Improving Sequence-to-Sequence Learning via Optimal Transport
Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE). However, standard MLE training considers a word-level objective, predicting the next word given the previous ground-truth partial sentence. This procedure focuses on modeling local syntactic patterns, and may fail to capture long-range semantic structure. We present a novel solution to alleviate these issues. Our approach imposes global sequence-level guidance via new supervision based on optimal transport, enabling the overall characterization and preservation of semantic features. We further show that this method can be understood as a Wasserstein gradient flow trying to match our model to the ground truth sequence distribution. Extensive experiments are conducted to validate the utility of the proposed approach, showing consistent improvements over a wide variety of NLP tasks, including machine translation, abstractive text summarization, and image captioning.
Code (0)
등록된 구현이 없습니다.
Tasks
Abstractive Text SummarizationImage CaptioningMachine TranslationSentenceText SummarizationTranslationSimilar Papers 제목 키워드 기반
Order-Preserving Wasserstein Distance for Sequence Matching
We present a new distance measure between sequences that can tackle local temporal distortion and periodic sequences with arbitrary starting points. Through viewing the instances of sequences as empirical samples of an u…
A Differentiable Alignment Framework for Sequence-to-Sequence Modeling via Optimal Transport
Accurate sequence-to-sequence (seq2seq) alignment is critical for applications like medical speech analysis and language learning tools relying on automatic speech recognition (ASR). State-of-the-art end-to-end (E2E) ASR…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSemantic Matching for Sequence-to-Sequence Learning
In sequence-to-sequence models, classical optimal transport (OT) can be applied to semantically match generated sentences with target sentences. However, in non-parallel settings, target sentences are usually unavailable…
GaitMorph: Transforming Gait by Optimally Transporting Discrete Codes
Gait, the manner of walking, has been proven to be a reliable biometric with uses in surveillance, marketing and security. A promising new direction for the field is training gait recognition systems without explicit hum…
Data AugmentationGait RecognitionMarketingMORPH+1Generating Temporally-ordered Event Sequences via Event Optimal Transport
Generating temporally-ordered event sequences in texts is important to natural language processing. Two emerging tasks in this direction are temporal event ordering (rearranging the set of events to correct order) and ev…