# How to Encode Domain Information in Relation Classification

arXiv: https://arxiv.org/abs/2404.13760 · HTML: https://mlsanity.com/paper/2404.13760/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 21 Apr 2024.

## Builds on (most cited first, 11 of 11)

- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [CrossNER: Evaluating Cross-Domain Named Entity Recognition](https://mlsanity.com/paper/2012.04373/) (2020)
- [Many Languages, One Parser](https://mlsanity.com/paper/1602.01595/) (2016)
- [CrossRE: A Cross-Domain Dataset for Relation Extraction](https://mlsanity.com/paper/2210.09345/) (2022)
- [82 Treebanks, 34 Models: Universal Dependency Parsing with Multi-Treebank Models](https://mlsanity.com/paper/1809.02237/) (2018)
- [Parser Training with Heterogeneous Treebanks](https://mlsanity.com/paper/1805.05089/) (2018)
- [On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions](https://mlsanity.com/paper/2103.01273/) (2021)
- [Treebank Embedding Vectors for Out-of-domain Dependency Parsing](https://mlsanity.com/paper/2005.00800/) (2020)
- [Parsing with Pretrained Language Models, Multiple Datasets, and Dataset Embeddings](https://mlsanity.com/paper/2112.03625/) (2021)

## Abstract (arXiv)

Current language models require a lot of training data to obtain high performance. For Relation Classification (RC), many datasets are domain-specific, so combining datasets to obtain better performance is non-trivial. We explore a multi-domain training setup for RC, and attempt to improve performance by encoding domain information. Our proposed models improve > 2 Macro-F1 against the baseline setup, and our analysis reveals that not all the labels benefit the same: The classes which occupy a similar space across domains (i.e., their interpretation is close across them, for example "physical") benefit the least, while domain-dependent relations (e.g., "part-of'') improve the most when encoding domain information.