21 |
The Language of Dreams: Application of Linguistics-Based Approaches for the Automated Analysis of Dream Experiences
|
|
|
|
In: Clocks & Sleep ; Volume 3 ; Issue 3 ; Pages 35-514 (2021)
|
|
BASE
|
|
Show details
|
|
22 |
Completing WordNets with Sememe Knowledge
|
|
|
|
In: Electronics; Volume 11; Issue 1; Pages: 79 (2021)
|
|
BASE
|
|
Show details
|
|
23 |
Combination of Time Series Analysis and Sentiment Analysis for Stock Market Forecasting
|
|
|
|
In: Graduate Theses and Dissertations (2021)
|
|
BASE
|
|
Show details
|
|
24 |
Comparing vector document representation methods for authorship identification ; Comparando métodos de representação vectorial de documentos para identificação de autoria
|
|
Quintanilla, Pamela Rosy Revuelta. - : Biblioteca Digital de Teses e Dissertações da USP, 2021. : Universidade de São Paulo, 2021. : Instituto de Matemática e Estatística, 2021
|
|
BASE
|
|
Show details
|
|
25 |
Sulle tracce dell’espressione dell’interiorità: analisi diacronica di un corpus di narrativa italiana del XIX-XX secolo
|
|
|
|
BASE
|
|
Show details
|
|
26 |
Improved GloVe Word Embedding Using Linear Weighting Scheme for Word Similarity Tasks
|
|
|
|
In: Electronic Theses and Dissertations (2021)
|
|
Abstract:
One of the trends in Natural Language Processing (NLP) is the use of word embedding. Its aim is to build a low dimensional vector representation of words from text corpora. Global Vectors for Word Representation (GloVe) and Sikp-Gram with Negative Sampling (SGNS) are two representative word embedding methods. Existing papers have different conclusions on the performance of these two methods. This thesis focuses on GloVe and studies its commonalities and differences with SGNS. Word co-occurrence is the cornerstone of all word embedding algorithms. One difference between GloVe and SGNS is the definition of co-occurrence. The weight of co-occurring words tapers o↵ with the distance between them. GloVe and SGNS adopts different weighting schemes. In SGNS, weight decreases linearly with the distance. In GloVe, the weight decreases harmonically, giving less weight to the words in the center of the window. We propose GloVe-L (GloVe Linear), by changing the weighting scheme to the linear weighting. We find that GloVe-L outperforms GloVe consistently in word similarity tasks. The conclusion is supported by extensive experiments on 8 Word evaluation benchmarks on Wikipedia training corpus. The thesis also explores the impact of hyper-parameters on the result, including window size and xmax in GloVe. Another interesting observation is that Glove-L does not work well for word analogy tasks.
|
|
Keyword:
Computer Sciences; GloVe; Word co-occurrence; Word embedding; Word2Vec
|
|
URL: https://scholar.uwindsor.ca/cgi/viewcontent.cgi?article=9658&context=etd https://scholar.uwindsor.ca/etd/8653
|
|
BASE
|
|
Hide details
|
|
27 |
On The Role of Machine Learning in A Human Learning Process
|
|
|
|
In: Teaching Culturally and Linguistically Diverse International Students in Open or Online Learning Environments: A Research Symposium (2021)
|
|
BASE
|
|
Show details
|
|
28 |
Detection of Hate Speech Spreaders using Convolutional Neural Networks
|
|
|
|
BASE
|
|
Show details
|
|
29 |
Whatever it takes to understand a central banker: Embedding their words using neural networks
|
|
|
|
BASE
|
|
Show details
|
|
30 |
Complete Variable-Length Codes: An Excursion into Word Edit Operations
|
|
|
|
In: LATA 2020 ; https://hal.archives-ouvertes.fr/hal-02389403 ; LATA 2020, Mar 2020, Milan, Italy (2020)
|
|
BASE
|
|
Show details
|
|
31 |
Apprentissage de plongements de mots sur des corpus en langue de spécialité : une étude d’impact
|
|
|
|
In: Actes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 3 : Rencontre des Étudiants Chercheurs en Informatique pour le TAL ; 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 3 : Rencontre des Étudiants Chercheurs en Informatique pour le TAL ; https://hal.archives-ouvertes.fr/hal-02786198 ; 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 3 : Rencontre des Étudiants Chercheurs en Informatique pour le TAL, Jun 2020, Nancy, France. pp.164-178 (2020)
|
|
BASE
|
|
Show details
|
|
32 |
Unsupervised cross-lingual representation modeling for variable length phrases ; Apprentissage de représentations cross-lingue d’expressions de longueur variable
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-02938554 ; Computation and Language [cs.CL]. Université de Nantes, 2020. English (2020)
|
|
BASE
|
|
Show details
|
|
33 |
Word Representations Concentrate and This is Good News!
|
|
|
|
In: CoNLL 2020 - 24th Conference on Computational Natural Language Learning ; https://hal.univ-grenoble-alpes.fr/hal-03356609 ; CoNLL 2020 - 24th Conference on Computational Natural Language Learning, Association for Computational Linguistics (ACL), Nov 2020, Online, France. pp.325-334, ⟨10.18653/v1/2020.conll-1.25⟩ (2020)
|
|
BASE
|
|
Show details
|
|
34 |
Implementing Eco’s Model Reader with WordEmbeddings. An Experiment on Facebook Ideological Bots
|
|
|
|
In: JADT - Journées d'analyse des données textuelles ; https://hal.archives-ouvertes.fr/hal-03144105 ; JADT - Journées d'analyse des données textuelles, Jun 2020, Toulouse, France (2020)
|
|
BASE
|
|
Show details
|
|
35 |
Natural language understanding in argumentative dialogue systems ...
|
|
|
|
BASE
|
|
Show details
|
|
36 |
Automatic Creation of Correspondence Table of Meaning Tags from Two Dictionaries in One Language Using Bilingual Word Embedding
|
|
|
|
BASE
|
|
Show details
|
|
37 |
ArAutoSenti: Automatic annotation and new tendencies for sentiment classification of Arabic messages
|
|
|
|
BASE
|
|
Show details
|
|
38 |
French AXA Insurance Word Embeddings : Effects of Fine-tuning BERT and Camembert on AXA France’s data
|
|
Zouari, Hend. - : KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020
|
|
BASE
|
|
Show details
|
|
39 |
Entropy-Based Approach for the Detection of Changes in Arabic Newspapers’ Content
|
|
|
|
In: Entropy ; Volume 22 ; Issue 4 (2020)
|
|
BASE
|
|
Show details
|
|
40 |
A Framework for Word Embedding Based Automatic Text Summarization and Evaluation
|
|
|
|
In: Information ; Volume 11 ; Issue 2 (2020)
|
|
BASE
|
|
Show details
|
|
|
|