Web ◽  
2021 ◽  
pp. 1-17
Author(s):  
Lucia Siciliani ◽  
Pierpaolo Basile ◽  
Pasquale Lops ◽  
Giovanni Semeraro
Keyword(s):  
Natural Language ◽  
Question Answering ◽  
Query Language ◽  
State Of The Art ◽  
Translation Process ◽  
Specific Data ◽  
Data Query ◽  
Question Answering Systems ◽  
Knowledge Graphs ◽  
The Impact

Question Answering (QA) over Knowledge Graphs (KG) aims to develop a system that is capable of answering users’ questions using the information coming from one or multiple Knowledge Graphs, like DBpedia, Wikidata, and so on. Question Answering systems need to translate the user’s question, written using natural language, into a query formulated through a specific data query language that is compliant with the underlying KG. This translation process is already non-trivial when trying to answer simple questions that involve a single triple pattern. It becomes even more troublesome when trying to cope with questions that require modifiers in the final query, i.e., aggregate functions, query forms, and so on. The attention over this last aspect is growing but has never been thoroughly addressed by the existing literature. Starting from the latest advances in this field, we want to further step in this direction. This work aims to provide a publicly available dataset designed for evaluating the performance of a QA system in translating articulated questions into a specific data query language. This dataset has also been used to evaluate three QA systems available at the state of the art.

Sign in / Sign up

Export Citation Format

Share Document