scholarly journals Knowing What, How and Why: A Near Complete Solution for Aspect-Based Sentiment Analysis

2020 ◽  
Vol 34 (05) ◽  
pp. 8600-8607
Author(s):  
Haiyun Peng ◽  
Lu Xu ◽  
Lidong Bing ◽  
Fei Huang ◽  
Wei Lu ◽  
...  
Keyword(s):  
Sentiment Analysis ◽  
State Of The Art ◽  
Complete Solution ◽  
Unified Model ◽  
Two Stage ◽  
Fine Grained ◽  
Aspect Extraction ◽  
Second Stage ◽  
Opinion Extraction ◽  
Complete Story

Target-based sentiment analysis or aspect-based sentiment analysis (ABSA) refers to addressing various sentiment analysis tasks at a fine-grained level, which includes but is not limited to aspect extraction, aspect sentiment classification, and opinion extraction. There exist many solvers of the above individual subtasks or a combination of two subtasks, and they can work together to tell a complete story, i.e. the discussed aspect, the sentiment on it, and the cause of the sentiment. However, no previous ABSA research tried to provide a complete solution in one shot. In this paper, we introduce a new subtask under ABSA, named aspect sentiment triplet extraction (ASTE). Particularly, a solver of this task needs to extract triplets (What, How, Why) from the inputs, which show WHAT the targeted aspects are, HOW their sentiment polarities are and WHY they have such polarities (i.e. opinion reasons). For instance, one triplet from “Waiters are very friendly and the pasta is simply average” could be (‘Waiters’, positive, ‘friendly’). We propose a two-stage framework to address this task. The first stage predicts what, how and why in a unified model, and then the second stage pairs up the predicted what (how) and why from the first stage to output triplets. In the experiments, our framework has set a benchmark performance in this novel triplet extraction task. Meanwhile, it outperforms a few strong baselines adapted from state-of-the-art related methods.

scholarly journals Learning to Hallucinate Face Images via Component Generation and Enhancement

2017 ◽  
Author(s):  
Yibing Song ◽  
Jiawei Zhang ◽  
Shengfeng He ◽  
Linchao Bao ◽  
Qingxiong Yang
Keyword(s):  
High Resolution ◽  
State Of The Art ◽  
Ground Truth ◽  
Input Image ◽  
Two Stage ◽  
Face Hallucination ◽  
Fine Grained ◽  
Second Stage ◽  
Training Images ◽  
Face Images

We propose a two-stage method for face hallucination. First, we generate facial components of the input image using CNNs. These components represent the basic facial structures. Second, we synthesize fine-grained facial structures from high resolution training images. The details of these structures are transferred into facial components for enhancement. Therefore, we generate facial components to approximate ground truth global appearance in the first stage and enhance them through recovering details in the second stage. The experiments demonstrate that our method performs favorably against state-of-the-art methods.

scholarly journals Multiple Instance Learning Networks for Fine-Grained Sentiment Analysis

2018 ◽  
Vol 6 ◽  
pp. 17-31 ◽  
Author(s):  
Stefanos Angelidis ◽  
Mirella Lapata
Keyword(s):  
Sentiment Analysis ◽  
Neural Model ◽  
Multiple Instance Learning ◽  
Superior Performance ◽  
Learning Networks ◽  
Scoring Method ◽  
Fine Grained ◽  
Opinion Extraction ◽  
Elicitation Study ◽  
Discourse Units

We consider the task of fine-grained sentiment analysis from the perspective of multiple instance learning (MIL). Our neural model is trained on document sentiment labels, and learns to predict the sentiment of text segments, i.e. sentences or elementary discourse units (EDUs), without segment-level supervision. We introduce an attention-based polarity scoring method for identifying positive and negative text snippets and a new dataset which we call SpoT (as shorthand for Segment-level POlariTy annotations) for evaluating MIL-style sentiment models like ours. Experimental results demonstrate superior performance against multiple baselines, whereas a judgement elicitation study shows that EDU-level opinion extraction produces more informative summaries than sentence-based alternatives.

