Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis

Wang, Wenya; Pan, Sinno Jialin; Dahlmeier, Daniel; Xiao, Xiaokui

doi:10.18653/v1/d16-1059

Cited by 366 publications

(274 citation statements)

References 30 publications

Supporting

Mentioning

272

Contrasting

Unclassified

Order By: Relevance

“…We run experiments on three benchmark datasets, taken from Se-mEval2014 (Pontiki et al, 2014) and SemEval 2015 (Pontiki et al, 2015). The opinion terms are annotated by Wang et al (2016a). We use two document-level datasets from (He et al, 2018b).…”

Section: Learningmentioning

confidence: 99%

An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis

He¹,

Lee²,

Ng³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

223

184

View full text Add to dashboard Cite

Aspect-based sentiment analysis produces a list of aspect terms and their corresponding sentiments for a natural language sentence. This task is usually done in a pipeline manner, with aspect term extraction performed first, followed by sentiment predictions toward the extracted aspect terms. While easier to develop, such an approach does not fully exploit joint information from the two subtasks and does not use all available sources of training information that might be helpful, such as document-level labeled sentiment corpus. In this paper, we propose an interactive multi-task learning network (IMN) which is able to jointly learn multiple related tasks simultaneously at both the token level as well as the document level. Unlike conventional multi-task learning methods that rely on learning common features for the different tasks, IMN introduces a message passing architecture where information is iteratively passed to different tasks through a shared set of latent variables. Experimental results demonstrate superior performance of the proposed method against multiple baselines on three benchmark datasets.

show abstract

Section: Learningmentioning

confidence: 99%

An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis

He¹,

Lee²,

Ng³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

223

184

View full text Add to dashboard Cite

show abstract

“…In what follows, we sometimes refer to an aspect-opinion pair as an opinion. Aspect and opinion term extractions are sequence tagging tasks as in ABSA [22,48,49,55], where V = {B-AS, I-AS, B-OP, I-OP, O} using the classic IOB format. The B-AS/B-OP tags indicate that a token is at the beginning of an aspect/opinion term, the I-AS/I-OP tags indicate that a token is inside an aspect/opinion term and O tags indicate that a token is outside of any aspect/opinion term.…”

Section: Tagging and Span Classificationmentioning

confidence: 99%

Snippext: Semi-supervised Opinion Mining with Augmented Data

Miao

Wang

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

Online services are interested in solutions to opinion mining, which is the problem of extracting aspects, opinions, and sentiments from text. One method to mine opinions is to leverage the recent success of pre-trained language models which can be fine-tuned to obtain highquality extractions from reviews. However, fine-tuning language models still requires a non-trivial amount of training data.In this paper, we study the problem of how to significantly reduce the amount of labeled training data required in fine-tuning language models for opinion mining. We describe Snippext, an opinion mining system developed over a language model that is fine-tuned through semi-supervised learning with augmented data. A novelty of Snippext is its clever use of a two-prong approach to achieve state-of-the-art (SOTA) performance with little labeled training data through: (1) data augmentation to automatically generate more labeled training data from existing ones, and (2) a semi-supervised learning technique to leverage the massive amount of unlabeled data in addition to the (limited amount of) labeled data. We show with extensive experiments that Snippext performs comparably and can even exceed previous SOTA results on several opinion mining tasks with only half the training data required. Furthermore, it achieves new SOTA results when all training data are leveraged. By comparison to a baseline pipeline, we found that Snippext extracts significantly more fine-grained opinions which enable new opportunities of downstream applications. ACM Reference Format:

show abstract

“…Word embeddings are commonly used features, hand-crafted features such as POS tag classes and chunk information can also be combined to yield better performance (Liu et al, 2015a;Yin et al, 2016). For example, Wang et al (2016) construct a recursive neural network based on the dependency parsing tree of a sentence with word embeddings as input. The output of the neural network is then fed into a CRF.…”

Section: Related Workmentioning

confidence: 99%

Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision

Dai

Song

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

115

View full text Add to dashboard Cite

Lack of labeled training data is a major bottleneck for neural network based aspect and opinion term extraction on product reviews. To alleviate this problem, we first propose an algorithm to automatically mine extraction rules from existing training examples based on dependency parsing results. The mined rules are then applied to label a large amount of auxiliary data. Finally, we study training procedures to train a neural model which can learn from both the data automatically labeled by the rules and a small amount of data accurately annotated by human. Experimental results show that although the mined rules themselves do not perform well due to their limited flexibility, the combination of human annotated data and rule labeled auxiliary data can improve the neural model and allow it to achieve performance better than or comparable with the current state-of-the-art.

show abstract

Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis

Cited by 366 publications

References 30 publications

An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis

An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis

Snippext: Semi-supervised Opinion Mining with Augmented Data

Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision

Contact Info

Product

Resources

About