|
|
Sentence representations with similarity interpretation
Svobodová, Zuzana ; Hudeček, Vojtěch (advisor) ; Libovický, Jindřich (referee)
Sentence representations - embeddings - obtained from neural network models are the core part of many applications in both academia and industry. Although embeddings reach great results in correlation with human sense of sentence similarity, there is often a lack of explanation for why models choose sentences to be similar. In this thesis, we strive to increase the interpretability of model embeddings by incorporating different semantic sentence level annotations in the learning process. We introduce a model called SBERTslice that produces embeddings that can distinguish nuanced semantic variations in text, including elements like negation, sentiment, named entities, emotional tone, and verb-oriented relation between words in a text. We evaluated SBERTslice embeddings in various text classification and semantic sim- ilarity tasks and for a majority of them, SBERTslice outperformed the original SBERT. 1
|
|
|
Low-resource methods for dialogue systems applications
Hudeček, Vojtěch ; Dušek, Ondřej (advisor) ; Skantze, Gabriel (referee) ; Schwarz, Petr (referee)
This thesis focuses on developing and improving task-oriented dialogue systems design in the rapidly growing landscape of artificial intelligence and natural language processing. We propose techniques that can substantially decrease development and deployment costs, motivated by the desire to make these systems more adaptable and scalable. We introduce multiple novel approaches to achieving these goals. Firstly, we present a weakly supervised automatic data annotation pipeline that can transform raw dialogue transcript into a refined set of semantically coherent concepts, bypassing the need for exhaustive manual annotations in natural language understanding for a given domain and significantly streamlining the development process. We also explore the largely uninvestigated field of latent variable models in task-oriented dialogue system modeling. These models offer excellent capabilities with the potential to uncover the structure of behavioral patterns seen in the dialogue through inspection of the latent space and comparison with actions taken by the model. Furthermore, we explore the potential of these models to form hierarchical representations using our proposed architecture. Following recent progress in the field, we harness the power of pre-trained large language models using in-context learning. We...
|
|
|
Improving text-to-speech in spoken dialogue systems by employing user's feedback
Hudeček, Vojtěch ; Žabokrtský, Zdeněk (advisor) ; Peterek, Nino (referee)
Although spoken dialogue systems have greatly improved, they still cannot handle communications involving unknown topics. One of the problems is, that they experience difficulties when they should pronounce unknown words. We will investigate methods that can improve spoken dialogue systems by correcting the pronunciation of unknown words. This is a crucial step to provide a better user experience, since for example mispronounced proper nouns are highly undesirable. Incorrect pronunciation is caused by imperfect phonetic representation of the word. We aim to detect incorrectly pronounced words, use knowledge about the pronunciation and user's feedback and correct the transcriptions accordingly. Furthermore, the learned phonetic transcriptions can be added to the speech recognition module's vocabulary. Thus extracting correct pronunciations benefits both speech recognition and text-to-speech components of the dialogue systems.
|
|
|
Distributed video compression in the peer to peer networks
Hudeček, Vojtěch ; Steinhauser, Antonín (advisor) ; Jiráček, Zbyněk (referee)
Despite today's computers' performance there still exist some tasks that are quite time demanding. Nature of some of these tasks allows to split them into smaller parts that can be processed in parallel. Distributing work among more computers in order to speed up such processes is a common technique. However, most of the approaches use client-server architecture to achieve this goal. We provide purely peer-to-peer solution which allows high level of scalability, error recovery and easy maintaining. No special role is needed in our framework and each node can join the network at any time. Also the system is able to deal with node failures, keeping the overall computation time reasonable. Tests showed that significant improvement can be achieved in local area networks. 1
|
guest ::
RSS feed.