# Online Segment to Segment Neural Transduction

arXiv: https://arxiv.org/abs/1609.08194 · HTML: https://mlsanity.com/paper/1609.08194/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2016.

## Built on by (most cited first, 14 of 14)

- [Sequence-to-Sequence Learning with Latent Neural Grammars](https://mlsanity.com/paper/2109.01135/) (2021)
- [Structured Reordering for Modeling Latent Alignments in Sequence Transduction](https://mlsanity.com/paper/2106.03257/) (2021)
- [Inducing and Using Alignments for Transition-based AMR Parsing](https://mlsanity.com/paper/2205.01464/) (2022)
- [Neural HMMs are all you need (for high-quality attention-free TTS)](https://mlsanity.com/paper/2108.13320/) (2021)
- [OverFlow: Putting flows on top of neural transducers for better TTS](https://mlsanity.com/paper/2211.06892/) (2022)
- [Subword Segmental Machine Translation: Unifying Segmentation and Target Sentence Generation](https://mlsanity.com/paper/2305.07005/) (2023)
- [Review of end-to-end speech synthesis technology based on deep learning](https://mlsanity.com/paper/2104.09995/) (2021)
- [Compositional Generalisation with Structured Reordering and Fertility Layers](https://mlsanity.com/paper/2210.03183/) (2022)
- [A study of latent monotonic attention variants](https://mlsanity.com/paper/2103.16710/) (2021)
- [Monotonic segmental attention for automatic speech recognition](https://mlsanity.com/paper/2210.14742/) (2022)
- [Computational Morphology with Neural Network Approaches](https://mlsanity.com/paper/2105.09404/) (2021)
- [Foundations of Multisensory Artificial Intelligence](https://mlsanity.com/paper/2404.18976/) (2024)
- [Neural String Edit Distance](https://mlsanity.com/paper/2104.08388/) (2021)
- [Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming](https://mlsanity.com/paper/2306.02568/) (2023)

## Abstract (arXiv)

We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits exact polynomial marginalization of the latent segmentation during training, and during decoding beam search is employed to find the best alignment path together with the predicted output sequence. Our model tackles the bottleneck of vanilla encoder-decoders that have to read and memorize the entire input sequence in their fixed-length hidden states before producing any output. It is different from previous attentive models in that, instead of treating the attention weights as output of a deterministic function, our model assigns attention weights to a sequential latent variable which can be marginalized out and permits online generation. Experiments on abstractive sentence summarization and morphological inflection show significant performance gains over the baseline encoder-decoders.