The binary form BOWs are encoded so that the information on the aspect and context words are nearly lossless for sentiment classification. We attain interpretability by converting the intricate position-dependent textual semantics into binary form, mapping all the features into bag-of-words (BOWs). This paper proposes human-interpretable learning of aspect-based sentiment analysis (ABSA), employing the recently introduced Tsetlin Machines (TMs). Being able to share clauses, we believe CoTM will enable new TM application domains that involve multiple outputs, such as learning language models and auto-encoding. Our evaluations on imbalanced versions of IMDb- and CIFAR10 data show that CoTM is robust towards high degrees of class imbalance. We further investigate robustness towards imbalanced training data. While TM and CoTM accuracy is similar when using more than 1K clauses per class, CoTM reaches peak accuracy 3x faster on MNIST with 8K clauses. E.g., accuracy goes from 71.99% to 89.66% on Fashion-MNIST when employing 50 clauses per class (22 Kb memory). Our empirical results on MNIST, Fashion-MNIST, and Kuzushiji-MNIST show that CoTM obtains significantly higher accuracy than TM on 50- to 1K-clause configurations, indicating an ability to repurpose clauses. The resulting coalesced Tsetlin Machine (CoTM) simultaneously learns both the weights and the composition of each clause by employing interacting Stochastic Searching on the Line (SSL) and Tsetlin Automata (TA) teams. The clauses thus coalesce to produce multiple outputs. A positive weight makes the clause vote for output 1, while a negative weight makes the clause vote for output 0. Each clause is related to each output by using a weight. In this paper, we introduce clause sharing, merging multiple TMs into a single one. Employing multiple TMs hinders pattern reuse because each TM then operates in a silo. While efficient for single-output problems, one needs a separate TM per output for multi-output problems. A TM represents patterns as conjunctive clauses in propositional logic (AND-rules), each clause voting for or against a particular output. Using finite-state machines to learn patterns, Tsetlin machines (TMs) have obtained competitive accuracy and learning speed across several benchmarks, with frugal memory- and energy footprint.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |