Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 7 of 7 for “"sentence representations"”.
-
Conditional Neural Language Models for Multimodal Learning and Natural Language Understanding
… neural language model for learning distributed representations of attributes and meta data. Our model allows for contextual word relatedness comparisons through decompositions of a word embedding tensor. Finally we show how we can abstract the skip-gram model for learning word representations to …
-
Identifying customer needs from user-generated content
… to filter out non-informative content and dense sentence representations to identify sufficiently different sentences for manual review. An empirical proof-of-concept compares customer needs for oral care products identified from online reviews (UGC) with customer needs identified by a …
-
Structure and geometry in sequence-processing neural networks
… how various language features affect model representations and long-term behavior through the use of linear probing techniques. To tease out the geometrical properties of BERT's internal representations, we task the model with 5 linguistic abstractions (word, part-of-speech, combinatory …
-
Geometries of word embeddings
… Both word2vec and GloVe are static whose word representations are independent of its context, while GPT and BERT are contextualized whose representations will change corresponding to the semantics conveyed by its surrounding words. In this dissertation, we study four problems associated with …
-
Neural approaches to discourse coherence: modeling, evaluation and application
… examine the effect of using contextualised word representations in single-task and multi-task setups. I evaluate my models on a synthetic dataset where incoherent documents are created by shuffling the sentence order in coherent original documents. The results show the efficacy of my multi-task …
-
Text mining at multiple granularity: leveraging subwords, words, phrases, and sentences
… to many levels of semantic granularity such as sentences, phrases, words, or subword structures. Once the text in represented at different levels of semantic granularity, we demonstrate techniques that can leverage the properly encoded text to solve a variety of NLP tasks. Specifically, this …
-
Morphological Segmentation During Silent Reading
… segmentation: (a) that it applies on phonemic representations, and (b) that it outputs affixal information that is taken up and used at representational levels higher than the lexical one. In two experiments, participants' eye-movements were monitored while they silently read sentences where …