Input Combination Strategies for Multi-Source Transformer Decoder
In multi-source sequence-to-sequence tasks, the attention mechanism can be modeled in several ways. This topic has been thoroughly studied on recurrent architectures. In this paper, we extend the previous work to the encoder-decoder attention in the Transformer architecture. We propose four different input combination strategies for the encoder-decoder attention: serial, parallel, flat, and hierarchical. We evaluate our methods on tasks of multimodal translation and translation with multiple source languages. The experiments show that the models are able to use multiple sources and improve over single source baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Input Combination Strategies for Multi-Source Transformer Decoder
In multi-source sequence-to-sequence tasks, the attention mechanism can be modeled in several ways. This topic has been thoroughly studied on recurrent architectures. In this paper, we extend the previous work to the enc…
DecoderImage CaptioningMachine TranslationMultimodal Machine Translation+2MVP: Multi-source Voice Pathology detection
Voice disorders significantly impact patient quality of life, yet non-invasive automated diagnosis remains under-explored due to both the scarcity of pathological voice data, and the variability in recording sources. Thi…
SentenceVoice pathology detectionFine-tuning Transformers with Additional Context to Classify Discursive Moves in Mathematics Classrooms
“Talk moves” are specific discursive strategies used by teachers and students to facilitate conversations in which students share their thinking, and actively consider the ideas of others, and engage in rich discussions.…
Data Augmentation for Transformer-based G2P
The Transformer model has been shown to outperform other neural seq2seq models in several character-level tasks. It is unclear, however, if the Transformer would benefit as much as other seq2seq models from data augmenta…
Data AugmentationAutomatic Discovery of Composite SPMD Partitioning Strategies in PartIR
Large neural network models are commonly trained through a combination of advanced parallelism strategies in a single program, multiple data (SPMD) paradigm. For example, training large transformer models requires combin…