Essays about: "språkförståelse"
Showing result 1 - 5 of 11 essays containing the word språkförståelse.
-
1. Nested Noun Phrase Detection in English Text with BERT
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : In this project, we address the task of nested noun phrase identification in English sentences, where a phrase is defined as a group of words functioning as one unit in a sentence. Prior research has extensively explored the identification of various phrases for language understanding and text generation tasks. READ MORE
-
2. What comes next? : Investigating the neural correlates of predictability during conversation with fMRI
University essay from Stockholms universitet/Institutionen för lingvistikAbstract : The notion that prediction plays a role in language processing is getting less controversial, however research and discussion is ongoing as to the nature and extent of its involvement. Previous studies have mainly focused on prediction during comprehension in restricted paradigms. READ MORE
-
3. The brain in conversation: Mapping the neural correlates of turn-taking, production, and comprehension using fMRI
University essay from Stockholms universitet/Institutionen för lingvistikAbstract : Conversation is the primary mode of language use. A key feature of conversation is turn-taking, during which interlocutors rapidly switch between speaker and listener roles without conscious effort. READ MORE
-
4. Task-agnostic knowledge distillation of mBERT to Swedish
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Large transformer models have shown great performance in multiple natural language processing tasks. However, slow inference, strong dependency on powerful hardware, and large energy consumption limit their availability. READ MORE
-
5. VL Tasks: Which Models Suit? : Investigate Different Models for Swedish Image-Text Relation Task
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : In common sense, modality measures the number of areas a model covers. Multi-modal or cross-modal models can handle two or more areas simultaneously. Some common cross-models include Vision-Language models, Speech-Language models, and Vision-Speech models. READ MORE