Two-Stage Sintering of Nb2O5 Doped Zirconia Toughened Alumina (ZTA) Composites

2020 ◽  
Vol 861 ◽  
pp. 327-333
Author(s):  
Teow Hsien Loong ◽  
Se Yong Eh Noum ◽  
Wong Wai Mun
Keyword(s):  
Mechanical Properties ◽  
Hip Replacement ◽  
Niobium Oxide ◽  
Sintering Temperature ◽  
Well Being ◽  
Two Stage ◽  
Total Hip ◽  
Fine Grained ◽  
Second Stage ◽  
Zirconia Toughened Alumina

It is estimated that 130 million people will suffer from osteoarthritis by 2050 which require patient to undergo a surgical procedure known as total hip replacement which has lifespan of 20 years and failure rates of ~1%. This research would highlight the effects of doping Niobium Oxide (Nb2O5) between 0 vol % to 0.8 vol % into Zirconia-Toughened Alumina (ZTA) composites which is the main biomaterials used to manufacture total hip arthroplasty. The samples were sintered using two-stage sintering (TSS) between 1400°C and 1550°C for first-stage sintering temperature at heating rate of 20°C/min. At second stage, the samples were sintered at 1350°C and hold for 12 hours. It was found that TSS combined with addition of Nb2O5 as dopants were beneficial in producing fine-grained ZTA composites with improved mechanical properties compared to undoped ZTA composites produced via TSS. Compared to undoped ZTA composites, samples doped with Nb2O5 and sintered at T1 ≥1400°C were fully densed (>98%), achieved Vickers hardness more than 20 GPa and Young’s modulus higher than 410 GPa and at the same time fracture toughness of more than 8 MPam1/2. Based on the findings, production of ZTA composites with enhanced mechanical properties with longer lifespan is possible which is beneficial in ensuring the well-being of osteoarthritis patients.

scholarly journals A Mixed approach of Deep Learning method and Rule-Based method to improve Aspect Level Sentiment Analysis

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Paramita Ray ◽  
Amlan Chakrabarti
Keyword(s):  
Deep Learning ◽  
Sentiment Analysis ◽  
State Of The Art ◽  
The State ◽  
Learning Approach ◽  
Learning Method ◽  
Rule Based ◽  
Aspect Extraction ◽  
Art Methods ◽  
Rule Based Approach

Social networks have changed the communication patterns significantly. Information available from different social networking sites can be well utilized for the analysis of users opinion. Hence, the organizations would benefit through the development of a platform, which can analyze public sentiments in the social media about their products and services to provide a value addition in their business process. Over the last few years, deep learning is very popular in the areas of image classification, speech recognition, etc. However, research on the use of deep learning method in sentiment analysis is limited. It has been observed that in some cases the existing machine learning methods for sentiment analysis fail to extract some implicit aspects and might not be very useful. Therefore, we propose a deep learning approach for aspect extraction from text and analysis of users sentiment corresponding to the aspect. A seven layer deep convolutional neural network (CNN) is used to tag each aspect in the opinionated sentences. We have combined deep learning approach with a set of rule-based approach to improve the performance of aspect extraction method as well as sentiment scoring method. We have also tried to improve the existing rule-based approach of aspect extraction by aspect categorization with a predefined set of aspect categories using clustering method and compared our proposed method with some of the state-of-the-art methods. It has been observed that the overall accuracy of our proposed method is 0.87 while that of the other state-of-the-art methods like modified rule-based method and CNN are 0.75 and 0.80 respectively. The overall accuracy of our proposed method shows an increment of 7–12% from that of the state-of-the-art methods.

scholarly journals Learn to Select via Hierarchical Gate Mechanism for Aspect-Based Sentiment Analysis

2019 ◽  
Author(s):  
Xiangying Ran ◽  
Yuanyuan Pan ◽  
Wei Sun ◽  
Chongjun Wang
Keyword(s):  
Neural Network ◽  
Sentiment Analysis ◽  
State Of The Art ◽  
Original Sequence ◽  
Fine Grained ◽  
Complex Sentences ◽  
Specific Memory ◽  
Related Part ◽  
Memory Network ◽  
The Given

