scholarly journals Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods

2010 ◽  
Vol 36 (3) ◽  
pp. 341-387 ◽  
Author(s):  
Nitin Madnani ◽  
Bonnie J. Dorr
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Recent Work ◽  
Language Processing ◽  
Data Driven ◽  
Future Trends ◽  
Automatic Construction ◽  
Work Done ◽  
Paraphrase Generation ◽  
Potential Use

The task of paraphrasing is inherently familiar to speakers of all languages. Moreover, the task of automatically generating or extracting semantic equivalences for the various units of language—words, phrases, and sentences—is an important part of natural language processing (NLP) and is being increasingly employed to improve the performance of several NLP applications. In this article, we attempt to conduct a comprehensive and application-independent survey of data-driven phrasal and sentential paraphrase generation methods, while also conveying an appreciation for the importance and potential use of paraphrases in the field of NLP research. Recent work done in manual and automatic construction of paraphrase corpora is also examined. We also discuss the strategies used for evaluating paraphrase generation techniques and briefly explore some future trends in paraphrase generation.

A Review and evaluation of Machine Translation methods for Lumasaaba

2020 ◽  
pp. 3-17
Author(s):  
Peter Nabende
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
Research Area ◽  
Data Driven ◽  
East African ◽  
Data Set ◽  
African Languages ◽  
Translation Methods

Natural Language Processing for under-resourced languages is now a mainstream research area. However, there are limited studies on Natural Language Processing applications for many indigenous East African languages. As a contribution to covering the current gap of knowledge, this paper focuses on evaluating the application of well-established machine translation methods for one heavily under-resourced indigenous East African language called Lumasaaba. Specifically, we review the most common machine translation methods in the context of Lumasaaba including both rule-based and data-driven methods. Then we apply a state of the art data-driven machine translation method to learn models for automating translation between Lumasaaba and English using a very limited data set of parallel sentences. Automatic evaluation results show that a transformer-based Neural Machine Translation model architecture leads to consistently better BLEU scores than the recurrent neural network-based models. Moreover, the automatically generated translations can be comprehended to a reasonable extent and are usually associated with the source language input.

scholarly journals Natural Language Processing Based Method for Clustering and Analysis of Aviation Safety Narratives

Aerospace ◽  
2020 ◽  
Vol 7 (10) ◽  
pp. 143
Author(s):  
Rodrigo L. Rose ◽  
Tejas G. Puranik ◽  
Dimitri N. Mavris
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Safety Data ◽  
Aviation Safety ◽  
Data Driven ◽  
Flight Safety ◽  
Commercial Aviation ◽  
Unique Challenge ◽  
Aviation Safety Reporting System

The complexity of commercial aviation operations has grown substantially in recent years, together with a diversification of techniques for collecting and analyzing flight data. As a result, data-driven frameworks for enhancing flight safety have grown in popularity. Data-driven techniques offer efficient and repeatable exploration of patterns and anomalies in large datasets. Text-based flight safety data presents a unique challenge in its subjectivity, and relies on natural language processing tools to extract underlying trends from narratives. In this paper, a methodology is presented for the analysis of aviation safety narratives based on text-based accounts of in-flight events and categorical metadata parameters which accompany them. An extensive pre-processing routine is presented, including a comparison between numeric models of textual representation for the purposes of document classification. A framework for categorizing and visualizing narratives is presented through a combination of k-means clustering and 2-D mapping with t-Distributed Stochastic Neighbor Embedding (t-SNE). A cluster post-processing routine is developed for identifying driving factors in each cluster and building a hierarchical structure of cluster and sub-cluster labels. The Aviation Safety Reporting System (ASRS), which includes over a million de-identified voluntarily submitted reports describing aviation safety incidents for commercial flights, is analyzed as a case study for the methodology. The method results in the identification of 10 major clusters and a total of 31 sub-clusters. The identified groupings are post-processed through metadata-based statistical analysis of the learned clusters. The developed method shows promise in uncovering trends from clusters that are not evident in existing anomaly labels in the data and offers a new tool for obtaining insights from text-based safety data that complement existing approaches.

scholarly journals Data-driven materials research enabled by natural language processing and information extraction

