# Extracting Text Representations for Terms and Phrases in Technical Domains

arXiv: https://arxiv.org/abs/2305.15867 · HTML: https://mlsanity.com/paper/2305.15867/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 30 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Multilingual Universal Sentence Encoder for Semantic Retrieval](https://mlsanity.com/paper/1907.04307/) (2019)
- [TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning](https://mlsanity.com/paper/2104.06979/) (2021)
- [On the Use of ArXiv as a Dataset](https://mlsanity.com/paper/1905.00075/) (2019)
- [Unsupervised Alignment of Embeddings with Wasserstein Procrustes](https://mlsanity.com/paper/1805.11222/) (2018)
- [Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion](https://mlsanity.com/paper/1804.07745/) (2018)
- [Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing](https://mlsanity.com/paper/1902.09492/) (2019)
- [Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems](https://mlsanity.com/paper/1909.02107/) (2019)
- [Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems](https://mlsanity.com/paper/2007.14523/) (2020)
- [The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications](https://mlsanity.com/paper/2207.04043/) (2022)
- [Learning Compressed Embeddings for On-Device Inference](https://mlsanity.com/paper/2203.10135/) (2022)
- [Embedding Compression with Isotropic Iterative Quantization](https://mlsanity.com/paper/2001.05314/) (2020)
- [Patents Phrase to Phrase Semantic Matching Dataset](https://mlsanity.com/paper/2208.01171/) (2022)
- [Unsupervised Term Extraction for Highly Technical Domains](https://mlsanity.com/paper/2210.13118/) (2022)

## Abstract (arXiv)

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple applications ranging from ranking results in search to summarization. Common approaches to create dense representations include training domain-specific embeddings with self-supervised setups or using sentence encoder models trained over similarity tasks. In contrast to static embeddings, sentence encoders do not suffer from the out-of-vocabulary (OOV) problem, but impose significant computational costs. In this paper, we propose a fully unsupervised approach to text encoding that consists of training small character-based models with the objective of reconstructing large pre-trained embedding matrices. Models trained with this approach can not only match the quality of sentence encoders in technical domains, but are 5 times smaller and up to 10 times faster, even on high-end GPUs.