GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis

Luo, Huaishao; Ji, Lei; Li, Tianrui; Jiang, Daxin; Duan, Nan

doi:10.18653/v1/2020.findings-emnlp.6

Cited by 25 publications

(11 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aspect-Opinion Pair Extraction (AOPE) SpanMlt [13], SDRN [11], GTS [75], QDSL [76], SynFue [77] End-to-End ABSA (E2E-ABSA) NN-CRF [78], MNN [79], E2E-TBSA [80], DOER [81], IMN [82], SPAN [83], RACL [84], GRACE [85], IMKTN [86], RF-MRC [87] Aspect Category Sentiment Analysis (ACSA) AddOneDim [88], Hier-GCN [89], BART-generation [90] Triplet Extraction…”

Section: Pair Extractionmentioning

confidence: 99%

“…These end-to-end methods can be generally divided into two types [10,78], as shown in Table 3. The first "joint" method exploits the relation between two subtasks via training them jointly within a multi-task learning framework [81,82,84,85,86]. Two label sets including the aspect boundary label (the first row) and the sentiment label (the second row) are adopted to predict the two types of sentiment elements.…”

Section: End-to-end Absa (E2e-absa)mentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges

Zhang¹,

Li²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

As an important fine-grained sentiment analysis problem, aspect-based sentiment analysis (ABSA), aiming to analyze and understand people's opinions at the aspect level, has been attracting considerable interest in the last decade. To handle ABSA in different scenarios, various tasks have been introduced for analyzing different sentiment elements and their relations, including the aspect term, aspect category, opinion term, and sentiment polarity. Unlike early ABSA works focusing on a single sentiment element, many compound ABSA tasks involving multiple elements have been studied in recent years for capturing more complete aspect-level sentiment information. However, a systematic review of various ABSA tasks and their corresponding solutions is still lacking, which we aim to fill in this survey. More specifically, we provide a new taxonomy for ABSA which organizes existing studies from the axes of concerned sentiment elements, with an emphasis on recent advances of compound ABSA tasks. From the perspective of solutions, we summarize the utilization of pre-trained language models for ABSA, which improved the performance of ABSA to a new stage. Besides, techniques for building more practical ABSA systems in cross-domain/lingual scenarios are discussed. Finally, we review some emerging topics and discuss some open challenges to outlook potential future directions of ABSA.

show abstract

Section: Pair Extractionmentioning

confidence: 99%

Section: End-to-end Absa (E2e-absa)mentioning

confidence: 99%

A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges

Zhang¹,

Li²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Trusca et al extend [36] with deep contextual word embeddings and add an extra attention layer to its high-level representations [34]. To address the imbalance issue and utilize the interaction between aspect terms, Luo et al [24] propose a gradient harmonized and cascaded labelling model based on BERT. Chen et al [7] utilize directional graph convolutional networks to perform end-to-end ABSA task.…”

Section: Aspect-based Sentiment Analysismentioning

confidence: 99%

Phocus: Picking Valuable Research from a Sea of Citations

Zhang¹,

Ren²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

The deluge of new papers has significantly blocked the development of academics, which is mainly caused by author-level and publication-level evaluation metrics that only focus on quantity. Those metrics have resulted in several severe problems that trouble scholars focusing on the important research direction for a long time and even promote an impetuous academic atmosphere.To solve those problems, we propose Phocus, a novel academic evaluation mechanism for authors and papers. Phocus analyzes the sentence containing a citation and its contexts to predict the sentiment towards the corresponding reference. Combining others factors, Phocus classifies citations coarsely, ranks all references within a paper, and utilizes the results of the classifier and the ranking model to get the local influential factor of a reference to the citing paper. The global influential factor of the reference to the citing paper is the product of the local influential factor and the total influential factor of the citing paper. Consequently, an author's academic influential factor is the sum of one's contributions to each paper one co-authors.

show abstract

“…Post-training refers to the process of performing additional unsupervised training to a PLM such as BERT using unlabeled domain-specific data, prior to fine-tuning. It has been shown that this leads to improved performance by helping the PLM to adapt to the target domain [46][47][48][49]. We start with a monolingual PLM in L S and completely adapt it to L T .…”

Section: Transfer Learning As Post-trainingmentioning

confidence: 99%

Exploring the Data Efficiency of Cross-Lingual Post-Training in Pretrained Language Models

Lee

Yang

Whang³

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Language model pretraining is an effective method for improving the performance of downstream natural language processing tasks. Even though language modeling is unsupervised and thus collecting data for it is relatively less expensive, it is still a challenging process for languages with limited resources. This results in great technological disparity between high- and low-resource languages for numerous downstream natural language processing tasks. In this paper, we aim to make this technology more accessible by enabling data efficient training of pretrained language models. It is achieved by formulating language modeling of low-resource languages as a domain adaptation task using transformer-based language models pretrained on corpora of high-resource languages. Our novel cross-lingual post-training approach selectively reuses parameters of the language model trained on a high-resource language and post-trains them while learning language-specific parameters in the low-resource language. We also propose implicit translation layers that can learn linguistic differences between languages at a sequence level. To evaluate our method, we post-train a RoBERTa model pretrained in English and conduct a case study for the Korean language. Quantitative results from intrinsic and extrinsic evaluations show that our method outperforms several massively multilingual and monolingual pretrained language models in most settings and improves the data efficiency by a factor of up to 32 compared to monolingual training.

show abstract

GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis

Cited by 25 publications

References 38 publications

A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges

A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges

Phocus: Picking Valuable Research from a Sea of Citations

Exploring the Data Efficiency of Cross-Lingual Post-Training in Pretrained Language Models

Contact Info

Product

Resources

About