Attention Strategies for Multi-Source Sequence-to-Sequence Learning
Modeling attention in neural multi-source sequence-to-sequence learning remains a relatively unexplored area, despite its usefulness in tasks that incorporate multiple source languages or modalities. We propose two novel approaches to combine the outputs of attention mechanisms over each source sequence, flat and hierarchical. We compare the proposed methods with existing techniques and present results of systematic evaluation of those methods on the WMT16 Multimodal Translation and Automatic Post-editing tasks. We show that the proposed methods achieve competitive results on both tasks.
Code (1)
Tasks
Automatic Post-EditingTranslationSimilar Papers 제목 키워드 기반
Attention Strategies for Multi-Source Sequence-to-Sequence Learning
Modeling attention in neural multi-source sequence-to-sequence learning remains a relatively unexplored area, despite its usefulness in tasks that incorporate multiple source languages or modalities. We propose two novel…
Automatic Post-EditingImage CaptioningMachine TranslationText Summarization+1Input 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…
DecoderTranslationInput 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+2Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling
Multi-head attention has each of the attention heads collect salient information from different parts of an input sequence, making it a powerful mechanism for sequence modeling. Multilingual and multi-domain learning are…
speech-recognitionSpeech RecognitionSpeech-to-TextSpeech-to-Text Translation+1Analysis of Multilingual Sequence-to-Sequence speech recognition systems
This paper investigates the applications of various multilingual approaches developed in conventional hidden Markov model (HMM) systems to sequence-to-sequence (seq2seq) automatic speech recognition (ASR). On a set compo…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Sequence-To-Sequence Speech Recognitionspeech-recognition+2