Aspect Sentiment Classification with Aspect-Specific Opinion Spans

Xu, Lu; Bing, Lidong; Lu, Wei; Huang, Fei

doi:10.18653/v1/2020.emnlp-main.288

Cited by 53 publications

(21 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…-HAST+MCRF: A pipeline of (i) HAST, 15 a TE system based on capturing aspect detection history and opinion summary (Li et al, 2018); and (ii) MCRF-SA, 16 an SC system utilizing multiple CRF-based structured attention models (Xu et al, 2020a).…”

Section: Benchmark Resultsmentioning

confidence: 99%

YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews

Orbach

Toledo-Ronen

Spector

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Current TSA evaluation in a cross-domain setup is restricted to the small set of review domains available in existing datasets. Such an evaluation is limited, and may not reflect true performance on sites like Amazon or Yelp that host diverse reviews from many domains. To address this gap, we present YASO -a new TSA evaluation dataset of open-domain user reviews. YASO contains 2215 English sentences from dozens of review domains, annotated with target terms and their sentiment. Our analysis verifies the reliability of these annotations, and explores the characteristics of the collected data. Benchmark results using five contemporary TSA systems show there is ample room for improvement on this challenging new dataset. YASO is available at github.com/IBM/yaso-tsa.

show abstract

Section: Benchmark Resultsmentioning

confidence: 99%

YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews

Orbach

Toledo-Ronen

Spector

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…Aspect sentiment analysis or targeted sentiment analysis is another popular task. Such a task either refers to predicting sentiment polarity for a given target (Dong et al, 2014;Chen et al, 2017;Xue and Li, 2018;Wang and Lu, 2018;Li et al, 2018a;Peng et al, 2018;Xu et al, 2020) or joint extraction of targets as well as sentiment associated with each target (Mitchell et al, 2013;Zhang et al, 2015;Li and Lu, 2017;Li and Lu, 2019;. The former mostly relies on different neural networks such as self-attention (Liu and Zhang, 2017) or memory networks (Tang et al, 2016) to generate an opinion representation for a given target for further classification.…”

Section: Related Workmentioning

confidence: 99%

Position-Aware Tagging for Aspect Sentiment Triplet Extraction

Xu¹,

Li²,

Lu³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

152

View full text Add to dashboard Cite

Aspect Sentiment Triplet Extraction (ASTE)is the task of extracting the triplets of target entities, their associated sentiment, and opinion spans explaining the reason for the sentiment. Existing research efforts mostly solve this problem using pipeline approaches, which break the triplet extraction process into several stages. Our observation is that the three elements within a triplet are highly related to each other, and this motivates us to build a joint model to extract such triplets using a sequence tagging approach. However, how to effectively design a tagging approach to extract the triplets that can capture the rich interactions among the elements is a challenging research question. In this work, we propose the first end-to-end model with a novel positionaware tagging scheme that is capable of jointly extracting the triplets. Our experimental results on several existing datasets show that jointly capturing elements in the triplet using our approach leads to improved performance over the existing approaches. We also conducted extensive experiments to investigate the model effectiveness and robustness 1 .

show abstract

“…Aspect-Based Sentiment Analysis (ABSA) (Pontiki et al, 2014) addresses various sentiment analysis tasks at a finegrained level. As mentioned in the Section 1, the subtasks mainly include ASC (Dong et al, 2014;He et al, 2018b;Li et al, 2018a;Peng et al, 2018;Wang and Lu, 2018;Li and Lu, 2019;Xu et al, 2020a), ATE (Qiu et al, 2011;Yin et al, 2016;Li et al, 2018b;Ma et al, 2019), OTE (Hu and Liu, 2004;Yang and Cardie, 2012;Klinger and Cimiano, 2013;Yang and Cardie, 2013). There is also another subtask named Target-oriented Opinion Words Extraction (TOWE) (Fan et al, 2019), which aim to extract the corresponding opinion words for a given target term.…”

Section: Related Workmentioning

confidence: 99%

Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction

Xu¹,

Chia²,

Bing³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

Aspect Sentiment Triplet Extraction (ASTE)is the most recent subtask of ABSA which outputs triplets of an aspect target, its associated sentiment, and the corresponding opinion term. Recent models perform the triplet extraction in an end-to-end manner but heavily rely on the interactions between each target word and opinion word. Thereby, they cannot perform well on targets and opinions which contain multiple words. Our proposed span-level approach explicitly considers the interaction between the whole spans of targets and opinions when predicting their sentiment relation. Thus, it can make predictions with the semantics of whole spans, ensuring better sentiment consistency. To ease the high computational cost caused by span enumeration, we propose a dual-channel span pruning strategy by incorporating supervision from the Aspect Term Extraction (ATE) and Opinion Term Extraction (OTE) tasks. This strategy not only improves computational efficiency but also distinguishes the opinion and target spans more properly. Our framework simultaneously achieves strong performance for the ASTE as well as ATE and OTE tasks. In particular, our analysis shows that our spanlevel approach achieves more significant improvements over the baselines on triplets with multi-word targets or opinions. 1 * Equal contribution. Lu Xu and Yew Ken Chia are under the Joint PhD Program between Alibaba and

show abstract

Aspect Sentiment Classification with Aspect-Specific Opinion Spans

Cited by 53 publications

References 39 publications

YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews

YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews

Position-Aware Tagging for Aspect Sentiment Triplet Extraction

Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction

Contact Info

Product

Resources

About