Computer Science > Computation and Language
[Submitted on 2 Sep 2021 (v1), last revised 16 Nov 2021 (this version, v7)]
Title:Sequence-to-Sequence Learning with Latent Neural Grammars
View PDFAbstract:Sequence-to-sequence learning with neural networks has become the de facto standard for sequence prediction tasks. This approach typically models the local distribution over the next word with a powerful neural network that can condition on arbitrary context. While flexible and performant, these models often require large datasets for training and can fail spectacularly on benchmarks designed to test for compositional generalization. This work explores an alternative, hierarchical approach to sequence-to-sequence learning with quasi-synchronous grammars, where each node in the target tree is transduced by a node in the source tree. Both the source and target trees are treated as latent and induced during training. We develop a neural parameterization of the grammar which enables parameter sharing over the combinatorial space of derivation rules without the need for manual feature engineering. We apply this latent neural grammar to various domains -- a diagnostic language navigation task designed to test for compositional generalization (SCAN), style transfer, and small-scale machine translation -- and find that it performs respectably compared to standard baselines.
Submission history
From: Yoon Kim [view email][v1] Thu, 2 Sep 2021 17:58:08 UTC (57 KB)
[v2] Mon, 11 Oct 2021 16:08:40 UTC (57 KB)
[v3] Sun, 17 Oct 2021 15:04:31 UTC (57 KB)
[v4] Mon, 1 Nov 2021 00:49:10 UTC (57 KB)
[v5] Tue, 2 Nov 2021 04:06:31 UTC (57 KB)
[v6] Fri, 12 Nov 2021 20:38:51 UTC (57 KB)
[v7] Tue, 16 Nov 2021 17:14:16 UTC (57 KB)
References & Citations
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.