2020 ◽  
Vol 7 (4) ◽  
pp. 041317
Author(s):  
Elsa A. Olivetti ◽  
Jacqueline M. Cole ◽  
Edward Kim ◽  
Olga Kononova ◽  
Gerbrand Ceder ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Information Extraction ◽  
Language Processing ◽  
Data Driven ◽  
Materials Research

A Voice Calculator Based on Speech Error Correction

2013 ◽  
Vol 846-847 ◽  
pp. 1239-1242
Author(s):  
Yang Yang ◽  
Hui Zhang ◽  
Yong Qi Wang
Keyword(s):  
Natural Language Processing ◽  
Numerical Calculation ◽  
Speech Recognition ◽  
Natural Language ◽  
Error Correction ◽  
Recent Work ◽  
Language Processing ◽  
Speech Error ◽  
Parsing Algorithm ◽  
Recognition Errors

This paper presents our recent work towards the development of a voice calculator based on speech error correction and natural language processing. The calculator enhances the accuracy of speech recognition by classifying and summarizing recognition errors on numerical calculation speech recognition area, then constructing Pinyin-text-mapping library and replacement rules, and combing priority correction mechanism and memory correction mechanism of Pinyin-text-mapping. For the expression after correctly recognizing, the calculator uses recursive-descent parsing algorithm and synthesized attribute computing algorithm to calculate the final result and output the result using TTS engine. The implementation of this voice calculator makes a calculator more humane and intelligent.

scholarly journals Email phishing: text classification using natural language processing

2020 ◽  
Vol 1 (1) ◽  
pp. 1-12 ◽  
Author(s):  
Priyanka Verma ◽  
Anjali Goyal ◽  
Yogita Gigras
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Private Information ◽  
Credit Card ◽  
Solution Approach ◽  
Main Motive ◽  
Work Done ◽  
Day By Day

Phishing is networked theft in which the main motive of phishers is to steal any person’s private information, its financial details like account number, credit card details, login information, payment mode information by creating and developing a fake page or a fake web site, which look completely authentic and genuine. Nowadays email phishing has become a big threat to all, and is increasing day by day. Moreover detection of phishing emails have been considered an important research issue as phishing emails have been increasing day by day. Various techniques have been introduced and applied to deal with such a big issue. The major objective of this research paper is giving a detailed description on the classification of phishing emails using the natural language processing concepts. NLP (natural language processing) concepts have been applied for the classification of emails, along with that accuracy rate of various classifiers have been calculated. The paper is presented in four sections. An introduction about phishing its types, its history, statistics, life cycle, motivation for phishers and working of email phishing have been discussed in the first section. The second section covers various technologies of phishing- email phishing and also description of evaluation metrics. An overview of the various proposed solutions and work done by researchers in this field in form of literature review has been presented in the third section. The solution approach and the obtained results have been defined in the fourth section giving a detailed description about NLP concepts and working procedure.

scholarly journals Ask me in your own words: paraphrasing for multitask question answering

2021 ◽  
Vol 7 ◽  
pp. e759
Author(s):  
G. Thomas Hudson ◽  
Noura Al Moubayed
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Question Answering ◽  
Natural Language Understanding ◽  
Multitask Learning ◽  
Single Model ◽  
Language Understanding ◽  
Class Labels ◽  
Paraphrase Generation

Multitask learning has led to significant advances in Natural Language Processing, including the decaNLP benchmark where question answering is used to frame 10 natural language understanding tasks in a single model. In this work we show how models trained to solve decaNLP fail with simple paraphrasing of the question. We contribute a crowd-sourced corpus of paraphrased questions (PQ-decaNLP), annotated with paraphrase phenomena. This enables analysis of how transformations such as swapping the class labels and changing the sentence modality lead to a large performance degradation. Training both MQAN and the newer T5 model using PQ-decaNLP improves their robustness and for some tasks improves the performance on the original questions, demonstrating the benefits of a model which is more robust to paraphrasing. Additionally, we explore how paraphrasing knowledge is transferred between tasks, with the aim of exploiting the multitask property to improve the robustness of the models. We explore the addition of paraphrase detection and paraphrase generation tasks, and find that while both models are able to learn these new tasks, knowledge about paraphrasing does not transfer to other decaNLP tasks.

Sign in / Sign up

Export Citation Format

Share Document