Essays about: "Natural language processing"

Showing result 1 - 5 of 260 essays containing the words Natural language processing.

  1. 1. Understand me, do you? : An experiment exploring the natural language understanding of two open source chatbots

    University essay from Blekinge Tekniska Högskola/Institutionen för programvaruteknik; Blekinge Tekniska Högskola/Institutionen för programvaruteknik

    Author : Linnéa Olofsson; Heidi Patja; [2021]
    Keywords : chatbot; natural language processing; natural language understanding; intent classification;

    Abstract : What do you think of when you hear the word chatbot? A helpful assistant when booking flight tickets? Maybe a frustrating encounter with a company’s customer support, or smart technologies that will eventually take over your job? The field of chatbots is under constant development and bots are more and more taking a place in our everyday life, but how well do they really understand us humans?  The objective of this thesis is to investigate how capable two open source chatbots are in understanding human language when given input containing spelling errors, synonyms or faulty syntax. The study will further investigate if the bots get better at identifying what the user’s intention is when supplied with more training data to base their analysis on. READ MORE

  2. 2. Named-entity recognition with BERT for anonymization of medical records

    University essay from Linköpings universitet/Institutionen för datavetenskap

    Author : Olle Bridal; [2021]
    Keywords : NLP; anonymization; de-identification; NER; BERT; medical records; Swedish;

    Abstract : Sharing data is an important part of the progress of science in many fields. In the largely deep learning dominated field of natural language processing, textual resources are in high demand. In certain domains, such as that of medical records, the sharing of data is limited by ethical and legal restrictions and therefore requires anonymization. READ MORE

  3. 3. Exploring Construction of a Company Domain-Specific Knowledge Graph from Financial Texts Using Hybrid Information Extraction

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Chun-Heng Jen; [2021]
    Keywords : Natural Language Processing; Information Extraction; Named Entity Recognition; Relation Extraction; Knowledge Graph; Naturlig språkbehandling; Informationsextraktion; Namngiven Entitetsigenkänning; Relationsextraktion; Kunskapsgraf;

    Abstract : Companies do not exist in isolation. They are embedded in structural relationships with each other. Mapping a given company’s relationships with other companies in terms of competitors, subsidiaries, suppliers, and customers are key to understanding a company’s major risk factors and opportunities. READ MORE

  4. 4. Data Segmentation Using NLP: Gender and Age

    University essay from Uppsala universitet/Avdelningen för datalogi; Uppsala universitet/Avdelningen för datalogi

    Author : Gustav Demmelmaier; Carl Westerberg; [2021]
    Keywords : Natural language processing; NLP; sentiment analysis; machine learning; demographics; demographic factors; gender; age; ethics;

    Abstract : Natural language processing (NLP) opens the possibilities for a computer to read, decipher, and interpret human languages to eventually use it in ways that enable yet further understanding of the interaction and communication between the human and the computer. When appropriate data is available, NLP makes it possible to determine not only the sentiment information of a text but also information about the author behind an online post. READ MORE

  5. 5. Evaluation of Approaches for Representation and Sentiment of Customer Reviews

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Stavros Giorgis; [2021]
    Keywords : machine learning; nlp; text analytics; sentiment analysis; transformers; tfidf; bow; fasttext; word2vec; bert; xlnet; roberta; maskininlärning; nlp; textanalys; sentimentanalys; transformatorer; tfidf; bow; fasttext; word2vec; bert; xlnet; roberta;

    Abstract : Classification of sentiment on customer reviews is a real-world application for many companies that offer text analytics and opinion extraction on customer reviews on different domains such as consumer electronics, hotels, restaurants, and car rental agencies. Natural Language Processing’s latest progress has seen the development of many new state-of-the-art approaches for representing the meaning of sentences, phrases, and words in the text using vector space models, so-called embeddings. READ MORE