From word embeddings to document similarities for improved information retrieval in software engineering

2016 ◽  
Author(s):  
Xin Ye ◽  
Hui Shen ◽  
Xiao Ma ◽  
Razvan Bunescu ◽  
Chang Liu
Keyword(s):  
Information Retrieval ◽  
Software Engineering ◽  
Word Embeddings

scholarly journals Linear Algebraic Structure of Word Senses, with Applications to Polysemy

2018 ◽  
Vol 6 ◽  
pp. 483-495 ◽  
Author(s):  
Sanjeev Arora ◽  
Yuanzhi Li ◽  
Yingyu Liang ◽  
Tengyu Ma ◽  
Andrej Risteski
Keyword(s):  
Information Retrieval ◽  
Random Walk ◽  
Algebraic Structure ◽  
Sparse Coding ◽  
Word Sense ◽  
Word Embeddings ◽  
Linear Superposition ◽  
Empirical Tests ◽  
Embedding Methods ◽  
Word Senses

Word embeddings are ubiquitous in NLP and information retrieval, but it is unclear what they represent when the word is polysemous. Here it is shown that multiple word senses reside in linear superposition within the word embedding and simple sparse coding can recover vectors that approximately capture the senses. The success of our approach, which applies to several embedding methods, is mathematically explained using a variant of the random walk on discourses model (Arora et al., 2016). A novel aspect of our technique is that each extracted word sense is accompanied by one of about 2000 “discourse atoms” that gives a succinct description of which other words co-occur with that word sense. Discourse atoms can be of independent interest, and make the method potentially more useful. Empirical tests are used to verify and support the theory.

Deep Learning

2020 ◽  
pp. 124-141 ◽  
Author(s):  
Menaga D. ◽  
Revathi S.
Keyword(s):  
Information Retrieval ◽  
Deep Learning ◽  
Software Engineering ◽  
Multimedia Information ◽  
Research Area ◽  
Multimedia Application ◽  
Information Process ◽  
Display Devices ◽  
Storage Devices ◽  
Major Application

Multimedia application is a significant and growing research area because of the advances in technology of software engineering, storage devices, networks, and display devices. With the intention of satisfying multimedia information desires of users, it is essential to build an efficient multimedia information process, access, and analysis applications, which maintain various tasks, like retrieval, recommendation, search, classification, and clustering. Deep learning is an emerging technique in the sphere of multimedia information process, which solves both the crisis of conventional and recent researches. The main aim is to resolve the multimedia-related problems by the use of deep learning. The deep learning revolution is discussed with the depiction and feature. Finally, the major application also explained with respect to different fields. This chapter analyzes the crisis of retrieval after providing the successful discussion of multimedia information retrieval that is the ability of retrieving an object of every multimedia.

scholarly journals A Data-Driven Strategy to Combine Word Embeddings in Information Retrieval

2021 ◽  
Author(s):  
Alfredo Silva ◽  
Marcelo Mendoza
Keyword(s):  
Information Retrieval ◽  
Natural Language Processing ◽  
Language Processing ◽  
Ad Hoc ◽  
Data Driven ◽  
Word Embeddings ◽  
Continuous Vector ◽  
Benchmark Data ◽  
Promising Line ◽  
Vector Representations

Word embeddings are vital descriptors of words in unigram representations of documents for many tasks in natural language processing and information retrieval. The representation of queries has been one of the most critical challenges in this area because it consists of a few terms and has little descriptive capacity. Strategies such as average word embeddings can enrich the queries' descriptive capacity since they favor the identification of related terms from the continuous vector representations that characterize these approaches. We propose a datadriven strategy to combine word embeddings. We use Idf combinations of embeddings to represent queries, showing that these representations outperform the average word embeddings recently proposed in the literature. Experimental results on benchmark data show that our proposal performs well, suggesting that data-driven combinations of word embeddings are a promising line of research in ad-hoc information retrieval.

Sign in / Sign up

Export Citation Format

Share Document