Language Independent Sequence Labelling for Opinion Target Extraction
This work addresses the problem of extracting opinion targets in multiple languages for sentiment analysis, though it appears incremental as it builds on existing methods.
The authors tackled Opinion Target Extraction by developing a language-independent sequence labeling system using clustering features on shallow local features, achieving best results for six languages across seven datasets.
In this research note we present a language independent system to model Opinion Target Extraction (OTE) as a sequence labelling task. The system consists of a combination of clustering features implemented on top of a simple set of shallow local features. Experiments on the well known Aspect Based Sentiment Analysis (ABSA) benchmarks show that our approach is very competitive across languages, obtaining best results for six languages in seven different datasets. Furthermore, the results provide further insights into the behaviour of clustering features for sequence labelling tasks. The system and models generated in this work are available for public use and to facilitate reproducibility of results.