Page: 1 2 3 4 5 6 7 8 9... 373
88 |
StaResGRU-CNN with CMedLMs: a stacked residual GRU-CNN with pre-trained biomedical language models for predictive intelligence
|
|
|
|
BASE
|
|
Show details
|
|
89 |
Machine Learning approaches for Topic and Sentiment Analysis in multilingual opinions and low-resource languages: From English to Guarani
|
|
|
|
BASE
|
|
Show details
|
|
90 |
Brazilian Portuguese verbal databases ; Bases lexicais verbais do português brasileiro
|
|
|
|
In: Domínios de Lingu@gem; Ahead of Print ; 1980-5799 (2022)
|
|
BASE
|
|
Show details
|
|
91 |
Representation learning of natural language and its application to language understanding and generation
|
|
|
|
Abstract:
How to properly represent language is a crucial and fundamental problem in Natural Language Processing (NLP). Language representation learning aims to encode rich information such as the syntax and semantics of the language into dense vectors. It facilitates the modeling, manipulation and analysis of natural language in computational linguistics. Existing algorithms utilize corpus statistics such as word co-occurrences to learn general-purpose language representation. Recent advances in generic representation integrate intensive information such as contextualized features from unlabeled text corpora. In this dissertation, we continue this line of research to incorporate rich knowledge into generic embeddings. We show that word representation could be enriched with various information including temporal and spatial variations as well as syntactic functionalities, and that text representation could be refined with topical knowledge. Moreover, we develop an insight into the geometry of pre-trained representation, and connect it to the semantic understanding such as identifying the idiomatic word usage. Besides generic representation, task-dependent representation is also extensively studied in downstream applications, where the representation is trained to encode domain information from labeled datasets. This dissertation leverages the capability of neural network models to integrate the task-specific supervision into language representations. We introduce new deep learning models and algorithms to train representations with external knowledge in annotated data. It is shown that the learned representation can assist in various downstream tasks in language understanding such as text classification and language generation such as text style transfer. ; U of I Only ; Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system
|
|
Keyword:
Language Generation; Language Understanding; Natural Language Processing; Representation Learning
|
|
URL: http://hdl.handle.net/2142/108110
|
|
BASE
|
|
Hide details
|
|
92 |
Detecting weak and strong Islamophobic hate speech on social media
|
|
|
|
BASE
|
|
Show details
|
|
93 |
An Empirical Study of Factors Affecting Language-Independent Models
|
|
|
|
BASE
|
|
Show details
|
|
94 |
Using Geolocated Text to Quantify Location in Real Estate Appraisal
|
|
|
|
BASE
|
|
Show details
|
|
95 |
TSM: Measuring the Enticement of Honeyfiles with Natural Language Processing
|
|
|
|
BASE
|
|
Show details
|
|
96 |
Modeling Phishing Decision using Instance Based Learning and Natural Language Processing
|
|
|
|
BASE
|
|
Show details
|
|
97 |
What to prioritize? Natural Language Processing for the Development of a Modern Bug Tracking Solution in Hardware Development
|
|
|
|
BASE
|
|
Show details
|
|
98 |
Eine agentenbasierte Architektur für Programmierung mit gesprochener Sprache
|
|
|
|
BASE
|
|
Show details
|
|
99 |
Um método adaptativo para análise sintática do Português Brasileiro. ; An adaptive method for syntactic analysis of Brazilian Portuguese.
|
|
Padovani, Djalma. - : Biblioteca Digital de Teses e Dissertações da USP, 2022. : Universidade de São Paulo, 2022. : Escola Politécnica, 2022
|
|
BASE
|
|
Show details
|
|
100 |
Multitask Pointer Network for Multi-Representational Parsing
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9... 373
|
|