Word Representations and Machine Learning Models for Implicit Sense Classification in Shallow Discourse Parsing

CoNLL 2015 featured a shared task on shallow discourse parsing. In 2016, the efforts continued with an increasing focus on sense classification. In the case of implicit sense classification, there was an interesting mix of traditional and modern machine learning classifiers using word representation...

Full description

Bibliographic Details
Main Author:	Callin, Jimmy
Format:	Others
Language:	English
Published:	Uppsala universitet, Institutionen för lingvistik och filologi 2017
Subjects:	machine learning neural networks word representations word embeddings distributional semantic models word vectors discourse parsing shallow discourse parsing maskininlärning neurala nätverk ordrepresentationer distributionella semantiska modeller diskursparsning Language Technology (Computational Linguistics) Språkteknologi (språkvetenskaplig databehandling)
Online Access:	http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-325876

id	ndltd-UPSALLA1-oai-DiVA.org-uu-325876
record_format	oai_dc
spelling	ndltd-UPSALLA1-oai-DiVA.org-uu-3258762018-01-14T05:11:32ZWord Representations and Machine Learning Models for Implicit Sense Classification in Shallow Discourse ParsingengCallin, JimmyUppsala universitet, Institutionen för lingvistik och filologi2017machine learningneural networksword representationsword embeddingsdistributional semantic modelsword vectorsdiscourse parsingshallow discourse parsingmaskininlärningneurala nätverkordrepresentationerdistributionella semantiska modellerdiskursparsningLanguage Technology (Computational Linguistics)Språkteknologi (språkvetenskaplig databehandling)CoNLL 2015 featured a shared task on shallow discourse parsing. In 2016, the efforts continued with an increasing focus on sense classification. In the case of implicit sense classification, there was an interesting mix of traditional and modern machine learning classifiers using word representation models. In this thesis, we explore the performance of a number of these models, and investigate how they perform using a variety of word representation models. We show that there are large performance differences between word representation models for certain machine learning classifiers, while others are more robust to the choice of word representation model. We also show that with the right choice of word representation model, simple and traditional machine learning classifiers can reach competitive scores even when compared with modern neural network approaches. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-325876application/pdfinfo:eu-repo/semantics/openAccess
collection	NDLTD
language	English
format	Others
sources	NDLTD
topic	machine learning neural networks word representations word embeddings distributional semantic models word vectors discourse parsing shallow discourse parsing maskininlärning neurala nätverk ordrepresentationer distributionella semantiska modeller diskursparsning Language Technology (Computational Linguistics) Språkteknologi (språkvetenskaplig databehandling)
spellingShingle	machine learning neural networks word representations word embeddings distributional semantic models word vectors discourse parsing shallow discourse parsing maskininlärning neurala nätverk ordrepresentationer distributionella semantiska modeller diskursparsning Language Technology (Computational Linguistics) Språkteknologi (språkvetenskaplig databehandling) Callin, Jimmy Word Representations and Machine Learning Models for Implicit Sense Classification in Shallow Discourse Parsing
description	CoNLL 2015 featured a shared task on shallow discourse parsing. In 2016, the efforts continued with an increasing focus on sense classification. In the case of implicit sense classification, there was an interesting mix of traditional and modern machine learning classifiers using word representation models. In this thesis, we explore the performance of a number of these models, and investigate how they perform using a variety of word representation models. We show that there are large performance differences between word representation models for certain machine learning classifiers, while others are more robust to the choice of word representation model. We also show that with the right choice of word representation model, simple and traditional machine learning classifiers can reach competitive scores even when compared with modern neural network approaches.
author	Callin, Jimmy
author_facet	Callin, Jimmy
author_sort	Callin, Jimmy
title	Word Representations and Machine Learning Models for Implicit Sense Classification in Shallow Discourse Parsing
title_short	Word Representations and Machine Learning Models for Implicit Sense Classification in Shallow Discourse Parsing
title_full	Word Representations and Machine Learning Models for Implicit Sense Classification in Shallow Discourse Parsing
title_fullStr	Word Representations and Machine Learning Models for Implicit Sense Classification in Shallow Discourse Parsing
title_full_unstemmed	Word Representations and Machine Learning Models for Implicit Sense Classification in Shallow Discourse Parsing
title_sort	word representations and machine learning models for implicit sense classification in shallow discourse parsing
publisher	Uppsala universitet, Institutionen för lingvistik och filologi
publishDate	2017
url	http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-325876
work_keys_str_mv	AT callinjimmy wordrepresentationsandmachinelearningmodelsforimplicitsenseclassificationinshallowdiscourseparsing
_version_	1718610003274760192

Word Representations and Machine Learning Models for Implicit Sense Classification in Shallow Discourse Parsing

Similar Items