Multi-Instance Multi-Label Learning Networks for Aspect-Category Sentiment Analysis

@inproceedings{Li2020MultiInstanceML,
  title={Multi-Instance Multi-Label Learning Networks for Aspect-Category Sentiment Analysis},
  author={Yuncong Li and Cunxiang Yin and Sheng-hua Zhong and Xu Pan},
  booktitle={Conference on Empirical Methods in Natural Language Processing},
  year={2020}
}
Aspect-category sentiment analysis (ACSA) aims to predict sentiment polarities of sentences with respect to given aspect categories. To detect the sentiment toward a particular aspect category in a sentence, most previous methods first generate an aspect category-specific sentence representation for the aspect category, then predict the sentiment polarity based on the representation. These methods ignore the fact that the sentiment of an aspect category mentioned in a sentence is an aggregation… 

Figures and Tables from this paper

A More Fine-Grained Aspect-Sentiment-Opinion Triplet Extraction Task

A more fine-grained Aspect-Sentiment-Opinion Triplet Extraction (ASOTE) Task is introduced and two methods for ASOTE are proposed, one based on multiple instance learning, which is trained on ASTE datasets, but can also perform the ASOTE task.

Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledge

This paper investigates the Aspect Category Sentiment Analysis (ACSA) task from a novel perspective by exploring a Beta Distribution guided aspect-aware graph construction based on external knowledge, and employs Beta Distribution to educe the aspect- Aware weight, which reflects the importance to the aspect.

Aspect-based Sentiment Analysis through EDU-level Attentions

This paper proposes to consider EDU boundaries in sentence modeling, with attentions at both word and EDU levels, and highlights sentiment-bearing words in EDU through word-level sparse attention and orthogonal regularization.

Domain-level Pairwise Semantic Interaction for Aspect-Based Sentiment Classification

Experimental results on four ABSC datasets show that PSI is superior to many competitive state-of-the-art baselines and can significantly alleviate the problem of class-imbalance.

SK2: Integrating Implicit Sentiment Knowledge and Explicit Syntax Knowledge for Aspect-Based Sentiment Analysis

  • Jia LiYuyuan Zhao Chongyang Tao
  • Computer Science
    Proceedings of the 31st ACM International Conference on Information & Knowledge Management
  • 2022
A brand-new unified framework for ABSA is proposed in this work, which incorporates both implicit sentiment knowledge and explicit syntax knowledge to better complete all ABSA tasks.

AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment Analysis

This paper presents an extremely weakly supervised multi-label Aspect Category Sentiment Analysis framework which only relies on a single word per class as an initial in-dicative information and proposes an automatic word selection technique to choose these seed categories and sentiment words.

Sentiment Interpretable Logic Tensor Network for Aspect-Term Sentiment Analysis

This study proposes a novel Sentiment Interpretable Logic Tensor Network (SILTN), which is interpretable because it is a neurosymbolic formalism and a computational model that supports learning and reasoning about data with a differentiable first-order logic language (FOL).

Solving Aspect Category Sentiment Analysis as a Text Generation Task

This work considers a more direct way of making use of pre-trained language models, by casting the ACSA tasks into natural language generation tasks, using natural language sentences to represent the output.

Mutual Disentanglement Learning for Joint Fine-Grained Sentiment Classification and Controllable Text Generation

This paper combines FGSC and FGSG as a joint dual learning system, encouraging them to learn the advantages from each other, and proposes decoupling the feature representations in two tasks into fine-grained aspect-oriented opinion variables and content variables respectively, by performing mutual disentanglement learning upon them.

Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detection

A novel label-enhanced prototypical network (LPN) for multi-label few-shot aspect category detection that leverages label description as auxiliary knowledge to learn more discriminative prototypes, which can retain aspect-relevant information while eliminating the harmful effect caused by irrelevant aspects.

References

SHOWING 1-10 OF 49 REFERENCES

Aspect Aware Learning for Aspect Category Sentiment Analysis

A novel aspect aware learning (AAL) framework for ACSA tasks to exploit the interaction between the aspect category and the contents under the guidance of both sentiment polarity and predefined categories is proposed.

Aspect-level Sentiment Classification with HEAT (HiErarchical ATtention) Network

A HiErarchical ATtention (HEAT) network for aspect-level sentiment classification is proposed, which better allocates appropriate sentiment expressions for a given aspect benefiting from the guidance of aspect terms.

Attention-based LSTM for Aspect-level Sentiment Classification

This paper reveals that the sentiment polarity of a sentence is not only determined by the content but is also highly related to the concerned aspect, and proposes an Attention-based Long Short-Term Memory Network for aspect-level sentiment classification.

A Joint Model for Aspect-Category Sentiment Analysis with Contextualized Aspect Embedding

A novel joint model which contains a contextualized aspect embedding layer and a shared sentiment prediction layer that transfers sentiment knowledge between aspect categories and alleviates the problem caused by data deficiency.

Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysis

This paper proposes a novel method for integrating aspect information into the neural model by modeling word-aspect relationships and achieves state-of-the-art performance on benchmark datasets, outperforming ATAE-LSTM by 4%-5% on average across multiple datasets.

Aspect Based Sentiment Analysis with Gated Convolutional Networks

A model based on convolutional neural networks and gating mechanisms, which is more accurate and efficient, and the novel Gated Tanh-ReLU Units can selectively output the sentiment features according to the given aspect or entity.

Aspect-level Sentiment Analysis using AS-Capsules

This paper proposes the aspect-level sentiment capsules model (AS-Capsules), which is capable of performing aspect detection and sentiment classification simultaneously, in a joint manner, and achieves state-of-the-art performances on a benchmark dataset for aspect- level sentiment analysis.

CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis

Constrained attention networks (CAN) are proposed, a simple yet effective solution to regularize the attention for multi-aspect sentiment analysis, which alleviates the drawback of the attention mechanism.

A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis

A new large-scale Multi-Aspect Multi-Sentiment (MAMS) dataset, in which each sentence contains at least two different aspects with different sentiment polarities, and proposes simple yet effective CapsNet and CapsNet-BERT models which combine the strengths of recent NLP advances.

A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis

A novel Aspect-Guided Deep Transition model, named AGDT, is proposed, which utilizes the given aspect to guide the sentence encoding from scratch with the specially-designed deep transition architecture, and an aspect-oriented objective is designed to enforce AGDT to reconstruct thegiven aspect with the generated sentence representation.