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 6 of 6 for “"Constrained Decoding"”.
-
Unreliable and resource-constrained decoding
… Decoders are also traditionally assumed to be unconstrained in physical resources like material, memory, and energy. This thesis studies how constraining reliability and resources in the decoder limits the performance of communication systems. Five communication problems are investigated. Broadly …
-
Provably reliable machine learning systems
… incremental verification techniques for DNNs and constrained decoding methods specific to LLMs.
-
LLM-Supported Natural Language to Bash Translation
… in-context learning, in-weight learning, and constrained decoding can improve NL2SH accuracy by up to 32%. Additionally, we consider military use cases for NL2SH models and discuss the limitations of current Department of Defense documentation standards for LLMs. We write and publish …
-
A hitchhiker’s guide to efficient non-projective dependency parsing
… dependency parsers: inference, sampling, decoding, and significance testing. The thesis will guide the reader through a series of novel extensions to existing algorithms, as well as the original develop- ment of new algorithms concerning these four processes in the dependency parsing …
-
Speech Foundation Models for Audio Processing
… the generation process, we introduce various constrained decoding strategies based on either the N-best list or an ASR lattice, enabling the error correction model to better utilise knowledge from the ASR system. Beyond supervised ASR error correction, we also investigate a training-free, …
-
Natural Language Processing per Human-centered AI
Nonostante i recenti progressi che hanno permesso ai sistemi di Intelligenza Artificiale (AI) di raggiungere prestazioni comparabili a quelle umane su benchmark consolidati, le tecnologie allo stato dell’arte mostrano ancora un calo di performance quando vengono applicate a compiti altamente …