# Unsupervised Attention-based Sentence-Level Meta-Embeddings from Contextualised Language Models

arXiv: https://arxiv.org/abs/2204.07746 · HTML: https://mlsanity.com/paper/2204.07746/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 16 Apr 2022.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [SentEval: An Evaluation Toolkit for Universal Sentence Representations](https://mlsanity.com/paper/1803.05449/) (2018)
- [Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings](https://mlsanity.com/paper/1804.05262/) (2018)
- [Dynamic Meta-Embeddings for Improved Sentence Representations](https://mlsanity.com/paper/1804.07983/) (2018)
- [Think Globally, Embed Locally --- Locally Linear Meta-embedding of Words](https://mlsanity.com/paper/1709.06671/) (2017)
- [Sentence Meta-Embeddings for Unsupervised Semantic Textual Similarity](https://mlsanity.com/paper/1911.03700/) (2019)
- [Learning Geometric Word Meta-Embeddings](https://mlsanity.com/paper/2004.09219/) (2020)
- [Learning Efficient Task-Specific Meta-Embeddings with Word Prisms](https://mlsanity.com/paper/2011.02944/) (2020)
- [Angular-Based Word Meta-Embedding Learning](https://mlsanity.com/paper/1808.04334/) (2018)

## Built on by (most cited first, 4 of 4)

- [TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2304.07547/) (2023)
- [A Survey on Word Meta-Embedding Learning](https://mlsanity.com/paper/2204.11660/) (2022)
- [Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings](https://mlsanity.com/paper/2204.12386/) (2022)
- [Together We Make Sense -- Learning Meta-Sense Embeddings from Pretrained Static Sense Embeddings](https://mlsanity.com/paper/2305.19092/) (2023)

## Abstract (arXiv)

A variety of contextualised language models have been proposed in the NLP community, which are trained on diverse corpora to produce numerous Neural Language Models (NLMs). However, different NLMs have reported different levels of performances in downstream NLP applications when used as text representations. We propose a sentence-level meta-embedding learning method that takes independently trained contextualised word embedding models and learns a sentence embedding that preserves the complementary strengths of the input source NLMs. Our proposed method is unsupervised and is not tied to a particular downstream task, which makes the learnt meta-embeddings in principle applicable to different tasks that require sentence representations. Specifically, we first project the token-level embeddings obtained by the individual NLMs and learn attention weights that indicate the contributions of source embeddings towards their token-level meta-embeddings. Next, we apply mean and max pooling to produce sentence-level meta-embeddings from token-level meta-embeddings. Experimental results on semantic textual similarity benchmarks show that our proposed unsupervised sentence-level meta-embedding method outperforms previously proposed sentence-level meta-embedding methods as well as a supervised baseline.