8DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction(2020.10.22)
生活随笔
收集整理的這篇文章主要介紹了
8DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction(2020.10.22)
小編覺得挺不錯的,現在分享給大家,幫大家做個參考.
DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction
Doer:面向方面項-極性共抽取的雙交叉共享RNN
Abstract
- This paper focuses on two related subtasks of aspect-based sentiment analysis, namely aspect term extraction and aspect sentiment classification, which we call aspect term-polarity co-extraction.
本文重點研究了基于方面的情感分析的兩個相關子任務,即方面項提取和方面情感分類,我們稱之為方面項-極性共抽取。 - The former task is to extract aspects of a product or service from an opinion document, and the latter is to identify the polarity expressed in the document about these extracted aspects.
前者的任務是從意見文檔中提取產品或服務的方面,而后者的任務是識別文檔中關于這些提取的方面所表達的極性。 - Most existing algorithms address them as two separate tasks and solve them one by one, or only perform one task, which can be complicated for real applications.
大多數現有的算法將它們作為兩個獨立的任務來處理,并逐個解決它們,或者只執行一個任務,這在實際應用中可能會很復雜。 - In this paper, we treat these two tasks as two sequence labeling problems and propose a novel Dual cross-shared RNN framework (DOER) to generate all aspect term-polarity pairs of the input sentence simultaneously.
在本文中,我們將這兩個任務視為兩個序列標記問題,并提出了一種新穎的雙重交叉共享RNN框架(DOER),可同時生成輸入句子的所有方面項-極性對。 - Specifically, DOER involves a dual recurrent neural network to extract the respective representation of each task, and a cross-shared unit to consider the relationship between them.
具體來說,DOER涉及一個雙重遞歸神經網絡以提取每個任務的各自表示,以及一個交叉共享的單元來考慮它們之間的關系。 - Experimental results demonstrate that the pro-posed framework outperforms state-of-the-art baselines on three benchmark datasets.
實驗結果表明,提出的框架在三個基準數據集上的性能優于最新的基線。
一、Introduction
Aspect terms extraction (ATE) and aspect sentiment classification (ASC) are two fundamental, fine-grained subtasks of aspect-based sentiment analysis.
-‘方面術語提取(ATE)’和‘方面情感分類(ASC)’是基于方面的情感分析的兩個基本的細粒度子任務。
二、Methodology
The proposed framework is shown in Figure 3a.We will first formulate the aspect term-polarity co-extraction problem and then describe this frame-work in detail in this section.
提議的框架如圖3a所示,我們將首先提出方面項-極性共提取問題,然后在本節中詳細描述此框架。
- 2.1 Problem Statement
- We solve it as two sequence labeling tasks.Formally, given a review sentence S with n words from a particular domain, denoted by S={wi|i=1,…,n}.
我們將其作為兩個序列標記任務來解決。形式上,給定一個具有來自特定域的n個單詞的評論句子S,表示為S = {wi | i = 1,…,n}。
Ta中的標記B,I和O分別代表方面術語的開頭,方面術語的內部和其他詞。標簽PO,NT,NG和CF分別指示極性類別:正,中性,負和沖突。Tp中的標簽O表示Ta中的其他單詞。
三、Experiments
- 3.4 Baseline Methods
Table 2: F1 score (%) comparison of all systems for aspect term-polarity pair extraction.
We use two abbreviations AuL and AuS for the ablation study. AuL denotes the auxiliary task of aspect term length enhancement, and AuS denotes the auxiliary task of sentiment lexicon enhancement.All baselines have publicly available codes
在消融研究中,我們使用兩個縮寫AuL和AuS。 AuL表示方面項長度增強的輔助任務,而AuS表示情感詞典增強的輔助任務。‘所有baseline有公開代碼’。
- 3.5 All baselines have publicly available codes - Comparison Results.:比較結果如表2所示,這是方面項-極性對的F1分數。 結果表明,我們的DOER在基線上獲得了持續的改進。
- Ablation Study.消融研究:為了測試Doer的每個組件的有效性,我們進行了消融實驗,結果如‘表2’最后一塊所示。
與S-BiLSTM相比,S-BiReGU具有更好的性能,這一事實表明了REGU在我們的任務中的有效性。 這種殘留架構使信息更有效地傳輸到下一層。
在CSU的幫助下,S-BiReGU + CSU的性能要比沒有它時更好。 我們認為,ATE和ASC之間的信息交互對于彼此改善至關重要。情感詞典的另一項輔助任務也可以增強該框架的表示能力。
作為S-BiReGU,CSU,AuL和AuS的整體,擬議的DOER實現了卓越的性能。 它主要得益于兩個輔助任務的增強功能以??及ATE和ASC兩條單獨路線的相互作用。 - ’Results on ATE‘:
- Visualization of Attention Scores in CSU:
五、Conclusion
- In this paper, we introduced a co-extraction task involving aspect term extraction and aspect sentiment classification for aspect-based sentiment analysis and proposed a novel framework DOER to solve the problem.
本文針對基于方面的情感分析,提出了一種包括方面術語提取和方面情感分類的聯合抽取任務,并提出了一種新的框架實施者來解決這一問題。 - The framework uses a joint sequence labeling approach and focuses on the interaction between two separate routes for aspect term extraction and aspect sentiment classification.
該框架使用聯合序列標注方法,重點研究了兩條獨立路徑之間的交互作用,用于特征詞提取和特征情感分類。 - To enhance the representation of sentiment and alleviate the difficulty of long aspect terms, two auxiliary tasks were also introduced in our framework.
為了增強情感表達并減輕長術語方面的困難,我們的框架中還引入了兩個輔助任務。 - Experimental results on three bench-mark datasets verified the effectiveness of DOERand showed that it significantly outperforms the baselines on aspect term-polarity co-extraction.
在三個基準數據集上的實驗結果驗證了DOER的有效性,并表明它在方面項-極性共提取方面明顯優于基線。
總結
以上是生活随笔為你收集整理的8DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction(2020.10.22)的全部內容,希望文章能夠幫你解決所遇到的問題。
- 上一篇: lucas–kanade_Lucas–K
- 下一篇: Ubuntu18.04+python3.