It's absolutely divine! Can fine-grained sentiment analysis benefit from coreference resolution?

Opinion Mining and Sentiment Analysis in Natural Language Processing (NLP) are challenging, as they require deep understanding. Understanding involves methods that could differentiate between the facts of explicit and implicit, regular and irregular, syntactical and semantic language rules. Researches oriented towards Natural Language Processing and Sentiment Analysis have many unresolved problems like co-reference resolution, negation handling, anaphora resolution, named-entity recognition, and word-sense disambiguation. This paper is proposed to develop an Optimized Partial Ancestral Graph (O-PAG) which is capable of mining patterns in human interactions and compare it with an existing tree based pattern mining approach. The experimental results are exposed to number of frequent interactions made and execution time. Results indicate that the overall performance can reach considerable improvements on using O-PAG approach.

Cybersecurity Knowledge Graph (CKG) has become an important structure to address the current cybersecurity crises and challenges, due to its powerful ability to model, mine, and leverage massive security intelligence data. To construct a comprehensive and explicit CKG with low redundancy, coreference resolution (CR) plays a crucial role as the core step in knowledge fusion. Although the research on coreference resolution techniques in Natural Language Processing (NLP) field has made notable achievements, there is still a great gap in the cybersecurity field. Therefore, the paper first investigates the effectiveness of the existing CR models on cybersecurity corpus and presents CyberCoref, an end-to-end coreference resolution model for cybersecurity entities. We propose an entity type prediction network that not only helps to improve mention representations and provide type consistency checks, but also enables the model to distinguish the coreference among different entity types and thus run the coreference resolution more granular. To overcome the problem of implicit contextual modeling adopted by the existing CR models, we innovative propose an explicit contextual modeling method for the coreference resolution task based on semantic text matching. Finally, we improve the span representation by introducing lexical and syntactic features. The experimental results demonstrate that CyberCoref improves the F1 values on the cybersecurity corpus by 6.9% compared to existing CR models.KeywordsCoreference resolutionSecurity intelligenceSemantic text matchingEntity type

The plethora of online reviews available on the internet has great insights about various products or entities. However, selecting or recommending a product by sifting through these reviews is a tedious and time consuming task. Sentiment analysis of such reviews helps understand the pros or cons of the product. In recent years researchers and industry people have leveraged such reviews to rank or recommend the products to new users. Ranking or recommending products using text reviews is a challenging task. In this study, we propose a framework to get a ranking of products using aspect-based sentiment analysis (ABSA). ABSA is a fine-grained sentiment analysis task that is useful for extracting opinions about the different aspects of a product. To facilitate automated ABSA, a novel approach for aspect sentiment classification is proposed in this study. Further to rank the products based on aspect-specific performance, a framework is developed using Multi-criteria decision-making (MCDM) techniques. A case study is performed in the automobile domain to rank various cars using the ABSA approach. To validate the effectiveness of the proposed approach, the ranking results are compared with the numeric ratings available for various aspects of the car. The experimental results show that the ranking obtained by the proposed approach matches the numerical ratings. Therefore, the car selection problem or recommendation of cars in the automobile domain can be effectively handled using the proposed framework.

With the accelerated evolution of social networks, there is a tremendous increase in opinions by the people about products or services. While this user-generated content in natural language is intended to be valuable, its large amounts require use of content mining methods and NLP to uncover the knowledge for various tasks. In this study, sentiment analysis is used to analyze and understand the opinions of users using statistical approaches, knowledge-based approaches, hybrid approaches, and concept-based ontologies. Unfortunately, sentiment analysis also experiences a range of difficulties like colloquial words, negation handling, ambiguity in word sense, coreference resolution, which highlight another perspective emphasizing that sentiment analysis is certainly a restricted NLP problem. The purpose of this chapter is to discover how sentiment analysis is a restricted NLP problem. Thus, this chapter discussed the concept of sentiment analysis in the field of NLP and explored that sentiment analysis is a restricted NLP problem due to the sophisticated nature of natural language.

We focus on automatic coreference resolution for blogs and news articles with user comments as part of a project on opinion mining. We aim to study the effect of the genre shift from edited, structured newspaper text to unedited, unstructured blog data. We compare our coreference resolution system on three data sets: newspaper articles, mixed newspaper articles and reader comments, and blog data. As can be expected the performance of the automatic coreference resolution system drops drastically when tested on unedited text. We describe the characteristics of the different data sets and we examine the typical errors made by the resolution system.

