| 1 |
Working memory and domain in DLD (Larson & Ellis Weismer, 2022) ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Working memory and domain in DLD (Larson & Ellis Weismer, 2022) ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Memory and linguistic demands of the Token Test (Pham et al., 2022) ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Memory and linguistic demands of the Token Test (Pham et al., 2022) ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Positive and negative priming differences between short-term and long-term identity coding of word-specific attentional priorities
|
|
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Generating Effective Sentence Representations: Deep Learning and Reinforcement Learning Approaches
|
|
|
|
In: Electronic Thesis and Dissertation Repository (2021)
|
|
Abstract:
Natural language processing (NLP) is one of the most important technologies of the information age. Understanding complex language utterances is also a crucial part of artificial intelligence. Many Natural Language applications are powered by machine learning models performing a large variety of underlying tasks. Recently, deep learning approaches have obtained very high performance across many NLP tasks. In order to achieve this high level of performance, it is crucial for computers to have an appropriate representation of sentences. The tasks addressed in the thesis are best approached having shallow semantic representations. These representations are vectors that are then embedded in a semantic space. We present a variety of novel approaches in deep learning applied to NLP for generating effective sentence representations in this space. These semantic representations can either be general or task-specific. We focus on learning task-specific sentence representations, where often these tasks have a good amount of overlap. We design a set of general purpose and task specific sentence encoders combining both word-level semantic knowledge and word- and sentence-level syntactic information. As a method for the former, we perform an intelligent amalgamation of word vectors using modern deep learning modules. For the latter, we use word-level knowledge, such as parts of speech, spelling, and suffix features, and sentence-level information drawn from natural language parse trees which provide the hierarchical structure of a sentence together with grammatical relations between the words. Further expertise is added with reinforcement learning which guides a machine learning model through a reward-penalty game. Rather than just striving for good performance, we always try to design models that are more transparent and explainable. We provide an intuitive explanation about the design of each model and how the model is making a decision. Our extensive experiments show that these models achieve competitive performance compared with the currently available state-of-the-art generalized and task-specific sentence encoders. All but one of the tasks dealt with English language texts. The multilingual semantic similarity task required creating a multilingual corpus for which we provide a novel semi-supervised approach to make artificial negative samples in the presence of just positive samples.
|
|
Keyword:
Artificial Intelligence and Robotics; Attention; Computer Sciences; Deep Learning; Long Short Term Memory; Reinforcement Learning; Sentence Representation; Transformer
|
|
URL: https://ir.lib.uwo.ca/etd/7780
https://ir.lib.uwo.ca/cgi/viewcontent.cgi?article=10295&context=etd
|
|
BASE
|
|
Hide details
|
|
|
| 13 |
Kesan emosi terhadap penerimaan bantuan dan hubungannya dengan kesejahteraan hidup dalam kalangan asnaf : satu kajian di Sabah
|
|
|
|
BASE
|
|
Show details
|
|
|
| 15 |
The psychometric evaluation of the Subjective Happiness Scale-Physically Disabled (SHS-PD) in Malaysia
|
|
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Environmental program and its effect on youth’s attitude towards the environment
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
