A SentiWordNet Strategy for Curriculum Learning in Sentiment Analysis
Language Technologies Research Center（语言技术研究中心）；Kohli Center on Intelligent Systems（科利智能系统中心）；International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）
Curriculum Learning (CL) is the idea that learning on a training set sequenced or ordered in a manner where samples range from easy to difficult, results in an increment in performance over otherwise random ordering. The idea parallels cognitive science's theory of how human brains learn, and that learning a difficult task can be made easier by phrasing it as a sequence of easy to difficult tasks. This idea has gained a lot of traction in machine learning and image processing for a while and recently in Natural Language Processing (NLP). In this paper, we apply the ideas of curriculum learning, driven by SentiWordNet in a sentiment analysis setting. In this setting, given a text segment, our aim is to extract its sentiment or polarity. SentiWordNet is a lexical resource with sentiment polarity annotations. By comparing performance with other curriculum strategies and with no curriculum, the effectiveness of the proposed strategy is presented. Convolutional, Recurrence, and Attention-based architectures are employed to assess this improvement. The models are evaluated on a standard sentiment dataset, Stanford Sentiment Treebank.
Trento RISE（特伦托RISE）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
Assigning a positive or negative score to a word out of context (i.e. a word's prior polarity) is a challenging task for sentiment analysis. In the literature, various approaches based on SentiWordNet have been proposed. In this paper, we compare the most often used techniques together with newly proposed ones and incorporate all of them in a learning framework to see whether blending them can further improve the estimation of prior polarity scores. Using two different versions of SentiWordNet and testing regression and classification models across tasks and datasets, our learning approach con…
Expanding Vietnamese SentiWordNet to Improve Performance of Vietnamese Sentiment Analysis Models
University of Engineering and Technology, Vietnam National University（越南国家大学工程技术大学）；University of Economic and Technical Industries（经济技术工业大学）；Hanoi University of Public Health（河内公共卫生大学）
Vidyavardhaka College of Engg.（维迪亚瓦尔达卡工程学院）；Government Engineering College, Hassan（哈桑政府工程学院）
The task of sentiment analysis of reviews is carried out using manually built / automatically generated lexicon resources of their own with which terms are matched with lexicon to compute the term count for positive and negative polarity. On the other hand the Sentiwordnet, which is quite different from other lexicon resources that gives scores (weights) of the positive and negative polarity for each word. The polarity of a word namely positive, negative and neutral have the score ranging between 0 to 1 indicates the strength/weight of the word with that sentiment orientation. In this paper, w…
This paper reports about our work in the NLP Tool Contest @ICON-2017, shared task on Sentiment Analysis for Indian Languages (SAIL) (code mixed). To implement our system, we have used a machine learning algo-rithm called Multinomial Naïve Bayes trained using n-gram and SentiWordnet features. We have also used a small SentiWordnet for English and a small SentiWordnet for Bengali. But we have not used any SentiWordnet for Hindi language. We have tested our system on Hindi-English and Bengali-English code mixed social media data sets released for the contest. The performance of our system is very…
Deriving prior polarity lexica for sentiment analysis - where positive or negative scores are associated with words out of context - is a challenging task. Usually, a trade-off between precision and coverage is hard to find, and it depends on the methodology used to build the lexicon. Manually annotated lexica provide a high precision but lack in coverage, whereas automatic derivation from pre-existing knowledge guarantees high coverage at the cost of a lower precision. Since the automatic derivation of prior polarities is less time consuming than manual annotation, there has been a great bloo…
Most of the existing pre-trained language representation models neglect to consider the linguistic knowledge of texts, which can promote language understanding in NLP tasks. To benefit the downstream tasks in sentiment analysis, we propose a novel language representation model called SentiLARE, which introduces word-level linguistic knowledge including part-of-speech tag and sentiment polarity (inferred from SentiWordNet) into pre-trained models. We first propose a context-aware sentiment attention mechanism to acquire the sentiment polarity of each word with its part-of-speech tag by querying…
SentiWordNet is an important lexical resource supporting sentiment analysis in opinion mining applications. In this paper, we propose a novel approach to construct a Vietnamese SentiWordNet (VSWN). SentiWordNet is typically generated from WordNet in which each synset has numerical scores to indicate its opinion polarities. Many previous studies obtained these scores by applying a machine learning method to WordNet. However, Vietnamese WordNet is not available unfortunately by the time of this paper. Therefore, we propose a method to construct VSWN from a Vietnamese dictionary, not from WordNet…
Sarcasm is considered one of the most difficult problem in sentiment analysis. In our ob-servation on Indonesian social media, for cer-tain topics, people tend to criticize something using sarcasm. Here, we proposed two additional features to detect sarcasm after a common sentiment analysis is conducted. The features are the negativity information and the number of interjection words. We also employed translated SentiWordNet in the sentiment classification. All the classifications were conducted with machine learning algorithms. The experimental results showed that the additional features are …
