[TOC]

  1. Title: Compositionality as Lexical Symmetry
  2. Author: Ekin Akyurek; Jacob Andreas
  3. Publish Year: Jan 2022
  4. Review Date: Feb 2022

Summary of paper

Motivation

Standard deep network models lack the inductive bias needed to generalize compositionally in tasks like semantic parsing, translation, and question answering.

So, a large body of work in NLP seeks to overcome this limitation with new model architectures that enforce a compositional process of sentence interpretation.

Goal

the question of this paper aims to answer is whether compositionality like other domain-specific constraints, can be formalized in the language of symmetry.

Language symmetry

they characterise the relationship between compositionality and symmetry for general problem domains.

there comes a statement

Homomorphism of symbol

image-20220208162321033

Proposition

if X is L-compositional, f is an L-homomorphism and x $\in$ X, then f(x) will also $\in$ X, Thus, based on the definition of symmetry, every homomorphism of L corresponds to a symmetry of X

image-20220208162945730

Alignment of text data and other-modal data pairs

image-20220208163928037

Some key terms

parameter typing schemes

TYPE is a high level module type (attention, classification, etc.)

image-20220208151138906

Symmetry property

image-20220208155645877

Lexicon

image-20220208161218638

Lexicon abstraction

image-20220208161626783

image-20220208161739648

Good things about the paper (one paragraph)

The author noticed that adding constraints on deep learning model architecture in order to operationalize the principle of compositionality is not effective compared to vanilla transformers.

So, the author tried to implement a data-centric view of the principle of compositionality, which means that we focus on the “transformation of a structural regularity of the lexicon” of training data so that we can capture the principle of compositionality.

Major comments

Essentially, this work gives a theoretical support for the use of data augmentation to improve generalisation performance of models.