# Breaking Down Word Semantics from Pre-trained Language Models through Layer-wise Dimension Selection

arXiv: https://arxiv.org/abs/2310.05115 · HTML: https://mlsanity.com/paper/2310.05115/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 8 Oct 2023.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [Analyzing the Structure of Attention in a Transformer Language Model](https://mlsanity.com/paper/1906.04284/) (2019)
- [Masking as an Efficient Alternative to Finetuning for Pretrained Language Models](https://mlsanity.com/paper/2004.12406/) (2020)
- [SenseBERT: Driving Some Sense into BERT](https://mlsanity.com/paper/1908.05646/) (2019)
- [Measuring Disentanglement: A Review of Metrics](https://mlsanity.com/paper/2012.09276/) (2020)
- [Theory and Evaluation Metrics for Learning Disentangled Representations](https://mlsanity.com/paper/1908.09961/) (2019)
- [A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations](https://mlsanity.com/paper/2105.02685/) (2021)
- [Disentangling Representations of Text by Masking Transformers](https://mlsanity.com/paper/2104.07155/) (2021)

## Abstract (arXiv)

Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and semantics, remains challenging. Disentangled representation learning has emerged as a promising approach, which separates specific aspects into distinct embeddings. Furthermore, different linguistic knowledge is believed to be stored in different layers of PLM. This paper aims to disentangle semantic sense from BERT by applying a binary mask to middle outputs across the layers, without updating pre-trained parameters. The disentangled embeddings are evaluated through binary classification to determine if the target word in two different sentences has the same meaning. Experiments with cased BERT_textttbase show that leveraging layer-wise information is effective and disentangling semantic sense further improve performance.