Papers › Aspect Detection using Word and Char Embeddings with (Bi)LSTM and CRF

Aspect Detection using Word and Char Embeddings with (Bi)LSTM and CRF

3 Sep 2019arXiv:1909.01276archive 2025-07-28

Łukasz Augustyniak, Tomasz Kajdanowicz, Przemysław Kazienko

We proposed a~new accurate aspect extraction method that makes use of both word and character-based embeddings. We have conducted experiments of various models of aspect extraction using LSTM and BiLSTM including CRF enhancement on five different pre-trained word embeddings extended with character embeddings. The results revealed that BiLSTM outperforms regular LSTM, but also word embedding coverage in train and test sets profoundly impacted aspect detection performance. Moreover, the additional CRF layer consistently improves the results across different models and text embeddings. Summing up, we obtained state-of-the-art F-score results for SemEval Restaurants (85%) and Laptops (80%).

PaperPDFCode

Code

laugustyniak/aspect_extraction officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Aspect ExtractionWord Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BiLSTMCRFLSTMSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections