Recursive Decoding: A Situated Cognition Approach to Compositional
Generation in Grounded Language Understanding
- URL: http://arxiv.org/abs/2201.11766v1
- Date: Thu, 27 Jan 2022 19:13:42 GMT
- Title: Recursive Decoding: A Situated Cognition Approach to Compositional
Generation in Grounded Language Understanding
- Authors: Matthew Setzler, Scott Howland, Lauren Phillips
- Abstract summary: We present Recursive Decoding, a novel procedure for training and using seq2seq models.
Rather than generating an entire output sequence in one pass, models are trained to predict one token at a time.
RD yields dramatic improvement on two previously neglected generalization tasks in gSCAN.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Compositional generalization is a troubling blind spot for neural language
models. Recent efforts have presented techniques for improving a model's
ability to encode novel combinations of known inputs, but less work has focused
on generating novel combinations of known outputs. Here we focus on this latter
"decode-side" form of generalization in the context of gSCAN, a synthetic
benchmark for compositional generalization in grounded language understanding.
We present Recursive Decoding (RD), a novel procedure for training and using
seq2seq models, targeted towards decode-side generalization. Rather than
generating an entire output sequence in one pass, models are trained to predict
one token at a time. Inputs (i.e., the external gSCAN environment) are then
incrementally updated based on predicted tokens, and re-encoded for the next
decoder time step. RD thus decomposes a complex, out-of-distribution sequence
generation task into a series of incremental predictions that each resemble
what the model has already seen during training. RD yields dramatic improvement
on two previously neglected generalization tasks in gSCAN. We provide analyses
to elucidate these gains over failure of a baseline, and then discuss
implications for generalization in naturalistic grounded language
understanding, and seq2seq more generally.
Related papers
- ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis [54.18659323181771]
We characterize several different forms of compositional generalization that are desirable in program synthesis.
We propose ExeDec, a novel decomposition-based strategy that predicts execution subgoals to solve problems step-by-step informed by program execution at each step.
arXiv Detail & Related papers (2023-07-26T01:07:52Z) - Real-World Compositional Generalization with Disentangled
Sequence-to-Sequence Learning [81.24269148865555]
A recently proposed Disentangled sequence-to-sequence model (Dangle) shows promising generalization capability.
We introduce two key modifications to this model which encourage more disentangled representations and improve its compute and memory efficiency.
Specifically, instead of adaptively re-encoding source keys and values at each time step, we disentangle their representations and only re-encode keys periodically.
arXiv Detail & Related papers (2022-12-12T15:40:30Z) - Hierarchical Sketch Induction for Paraphrase Generation [79.87892048285819]
We introduce Hierarchical Refinement Quantized Variational Autoencoders (HRQ-VAE), a method for learning decompositions of dense encodings.
We use HRQ-VAE to encode the syntactic form of an input sentence as a path through the hierarchy, allowing us to more easily predict syntactic sketches at test time.
arXiv Detail & Related papers (2022-03-07T15:28:36Z) - Grounded Graph Decoding Improves Compositional Generalization in
Question Answering [68.72605660152101]
Question answering models struggle to generalize to novel compositions of training patterns, such as longer sequences or more complex test structures.
We propose Grounded Graph Decoding, a method to improve compositional generalization of language representations by grounding structured predictions with an attention mechanism.
Our model significantly outperforms state-of-the-art baselines on the Compositional Freebase Questions (CFQ) dataset, a challenging benchmark for compositional generalization in question answering.
arXiv Detail & Related papers (2021-11-05T17:50:14Z) - Disentangled Sequence to Sequence Learning for Compositional
Generalization [62.954842223732435]
We propose an extension to sequence-to-sequence models which allows us to learn disentangled representations by adaptively re-encoding the source input.
Experimental results on semantic parsing and machine translation empirically show that our proposal yields more disentangled representations and better generalization.
arXiv Detail & Related papers (2021-10-09T22:27:19Z) - Inducing Transformer's Compositional Generalization Ability via
Auxiliary Sequence Prediction Tasks [86.10875837475783]
Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions.
Existing neural models have been shown to lack this basic ability in learning symbolic structures.
We propose two auxiliary sequence prediction tasks that track the progress of function and argument semantics.
arXiv Detail & Related papers (2021-09-30T16:41:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.