Aspect-based sentiment analysis (ABSA) is a fine-grained task. Recurrent Neural Network (RNN) model armed with attention mechanism seems a natural fit for this task, and actually it achieves the state-of-the-art performance recently. However, previous attention mechanisms proposed for ABSA may attend irrelevant words and thus downgrade the performance, especially when dealing with long and complex sentences with multiple aspects. In this paper, we propose a novel architecture named Hierarchical Gate Memory Network (HGMN) for ABSA: firstly, we employ the proposed hierarchical gate mechanism to learn to select the related part about the given aspect, which can keep the original sequence structure of sentence at the same time. After that, we apply Convolutional Neural Network (CNN) on the final aspect-specific memory. We conduct extensive experiments on the SemEval 2014 and Twitter dataset, and results demonstrate that our model outperforms attention based state-of-the-art baselines.

scholarly journals StackDRL: Stacked Deep Reinforcement Learning for Fine-grained Visual Categorization

2018 ◽  
Author(s):  
Xiangteng He ◽  
Yuxin Peng ◽  
Junjie Zhao
Keyword(s):  
Reinforcement Learning ◽  
Visual Information ◽  
Experimental Validation ◽  
State Of The Art ◽  
Two Stage ◽  
Visual Categorization ◽  
Fine Grained ◽  
Reward Function ◽  
Main Challenge ◽  
Labor Consumption

Fine-grained visual categorization (FGVC) is the discrimination of similar subcategories, whose main challenge is to localize the quite subtle visual distinctions between similar subcategories. There are two pivotal problems: discovering which region is discriminative and representative, and determining how many discriminative regions are necessary to achieve the best performance. Existing methods generally solve these two problems relying on the prior knowledge or experimental validation, which extremely restricts the usability and scalability of FGVC. To address the "which" and "how many" problems adaptively and intelligently, this paper proposes a stacked deep reinforcement learning approach (StackDRL). It adopts a two-stage learning architecture, which is driven by the semantic reward function. Two-stage learning localizes the object and its parts in sequence ("which"), and determines the number of discriminative regions adaptively ("how many"), which is quite appealing in FGVC. Semantic reward function drives StackDRL to fully learn the discriminative and conceptual visual information, via jointly combining the attention-based reward and category-based reward. Furthermore, unsupervised discriminative localization avoids the heavy labor consumption of labeling, and extremely strengthens the usability and scalability of our StackDRL approach. Comparing with ten state-of-the-art methods on CUB-200-2011 dataset, our StackDRL approach achieves the best categorization accuracy.

scholarly journals One for “All”: a unified model for fine-grained sentiment analysis under three tasks

2021 ◽  
Vol 7 ◽  
pp. e816
Author(s):  
Heng-yang Lu ◽  
Jun Yang ◽  
Cong Hu ◽  
Wei Fang
Keyword(s):  
Sentiment Analysis ◽  
Data Augmentation ◽  
Language Model ◽  
Unified Model ◽  
Training Data ◽  
Low Resource ◽  
Fine Grained ◽  
Questions And Answers ◽  
Resource Conditions ◽  
Media Data

Background Fine-grained sentiment analysis is used to interpret consumers’ sentiments, from their written comments, towards specific entities on specific aspects. Previous researchers have introduced three main tasks in this field (ABSA, TABSA, MEABSA), covering all kinds of social media data (e.g., review specific, questions and answers, and community-based). In this paper, we identify and address two common challenges encountered in these three tasks, including the low-resource problem and the sentiment polarity bias. Methods We propose a unified model called PEA by integrating data augmentation methodology with the pre-trained language model, which is suitable for all the ABSA, TABSA and MEABSA tasks. Two data augmentation methods, which are entity replacement and dual noise injection, are introduced to solve both challenges at the same time. An ensemble method is also introduced to incorporate the results of the basic RNN-based and BERT-based models. Results PEA shows significant improvements on all three fine-grained sentiment analysis tasks when compared with state-of-the-art models. It also achieves comparable results with what the baseline models obtain while using only 20% of their training data, which demonstrates its extraordinary performance under extreme low-resource conditions.

scholarly journals Embedding Projection for Targeted Cross-lingual Sentiment: Model Comparisons and a Real-World Study

2019 ◽  
Vol 66 ◽  
Author(s):  
Jeremy Barnes ◽  
Roman Klinger
Keyword(s):  
Sentiment Analysis ◽  
State Of The Art ◽  
Target Language ◽  
Test Machine ◽  
Fine Grained ◽  
Sentence Level ◽  
Level Information ◽  
Cross Lingual ◽  
Multiple Domains ◽  
Embedding Methods