Many approaches to sentiment analysis rely on lexica where words are tagged with their prior polarity - i.e. if a word out of context evokes something positive or something negative. In particular, broad-coverage resources like SentiWordNet provide polarities for (almost) every word. Since words can have multiple senses, we address the problem of how to compute the prior polarity of a word starting from the polarity of each sense and returning its polarity strength as an index between -1 and 1. We compare 14 such formulae that appear in the literature, and assess which one best approximates th…
Language Technologies Research Center（语言技术研究中心）；International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）
The presented work aims at generating a systematically annotated corpus that can support the enhancement of sentiment analysis tasks in Telugu using word-level sentiment annotations. From OntoSenseNet, we extracted 11,000 adjectives, 253 adverbs, 8483 verbs and sentiment annotation is being done by language experts. We discuss the methodology followed for the polarity annotations and validate the developed resource. This work aims at developing a benchmark corpus, as an extension to SentiWordNet, and baseline accuracy for a model where lexeme annotations are applied for sentiment predictions. …
International Institute of Information Technology - Hyderabad（印度海得拉巴国际信息技术学院）
While Curriculum Learning (CL) has recently gained traction in Natural language Processing Tasks, it is still not adequately analyzed. Previous works only show their effectiveness but fail short to explain and interpret the internal workings fully. In this paper, we analyze curriculum learning in sentiment analysis along multiple axes. Some of these axes have been proposed by earlier works that need more in-depth study. Such analysis requires understanding where curriculum learning works and where it does not. Our axes of analysis include Task difficulty on CL, comparing CL pacing techniques, …
University of Ottawa（渥太华大学）；Dalhousie University（达尔豪斯大学）
In this study, we explored application of Word2Vec and Doc2Vec for sentiment analysis of clinical discharge summaries. We applied unsupervised learning since the data sets did not have sentiment annotations. Note that unsupervised learning is a more realistic scenario than supervised learning which requires an access to a training set of sentiment-annotated data. We aim to detect if there exists any underlying bias towards or against a certain disease. We used SentiWordNet to establish a gold sentiment standard for the data sets and evaluate performance of Word2Vec and Doc2Vec methods. We have…
Sentiment Analysis and other semantic tasks are commonly used for social media textual analysis to gauge public opinion and make sense from the noise on social media. The language used on social media not only commonly diverges from the formal language, but is compounded by codemixing between languages, especially in large multilingual societies like India. Traditional methods for learning semantic NLP tasks have long relied on end to end task specific training, requiring expensive data creation process, even more so for deep learning methods. This challenge is even more severe for resource sc…
M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）
Extensible Multi-Granularity Fusion Network and Transferable Curriculum Learning for Aspect-based Sentiment Analysis
School of Software Technology, Dalian University of Technology（大连理工大学软件学院）；Graduate School of Information, Production and Systems, Waseda University（早稻田大学信息生产与系统研究生学校）
Institute of Computing and Information Technology, Gomal University（戈马尔大学计算与信息技术学院）
Rapid increase in internet users along with growing power of online review sites and social media has given birth to sentiment analysis or opinion mining, which aims at determining what other people think and comment. Sentiments or Opinions contain public generated content about products, services, policies and politics. People are usually interested to seek positive and negative opinions containing likes and dislikes, shared by users for features of particular product or service. This paper proposed sentence-level lexical based domain independent sentiment classification method for different …
Samsung R&D Institute India - Bangalore（三星印度研发中心-班加罗尔）
Elastic Weight Consolidation (EWC) is a technique used in overcoming catastrophic forgetting between successive tasks trained on a neural network. We use this phenomenon of information sharing between tasks for domain adaptation. Training data for tasks such as sentiment analysis (SA) may not be fairly represented across multiple domains. Domain Adaptation (DA) aims to build algorithms that leverage information from source domains to facilitate performance on an unseen target domain. We propose a model-independent framework - Sequential Domain Adaptation (SDA). SDA draws on EWC for training on…
Curriculum Learning emphasizes the order of training instances in a computational learning setup. The core hypothesis is that simpler instances should be learned early as building blocks to learn more complex ones. Despite its usefulness, it is still unknown how exactly the internal representation of models are affected by curriculum learning. In this paper, we study the effect of curriculum learning on Long Short-Term Memory (LSTM) networks, which have shown strong competency in many Natural Language Processing (NLP) problems. Our experiments on sentiment analysis task and a synthetic task si…
University of California, Berkeley（加州大学伯克利分校）；Nankai University（南开大学）；Massachusetts Institute of Technology（麻省理工学院）；Didi Chuxing（滴滴出行）
Sentiment analysis of user-generated reviews or comments on products and services in social networks can help enterprises to analyze the feedback from customers and take corresponding actions for improvement. To mitigate large-scale annotations on the target domain, domain adaptation (DA) provides an alternate solution by learning a transferable model from other labeled source domains. Existing multi-source domain adaptation (MDA) methods either fail to extract some discriminative features in the target domain that are related to sentiment, neglect the correlations of different sources and the…
