REVIEW 1 cited by
Domain Adapted Word Embeddings for Improved Sentiment Classification
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Domain Adapted Word Embeddings for Improved Sentiment Classification
read the original abstract
Generic word embeddings are trained on large-scale generic corpora; Domain Specific (DS) word embeddings are trained only on data from a domain of interest. This paper proposes a method to combine the breadth of generic embeddings with the specificity of domain specific embeddings. The resulting embeddings, called Domain Adapted (DA) word embeddings, are formed by aligning corresponding word vectors using Canonical Correlation Analysis (CCA) or the related nonlinear Kernel CCA. Evaluation results on sentiment classification tasks show that the DA embeddings substantially outperform both generic and DS embeddings when used as input features to standard or state-of-the-art sentence encoding algorithms for classification.
Forward citations
Cited by 1 Pith paper
-
Deep Label-Wise Attentive Temporal Convolutional Networks Improve Medical Coding
LATCN (multi-layer TCN + label-wise attention) improves F1 ~9% and recall ~28% over DR-CAML on the top-50 MIMIC-III ICD coding task.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.