Learning Sentence Embeddings with Auxiliary Tasks for Cross-Domain
            Sentiment Classification

Yu, Jianfei; Jiang, Jing

doi:10.18653/v1/d16-1023

Cited by 199 publications

(144 citation statements)

References 20 publications

Supporting

Mentioning

144

Contrasting

Order By: Relevance

“…Most multitask learning studies have focused on improving the performance of the main task or all tasks by lower layer parameter sharing among multiple tasks (Zhang et al 2014;Yu and Jiang 2016;Liu et al 2015;Cheng, Fang, and Ostendorf 2015). For example, In the work of Zhang et al, head pose estimation and facial attribute inference tasks are used as the auxiliary tasks, which shares parameters except for the last layer's parameters that participate in each tasks' output.…”

Section: Multi-task Learningmentioning

confidence: 99%

Subtask Gated Networks for Non-Intrusive Load Monitoring

Shin

Joo

Yim

et al. 2019

AAAI

104

101

View full text Add to dashboard Cite

Non-intrusive load monitoring (NILM), also known as energy disaggregation, is a blind source separation problem where a households aggregate electricity consumption is broken down into electricity usages of individual appliances. In this way, the cost and trouble of installing many measurement devices over numerous household appliances can be avoided, and only one device needs to be installed. The problem has been well-known since Hart's seminal paper in 1992, and recently significant performance improvements have been achieved by adopting deep networks. In this work, we focus on the idea that appliances have on/off states, and develop a deep network for further performance improvements. Specifically, we propose a subtask gated network that combines the main regression network with an on/off classification subtask network. Unlike typical multitask learning algorithms where multiple tasks simply share the network parameters to take advantage of the relevance among tasks, the subtask gated network multiply the main network's regression output with the subtask's classification probability. When standby-power is additionally learned, the proposed solution surpasses the state-of-theart performance for most of the benchmark cases. The subtask gated network can be very effective for any problem that inherently has on/off states.

show abstract

Section: Multi-task Learningmentioning

confidence: 99%

Subtask Gated Networks for Non-Intrusive Load Monitoring

Shin

Joo

Yim

et al. 2019

AAAI

104

101

View full text Add to dashboard Cite

show abstract

“…Existing domain adaptation tasks for sentiment analysis focus on traditional sentiment classification without considering the aspect (Blitzer, Dredze, and Pereira 2007;Pan et al 2010;Glorot, Bordes, and Bengio 2011;Chen et al 2012;Bollegala, Weir, and Carroll 2013;Yu and Jiang 2016;Li et al 2018b). In terms of data scarcity and the value of task, transfer learning is more urgent for aspect-level sentiment analysis that characterizes users' different preferences.…”

Section: Related Workmentioning

confidence: 99%

Exploiting Coarse-to-Fine Task Transfer for Aspect-Level Sentiment Classification

Wei

Zhang

et al. 2019

AAAI

View full text Add to dashboard Cite

Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or a specific Aspect Term (AT). However, due to the especially expensive and labor-intensive labeling, existing public corpora in AT-level are all relatively small. Meanwhile, most of the previous methods rely on complicated structures with given scarce data, which largely limits the efficacy of the neural models. In this paper, we exploit a new direction named coarse-to-fine task transfer, which aims to leverage knowledge learned from a rich-resource source domain of the coarse-grained AC task, which is more easily accessible, to improve the learning in a low-resource target domain of the fine-grained AT task. To resolve both the aspect granularity inconsistency and feature mismatch between domains, we propose a Multi-Granularity Alignment Network (MGAN). In MGAN, a novel Coarse2Fine attention guided by an auxiliary task can help the AC task modeling at the same finegrained level with the AT task. To alleviate the feature false alignment, a contrastive feature alignment method is adopted to align aspect-specific feature representations semantically. In addition, a large-scale multi-domain dataset for the AC task is provided. Empirically, extensive experiments demonstrate the effectiveness of the MGAN. Source domain (Restaurant-R1) Target domain (Laptop-L) resolution Aspect term: Polarity: Positive fonts Aspect term: Polarity: Negative food food cheese Aspect category: Polarity: Positive food seafood sea Aspect category: Polarity: Positive restaurant cuisine Aspect category: Polarity: Negative MGAN w/o C2F MGAN PaS attention C2F attention C2A attention Prediction: NegativeThe shells were crisp and authentic, the filling was real ricotta cheese, not the fake junk a lot of Italian places use these days.

show abstract

“…To address this problem, unsupervised domain adaptation methods can be applied. While existing methods focus on traditional cross-domain sentiment classification to learn shared representations for sentences or documents, including pivot-based methods (Blitzer et al, 2007;Pan et al, 2010;Bollegala et al, 2013;Yu and Jiang, 2016), auto-encoders (Glorot et al, 2011;Chen et al, 2012;Zhou et al, 2016), domain adversarial networks (Ganin et al, 2016;Li et al, , 2018c, or semi-supervised methods (He et al, 2018a). Due to the difficulties in fine-grained adaptation, there exist very few methods for cross-domain aspect extraction Ding et al, 2017), which acts as a sub-task of E2E-ABSA, or aspect and opinion co-extraction (Li et al, 2012;Wang and Pan, 2018) that focuses on detecting aspect and opinion words, while E2E-ABSA needs to analyze more complicated correspondences between them.…”

Section: Related Workmentioning

confidence: 99%

Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning

Li¹,

Li²,

Wei³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem. However, such formulation hinders the effectiveness of supervised methods due to the lack of annotated sequence data in many domains. To address this issue, we firstly explore an unsupervised domain adaptation setting for this task. Prior work can only use common syntactic relations between aspect and opinion words to bridge the domain gaps, which highly relies on external linguistic resources. To resolve it, we propose a novel Selective Adversarial Learning (SAL) method to align the inferred correlation vectors that automatically capture their latent relations. The SAL method can dynamically learn an alignment weight for each word such that more important words can possess higher alignment weights to achieve finegrained (word-level) adaptation. Empirically, extensive experiments 1 demonstrate the effectiveness of the proposed SAL method. . 2019c. Dual adversarial neural transfer for low-resource named entity recognition. In ACL, pages 3461-3471.

show abstract

Learning Sentence Embeddings with Auxiliary Tasks for Cross-Domain Sentiment Classification

Cited by 199 publications

References 20 publications

Subtask Gated Networks for Non-Intrusive Load Monitoring

Subtask Gated Networks for Non-Intrusive Load Monitoring

Exploiting Coarse-to-Fine Task Transfer for Aspect-Level Sentiment Classification

Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning

Contact Info

Product

Resources

About