Challenge: Past work on sentence embedding models faces issues determining the causal impact of implicit syntax representations.
Approach: They construct a neural module net based on a transformer model and train it end-to-end to approximate the sentence’s embedding.
Outcome: The proposed model captures whether syntax is a strong model of its compositional ability.

Similar Papers

Quantifying Compositionality of Classic and State-of-the-Art Embeddings (2025.findings-emnlp)

Copied to clipboard

Challenge: Static word embeddings make strong claims about compositionality, but the SOTA generative models go too far in the other direction.
Approach: a new study evaluates the compositionality of word embeddings by canonical correlation analysis . strong compositional signals are observed in later training stages across data modalities .
Outcome: a new evaluation of compositional models shows that they exploit access meanings when justified . strong compositional signals are observed in later training stages and in deeper layers of the transformer-based model before a decline at the top layer.
Assessing Composition in Sentence Vector Representations (C18-1)

Copied to clipboard

Challenge: opacity of sentence vector representations is a challenge to achieving language understanding . current neural network models are unable to capture meaning information in dense vectors .
Approach: They propose a method that targets compositional meaning information in sentence embeddings with a high degree of precision and control.
Outcome: The proposed method extracts useful information about the different capacities of existing sentences models.
How do Transformer Embeddings Represent Compositions? A Functional Analysis (2025.findings-acl)

Copied to clipboard

Challenge: Despite the popularity of transformer-based models, little is known about how they represent compound words and whether they are compositional.
Approach: They evaluate compositionality in mistral, OpenAI Large, and Google embedding models and compare them with BERT.
Outcome: The proposed models perform best in addition, multiplication, dilation, regression, and the classic vector addition model performs almost as well as any other model.
LexSym: Compositionality as Lexical Symmetry (2023.acl-long)

Copied to clipboard

Challenge: Existing approaches to generalize compositional models fail to generalise from small datasets.
Approach: They propose a domain-general and model-agnostic formulation of compositionality as a constraint on symmetries of data distributions rather than models.
Outcome: The proposed procedure matches or surpasses state-of-the-art, task-specific models on COGS semantic parsing, SCAN and Alchemy instruction following, and CLEVR-CoGenT visual question answering datasets.
The Paradox of the Compositionality of Natural Language: A Neural Machine Translation Case Study (2022.acl-long)

Copied to clipboard

Challenge: Obtaining human-like performance in NLP is often argued to require compositional generalisation.
Approach: They re-instantiate three compositionality tests from the literature and reformulate them for neural machine translation.
Outcome: The proposed models are more compositional than models trained on more data, the authors show . they also show that some non-compositional behaviours are mistakes, whereas others reflect natural variation in data.
Multi-Step Inference for Reasoning Over Paragraphs (2020.emnlp-main)

Copied to clipboard

Challenge: Existing models for complex reasoning use symbols or black-box transformers . a compositional model can chain together free-form predicates and logical connectives .
Approach: They propose a compositional model that finds relevant sentences and then chains them together using neural modules.
Outcome: The proposed model improves performance on a recently-introduced dataset.
Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to learn sentence embeddings do not capture the semantic similarity of sentences.
Approach: They propose a framework that integrates compositional sentence operations into the embedding space and optimizes operator networks and a bottleneck encoder-decoder model to produce meaningful and interpretable sentence embeddables.
Outcome: The proposed framework improves the interpretability of sentence embeddings on four textual generation tasks while maintaining strong performance on traditional semantic similarity tasks.
Montague semantics and modifier consistency measurement in neural language models (2025.coling-main)

Copied to clipboard

Challenge: Existing studies on distributional language models have been focused on linguistics and their relationship with semantic formalisms for decades.
Approach: They propose a method for measuring compositional behavior in contemporary language embedding models by introducing three new tests inspired by Montague semantics.
Outcome: The proposed method measures compositional behavior in language embedding models on adjectival modifier phenomena in adjective-noun phrases.
Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in mechanistic interpretability have made progress in identifying circuits, the minimal computational subgraphs responsible for a model’s behavior on specific tasks.
Approach: They propose to analyze circuits for highly compositional subtasks within a transformer-based language model to determine their modularity and how they relate to each other.
Outcome: The proposed approach shows that the circuits identified exhibit notable node overlap and cross-task faithfulness.
Measuring Idiomaticity in Text Embedding Models with epsilon-compositionality (2026.eacl-long)

Copied to clipboard

Challenge: Existing studies on compositionality of text embedding models have limited understanding of the principle . idioms have traditionally been seen as non-compositional .
Approach: They propose to use formal definitions to define compositionality in text embedding models . they find that most models differentiate between idiomatic and non-idiomatic phrases .
Outcome: The proposed model is able to differentiate between idiomatic and non-idiomatic phrases, the authors show .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations