Shallow Domain Adaptive Embeddings for Sentiment Analysis

This paper proposes a way to improve the performance of existing algorithms for text classification in domains with strong language semantics. We propose a domain adaptation layer learns weights to combine a generic and a domain specific (DS) word embedding into a domain adapted (DA) embedding. The DA word embeddings are then used as inputs to a generic encoder + classifier framework to perform a downstream task such as classification. This adaptation layer is particularly suited to datasets that are modest in size, and which are, therefore, not ideal candidates for (re)training a deep neural network architecture. Results on binary and multi-class classification tasks using popular encoder architectures, including current state-of-the-art methods (with and without the shallow adaptation layer) show the effectiveness of the proposed approach.

[1]  Yang Liu,et al.  Multi-Domain Neural Machine Translation with Word-Level Domain Context Discrimination , 2018, EMNLP.

[2]  Yue Zhang,et al.  Learning Domain Representation for Multi-Domain Sentiment Classification , 2018, NAACL.

[3]  Hwee Tou Ng,et al.  Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification , 2018, EMNLP.

[4]  Teng Ren,et al.  Learning Named Entity Tagger using Domain-Specific Dictionary , 2018, EMNLP.

[5]  Jisun An,et al.  SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment , 2018, ACL.

[6]  Jure Leskovec,et al.  Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora , 2016, EMNLP.

[7]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[8]  Ping Li,et al.  Speaking two “Languages” in America: A semantic space analysis of how presidential candidates and their supporters represent abstract political concepts differently , 2017, Behavior research methods.

[9]  William A. Sethares,et al.  Domain Adapted Word Embeddings for Improved Sentiment Classification , 2018, ACL.

[10]  Xuanjing Huang,et al.  Recurrent Neural Network for Text Classification with Multi-Task Learning , 2016, IJCAI.

[11]  Quoc V. Le,et al.  Exploiting Similarities among Languages for Machine Translation , 2013, ArXiv.

[12]  Fabienne Braune,et al.  Two Methods for Domain Adaptation of Bilingual Tasks: Delightfully Simple and Broadly Applicable , 2018, ACL.

[13]  Bo Pang,et al.  Seeing Stars: Exploiting Class Relationships for Sentiment Categorization with Respect to Rating Scales , 2005, ACL.

[14]  Bowen Zhou,et al.  A Structured Self-attentive Sentence Embedding , 2017, ICLR.

[15]  Xiaoyan Zhu,et al.  Linguistically Regularized LSTM for Sentiment Classification , 2016, ACL.

[16]  T. Landauer,et al.  Indexing by Latent Semantic Analysis , 1990 .

[17]  Holger Schwenk,et al.  Supervised Learning of Universal Sentence Representations from Natural Language Inference Data , 2017, EMNLP.

[18]  Anton van den Hengel,et al.  Image-Based Recommendations on Styles and Substitutes , 2015, SIGIR.

[19]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[20]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[21]  Bohyung Han,et al.  Learning Multi-domain Convolutional Neural Networks for Visual Tracking , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[23]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.