# Distilling Relation Embeddings from Pre-trained Language Models

arXiv: https://arxiv.org/abs/2110.15705 · HTML: https://mlsanity.com/paper/2110.15705/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 95 references that are in the map.
- First posted on arXiv 21 Sep 2021.

## Builds on (most cited first, 30 of 52)

- [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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [What do you learn from context? Probing for sentence structure in contextualized word representations](https://mlsanity.com/paper/1905.06316/) (2019)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [How Many Data Points is a Prompt Worth?](https://mlsanity.com/paper/2103.08493/) (2021)
- [Assessing BERT's Syntactic Abilities](https://mlsanity.com/paper/1901.05287/) (2019)
- [Commonsense Knowledge Mining from Pretrained Models](https://mlsanity.com/paper/1909.00505/) (2019)
- [oLMpics -- On what Language Model Pre-training Captures](https://mlsanity.com/paper/1912.13283/) (2019)
- [Probing Pretrained Language Models for Lexical Semantics](https://mlsanity.com/paper/2010.05731/) (2020)
- [Learning Dense Representations for Entity Retrieval](https://mlsanity.com/paper/1909.10506/) (2019)
- [Improving and Simplifying Pattern Exploiting Training](https://mlsanity.com/paper/2103.11955/) (2021)

## Built on by (most cited first, 15 of 15)

- [StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding](https://mlsanity.com/paper/2310.12874/) (2023)
- [Visual Grounding Helps Learn Word Meanings in Low-Data Regimes](https://mlsanity.com/paper/2310.13257/) (2023)
- [Do large language models solve verbal analogies like children do?](https://mlsanity.com/paper/2310.20384/) (2023)
- [Modelling Commonsense Properties using Pre-Trained Bi-Encoders](https://mlsanity.com/paper/2210.02771/) (2022)
- [Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance](https://mlsanity.com/paper/2310.05597/) (2023)
- [Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling](https://mlsanity.com/paper/2403.14551/) (2024)
- [Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation](https://mlsanity.com/paper/2208.10734/) (2022)
- [A RelEntLess Benchmark for Modelling Graded Relations between Named Entities](https://mlsanity.com/paper/2305.15002/) (2023)
- [RelBERT: Embedding Relations with Language Models](https://mlsanity.com/paper/2310.00299/) (2023)
- [Knowledge Authoring with Factual English, Rules, and Actions](https://mlsanity.com/paper/2411.06253/) (2024)
- [Open-ended Commonsense Reasoning with Unrestricted Answer Scope](https://mlsanity.com/paper/2310.11672/) (2023)
- [Solving Hard Analogy Questions with Relation Embedding Chains](https://mlsanity.com/paper/2310.12379/) (2023)
- [SememeLM: A Sememe Knowledge Enhanced Method for Long-tail Relation Representation](https://mlsanity.com/paper/2406.10297/) (2024)
- [Semantic Component Analysis: Introducing Multi-Topic Distributions to Clustering-Based Topic Modeling](https://mlsanity.com/paper/2410.21054/) (2024)
- [Inferring Adjective Hypernyms with Language Models to Increase the Connectivity of Open English Wordnet](https://mlsanity.com/paper/2506.10715/) (2025)

## Abstract (arXiv)

Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense properties of everyday concepts to detailed factual knowledge about named entities. Among others, this makes it possible to distill high-quality word vectors from pre-trained language models. However, it is currently unclear to what extent it is possible to distill relation embeddings, i.e. vectors that characterize the relationship between two words. Such relation embeddings are appealing because they can, in principle, encode relational knowledge in a more fine-grained way than is possible with knowledge graphs. To obtain relation embeddings from a pre-trained language model, we encode word pairs using a (manually or automatically generated) prompt, and we fine-tune the language model such that relationally similar word pairs yield similar output vectors. We find that the resulting relation embeddings are highly competitive on analogy (unsupervised) and relation classification (supervised) benchmarks, even without any task-specific fine-tuning. Source code to reproduce our experimental results and the model checkpoints are available in the following repository: https://github.com/asahi417/relbert