Word-level human interpretable scoring mechanism for novel text detection using Tsetlin Machines

Bhattarai, Bimal; Granmo, Ole‐Christoffer; Jiao, Lei

doi:10.1007/s10489-022-03281-1

Cited by 8 publications

(4 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generating an episode (a path from the starting point to the terminal), using the -greedy policy with = 1 (taking random actions at each state) as the behaviour policy. Equation (5) shows the updating formula for the value iteration algorithm. Here, α, s and s , stand for the learning rate, the current state, and the next state after taking action a, respectively.…”

Section: Off-policy Learning With the Tsetlin Machinementioning

confidence: 99%

“…Several researchers have lately explored various TMbased natural language processing models, including text classification [4,21], novelty detection [5], semantic relation analysis [22], and aspect-based sentiment analysis [27], using conjunctive clauses to capture textual patterns. Other application areas are network attack detection [11], keyword spotting [12], biomedical systems design [16], and game playing [9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Off-policy and on-policy reinforcement learning with the Tsetlin machine

Gorji

Granmo

2023

Appl Intell

Self Cite

View full text Add to dashboard Cite

The Tsetlin Machine is a recent supervised learning algorithm that has obtained competitive accuracy- and resource usage results across several benchmarks. It has been used for convolution, classification, and regression, producing interpretable rules in propositional logic. In this paper, we introduce the first framework for reinforcement learning based on the Tsetlin Machine. Our framework integrates the value iteration algorithm with the regression Tsetlin Machine as the value function approximator. To obtain accurate off-policy state-value estimation, we propose a modified Tsetlin Machine feedback mechanism that adapts to the dynamic nature of value iteration. In particular, we show that the Tsetlin Machine is able to unlearn and recover from the misleading experiences that often occur at the beginning of training. A key challenge that we address is mapping the intrinsically continuous nature of state-value learning to the propositional Tsetlin Machine architecture, leveraging probabilistic updates. While accurate off-policy, this mechanism learns significantly slower than neural networks on-policy. However, by introducing multi-step temporal-difference learning in combination with high-frequency propositional logic patterns, we are able to close the performance gap. Several gridworld instances document that our framework can outperform comparable neural network models, despite being based on simple one-level AND-rules in propositional logic. Finally, we propose how the class of models learnt by our Tsetlin Machine for the gridworld problem can be translated into a more understandable graph structure. The graph structure captures the state-value function approximation and the corresponding policy found by the Tsetlin Machine.

show abstract

Section: Off-policy Learning With the Tsetlin Machinementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Off-policy and on-policy reinforcement learning with the Tsetlin machine

Gorji

Granmo

2023

Appl Intell

Self Cite

View full text Add to dashboard Cite

show abstract

“…This clause score provides the weightage of each input on the model. It has been employed in many applications such as word scoring mechanism [Bhattarai et al, 2022] and novelty detection [Bhattarai et al, 2020].…”

Section: Global Interpretation Of Tm On Spurious Correlationmentioning

confidence: 99%

Robust Interpretable Text Classification against Spurious Correlations Using AND-rules with Negation

Yang

Yin

et al. 2022

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

Multilingual neural machine translation (MNMT) trained in multiple language pairs has attracted considerable attention due to fewer model parameters and lower training costs by sharing knowledge among multiple languages. Nonetheless, multilingual training is plagued by language interference degeneration in shared parameters because of the negative interference among different translation directions, especially on high-resource languages. In this paper, we propose the multilingual translation model with the high-resource language-specific training (HLT-MT) to alleviate the negative interference, which adopts the two-stage training with the language-specific selection mechanism. Specifically, we first train the multilingual model only with the high-resource pairs and select the language-specific modules at the top of the decoder to enhance the translation quality of high-resource directions. Next, the model is further trained on all available corpora to transfer knowledge from high-resource languages (HRLs) to low-resource languages (LRLs). Experimental results show that HLT-MT outperforms various strong baselines on WMT-10 and OPUS-100 benchmarks. Furthermore, the analytic experiments validate the effectiveness of our method in mitigating the negative interference in multilingual training.

show abstract

“…In [18], a novel variant of the TM that randomly drops clauses has been proposed, from which we observe up to +10% increase in accuracy and 2× to 4× faster learning compared with vanilla TM. For natural language processing, the TM has also achieved competitive results in text classification [19], [20], word sense disambiguation [21], novelty detection [22], [23], fake news detection [24], semantic relation analysis [25], aspect-based sentiment analysis [26], and robustness towards counterfactual data [27]. Lately, more advanced architectures have appeared, such as the relational TM [3] and the coalesced TM [28].…”

Section: Introductionmentioning

confidence: 99%

On the Convergence of Tsetlin Machines for the XOR Operator

Jiao

Zhang

Granmo

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

The Tsetlin Machine (TM) is a novel machine learning algorithm with several distinct properties, including transparent inference and learning using hardware-near building blocks. Although numerous papers explore the TM empirically, many of its properties have not yet been analyzed mathematically. In this article, we analyze the convergence of the TM when input is non-linearly related to output by the XOR-operator. Our analysis reveals that the TM, with just two conjunctive clauses, can converge almost surely to reproducing XOR, learning from training data over an infinite time horizon. Furthermore, the analysis shows how the hyper-parameter T guides clause construction so that the clauses capture the distinct sub-patterns in the data. Our analysis of convergence for XOR thus lays the foundation for analyzing other more complex logical expressions. These analyses altogether, from a mathematical perspective, provide new insights on why TMs have obtained the state-of-the-art performance on several pattern recognition problems.

show abstract

Word-level human interpretable scoring mechanism for novel text detection using Tsetlin Machines

Cited by 8 publications

References 48 publications

Off-policy and on-policy reinforcement learning with the Tsetlin machine

Off-policy and on-policy reinforcement learning with the Tsetlin machine

Robust Interpretable Text Classification against Spurious Correlations Using AND-rules with Negation

On the Convergence of Tsetlin Machines for the XOR Operator

Contact Info

Product

Resources

About