# Adaptive Joint Learning of Compositional and Non-Compositional Phrase Embeddings

arXiv: https://arxiv.org/abs/1603.06067 · HTML: https://mlsanity.com/paper/1603.06067/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2016.

## Built on by (most cited first, 9 of 9)

- [AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Models](https://mlsanity.com/paper/2109.04413/) (2021)
- [Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models](https://mlsanity.com/paper/2308.13961/) (2023)
- [Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss](https://mlsanity.com/paper/2406.15175/) (2024)
- [Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings](https://mlsanity.com/paper/2204.12386/) (2022)
- [Getting BART to Ride the Idiomatic Train: Learning to Represent Idiomatic Expressions](https://mlsanity.com/paper/2207.03679/) (2022)
- [Unified Representation for Non-compositional and Compositional Expressions](https://mlsanity.com/paper/2310.19127/) (2023)
- [JARVix at SemEval-2022 Task 2: It Takes One to Know One? Idiomaticity Detection using Zero and One-Shot Learning](https://mlsanity.com/paper/2202.02394/) (2022)
- [Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic Languages](https://mlsanity.com/paper/2505.21937/) (2025)
- [Gyan: An Explainable Neuro-Symbolic Language Model](https://mlsanity.com/paper/2605.04759/) (2026)

## Abstract (arXiv)

We present a novel method for jointly learning compositional and non-compositional phrase embeddings by adaptively weighting both types of embeddings using a compositionality scoring function. The scoring function is used to quantify the level of compositionality of each phrase, and the parameters of the function are jointly optimized with the objective for learning phrase embeddings. In experiments, we apply the adaptive joint learning method to the task of learning embeddings of transitive verb phrases, and show that the compositionality scores have strong correlation with human ratings for verb-object compositionality, substantially outperforming the previous state of the art. Moreover, our embeddings improve upon the previous best model on a transitive verb disambiguation task. We also show that a simple ensemble technique further improves the results for both tasks.