Joint Decoding
Related Papers
Composition of Conditional Random Fields for Transfer Learning
Many learning tasks have subtasks for which much training data exists. Therefore, we want to transfer learning from the old, general- purpose subtask to a more specific new task, for …...
Joint Word Alignment and Bilingual Named Entity Recognition Using Dual Decomposition
Translated bi-texts contain complemen- tary language cues, and previous work on Named Entity Recognition (NER) has demonstrated improvements in perfor- mance over monolingual taggers by pro- moting agreement of tagging …...
Joint CTC/attention decoding for end-to-end speech recognition
AbstractEnd-to-end automatic speech recognition (ASR) has become a popular alternative to conventional DNN/HMM systems because it avoids the need for linguistic resources such as pronunciation dictionary, tokenization, and context-dependency trees, …...
The Covert Helps Parse the Overt
AbstractThis paper is concerned with whether deep syntactic information can help surface parsing, with a particular focus on empty categories. We design new algorithms to produce dependency trees in which …...
Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches
AbstractAn interesting and frequent type of multi-word expression (MWE) is the headless MWE, for which there are no true internal syntactic dominance relations; examples include many named entities (“Wells Fargo”) …...
Between Flexibility and Consistency: Joint Generation of Captions and Subtitles
AbstractSpeech translation (ST) has lately received growing interest for the generation of subtitles without the need for an intermediate source language transcription and timing (i.e. captions). However, the joint generation …...
CMU’s IWSLT 2022 Dialect Speech Translation System
AbstractThis paper describes CMU’s submissions to the IWSLT 2022 dialect speech translation (ST) shared task for translating Tunisian-Arabic speech to English text. We use additional paired Modern Standard Arabic data …...