Findings of the Association for Computational Linguistics: ACL 2022 · 2022 · 62 citations · 31 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingInformation ExtractionLanguage ModelingLanguage ModelsNatural Language GenerationOpinion MiningSentiment AnalysisAspectAspect ExtractionAspect Term ExtractionBenchmark DatasetsData Augmentation
Aspect-based sentiment analysis (ABSA) tasks aim to extract sentiment tuples from a sentence. Recent generative methods such as Seq2Seq models have achieved good performance by formulating the output as a sequence of sentiment tuples. However, the orders between the sentiment tuples do not naturally exist and the generation of the current tuple should not condition on the previous ones. In this paper, we propose Seq2Path to generate sentiment tuples as paths of a tree. A tree can represent "1-to-n" relations (e.g., an aspect term may correspond to multiple opinion terms) and the paths of a tree are independent and do not have orders. For training, we treat each path as an independent target, and we calculate the average loss of the ordinary Seq2Seq model over paths. For inference, we apply beam search with constrained decoding. By introducing an additional discriminative token and applying a data augmentation technique, valid paths can be automatically selected. We conduct experiments on five tasks including AOPE, ASTE, TASD, UABSA, ACOS. We evaluate our method on four common benchmark datasets including Laptop14, Rest14, Rest15, Rest16.
31
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2023 · 76.3K citations · Full text
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Attention-based LSTM for Aspect-level Sentiment Classification
Yequan Wang, Minlie Huang, Xiaoyan Zhu et al. · 2016 · 2.3K citations · Full text
SemEval-2014 Task 4: Aspect Based Sentiment Analysis
Maria Pontiki, Dimitrios Galanis, John Pavlopoulos et al. · 2014 · 1.9K citations · Full text