Sentiment analysis benefits from large, hand-annotated resources in order to train and test machine learning models, which are often data hungry. While some languages, e.g., English, have a vast arrayof these resources, most under-resourced languages do not, especially for fine-grained sentiment tasks, such as aspect-level or targeted sentiment analysis. To improve this situation, we propose a cross-lingual approach to sentiment analysis that is applicable to under-resourced languages and takes into account target-level information. This model incorporates sentiment information into bilingual distributional representations, byjointly optimizing them for semantics and sentiment, showing state-of-the-art performance at sentence-level when combined with machine translation. The adaptation to targeted sentiment analysis on multiple domains shows that our model outperforms other projection-based bilingual embedding methods on binary targetedsentiment tasks. Our analysis on ten languages demonstrates that the amount of unlabeled monolingual data has surprisingly little effect on the sentiment results. As expected, the choice of a annotated source language for projection to a target leads to better results for source-target language pairs which are similar. Therefore, our results suggest that more efforts should be spent on the creation of resources for less similar languages tothose which are resource-rich already. Finally, a domain mismatch leads to a decreased performance. This suggests resources in any language should ideally cover varieties of domains.

Intelligent product redesign strategy with ontology-based fine-grained sentiment analysis

2021 ◽  
pp. 1-21
Author(s):  
Siyu Zhu ◽  
Jin Qi ◽  
Jie Hu ◽  
Haiqing Huang
Keyword(s):  
Sentiment Analysis ◽  
State Of The Art ◽  
House Of Quality ◽  
Customer Preference ◽  
Fine Grained ◽  
Customer Preferences ◽  
Analysis Methods ◽  
System Information ◽  
Increasing Demand

Abstract With the increasing demand for a personalized product and rapid market response, many companies expect to explore online user-generated content (UGC) for intelligent customer hearing and product redesign strategy. UGC has the advantages of being more unbiased than traditional interviews, yielding in-time response, and widely accessible with a sheer volume. From online resources, customers’ preferences toward various aspects of the product can be exploited by promising sentiment analysis methods. However, due to the complexity of language, state-of-the-art sentiment analysis methods are still not accurate for practice use in product redesign. To tackle this problem, we propose an integrated customer hearing and product redesign system, which combines the robust use of sentiment analysis for customer hearing and coordinated redesign mechanisms. Ontology and expert knowledges are involved to promote the accuracy. Specifically, a fuzzy product ontology that contains domain knowledges is first learned in a semi-supervised way. Then, UGC is exploited with a novel ontology-based fine-grained sentiment analysis approach. Extracted customer preference statistics are transformed into multilevels, for the automatic establishment of opportunity landscapes and house of quality table. Besides, customer preference statistics are interactively visualized, through which representative customer feedbacks are concurrently generated. Through a case study of smartphone, the effectiveness of the proposed system is validated, and applicable redesign strategies for a case product are provided. With this system, information including customer preferences, user experiences, using habits and conditions can be exploited together for reliable product redesign strategy elicitation.

scholarly journals A BERT-Based Two-Stage Model for Chinese Chengyu Recommendation

2021 ◽  
Vol 20 (6) ◽  
pp. 1-18
Author(s):  
Minghuan Tan ◽  
Jing Jiang ◽  
Bing Tian Dai
Keyword(s):  
State Of The Art ◽  
The State ◽  
Stage Model ◽  
Performance Gain ◽  
Two Stage ◽  
Second Stage ◽  
Fine Tune

In Chinese, Chengyu are fixed phrases consisting of four characters. As a type of idioms, their meanings usually cannot be derived from their component characters. In this article, we study the task of recommending a Chengyu given a textual context. Observing some of the limitations with existing work, we propose a two-stage model, where during the first stage we re-train a Chinese BERT model by masking out Chengyu from a large Chinese corpus with a wide coverage of Chengyu. During the second stage, we fine-tune the re-trained, Chengyu-oriented BERT on a specific Chengyu recommendation dataset. We evaluate this method on ChID and CCT datasets and find that it can achieve the state of the art on both datasets. Ablation studies show that both stages of training are critical for the performance gain.

Sign in / Sign up

Export Citation Format

Share Document