A Simple Regularization-based Algorithm for Learning Cross-Domain Word Embeddings

Abstract

Learning word embeddings has received a significant amount of attention recently. Often, word embeddings are learned in an unsupervised manner from a large collection of text. The genre of the text typically plays an important role in the effectiveness of the resulting embeddings. How to effectively train word embedding models using data from different domains remains a problem that is underexplored. In this paper, we present a simple yet effective method for learning word embeddings based on text from different domains. We demonstrate the effectiveness of our approach through extensive experiments on various down-stream NLP tasks.

7 pages, accepted by EMNLP 2017

References in corpus (5)

• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Words and Phrases and their Compositionality
• Thumbs up? Sentiment Classification using Machine Learning Techniques
• Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition
• Neural CRF Parsing

Cited by in corpus (8)

• Semi-supervised representation learning via dual autoencoders for domain adaptation
• A Novel Bilingual Word Embedding Method for Lexical Translation Using Bilingual Sense Clique
• Text classification with word embedding regularization and soft similarity measure
• Neural Adaptation Layers for Cross-domain Named Entity Recognition
• Benchmark Performance of Machine And Deep Learning Based Methodologies for Urdu Text Document Classification
• Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification
• Data Annealing for Informal Language Understanding Tasks
• Learning Word Embeddings with Domain Awareness