The detection of coreferent pairs within a text is one of the basic tasks in the area of natural language processing (NLP). The state‑ of‑ the‑ art methods of coreference resolution are based on machine learning algorithms. The key idea of the methods is to detect certain regularities between the semantic or grammatical features of text entities. In the paper, the comparative analysis of current methods of coreference resolution in English and Ukrainian texts has been performed. The key disadvantage of many methods consists in the interpretation of coreference resolution as a classification problem. The result of coreferent pairs detection is the set of groups in which elements refer to a common entity. Therefore it is advisable to consider the coreference resolution as a clusterization task. The method of coreference resolution using the set of filtering sieves and a convolutional neural network has been suggested. The set of filtering sieves to find candidates for coreferent pairs formation has been implemented. The training process of a multichannel convolutional neural network on a marked Ukrainian corpus has been performed. The usage of a multichannel structure allows analyzing of the different components of text units: semantic, lexical, and grammatical features of words and sentences. Furthermore, it is possible to process input data with unfixed size (words or sentences of a text) using a convolutional layer. The output result of the method is the set of clusters. In order to form clusters, it is necessary to take into account the previous steps of the model’s workflow. Nevertheless, such an approach contradicts the traditional methodology of machine learning. Thus, the training process of the network has been performed using the SEARN algorithm that allows the solving of tasks with unfixed output structures using a classifier model. An experimental examination of the method on the corpus of Ukrainian news has been performed. In order to estimate the accuracy of the method the corresponding common metrics for clusterization tasks have been calculated. The results obtained can indicate that the suggested method can be used to find coreferent pairs within Ukrainian texts. The method can be also easily adapted and applied to other natural languages.

We present preliminary results on investigating the benefits of coreference resolution features for neural RST discourse parsing by considering different levels of coupling of the discourse parser with the coreference resolver. In particular, starting with a strong baseline neural parser unaware of any coreference information, we compare a parser which utilizes only the output of a neural coreference resolver, with a more sophisticated model, where discourse parsing and coreference resolution are jointly learned in a neural multitask fashion. Results indicate that these initial attempts to incorporate coreference information do not boost the performance of discourse parsing in a statistically significant way.

Semantics perception and refinement network for aspect-based sentiment analysis

Coreference resolution is targeted at collecting all mentions of an entity within a text into a single cluster. Various approaches for this task have already been proposed but the problem is still challenging. RU-EVAL-2014, an evaluation of anaphora and coreference resolution, renewed interest for this task for the Russian language. We try to follow this trend; our work can be viewed as an extension to recent approaches. Thorough manual feature engineering allows us to significantly improve current state-of-the-art results. Additionally, we compare applicability of various clustering algorithms to building coreference groups. That is essentially the second part of the approach.

Sentiment Analysis is a method to identify, extract, and quantify people's feelings, opinions, or attitudes. The wealth of online data motivates organizations to keep tabs on customers' opinions and feelings by turning to sentiment analysis tasks. Along with the sentiment analysis, the emotion analysis of written reviews is also essential to improve customer satisfaction with restaurant service. Due to the availability of massive online data, various computerized methods are proposed in the literature to decipher text sentiments. The majority of current methods rely on machine learning, which necessitates the pre-training of large datasets and incurs substantial space and time complexity. To address this issue, we propose a novel unsupervised sentiment classification model. This study presents an unsupervised mathematical optimization framework to perform sentiment and emotion analysis of reviews. The proposed model performs two tasks. First, it identifies a review's positive and negative sentiment polarities, and second, it determines customer satisfaction as either satisfactory or unsatisfactory based on a review. The framework consists of two stages. In the first stage, each review's context, rating, and emotion scores are combined to generate performance scores. In the second stage, we apply a non-cooperative game on performance scores and achieve Nash Equilibrium. The output from this step is the deduced sentiment of the review and the customer's satisfaction feedback. The experiments were performed on two restaurant review datasets and achieved state-of-the-art results. We validated and established the significance of the results through statistical analysis. The proposed model is domain and language-independent. The proposed model ensures rational and consistent results.

To analyze public perceptions of over-the-counter (OTC) hearing aids through sentiment and thematic analysis of online consumer reviews and their changes over time. Sentiment and thematic analysis. Online reviews from third-party and product websites. All English online consumer reviews posted between 2016 and 2024 for OTC hearing aids (83 models) were recorded (n = 21,727). Sentiment analysis was performed using Valence Aware Dictionary and Sentiment Reasoner (VADER), a rule-based sentiment analysis tool incorporating natural language processing. VADER provides scores for each review ranging from -1 (most negative), 0 (neutral), to 1 (most positive). Additional thematic analysis was performed for the top 100 most positive, neutral, and negative reviews (n = 300). Overall, mean (SD) VADER sentiment score of online reviews was generally positive at 0.587 (0.411). Multivariable regression analysis showed that higher VADER scores were associated with higher-priced and behind-the-ear (BTE) type hearing aids. Although there was a significant increase in a number of reviews after the Food and Drug Administration's new establishment of the OTC hearing aid category in 2022, the mean sentiment scores slightly decreased (β =-.10, [95%CI: -0.12 to -0.09]). Thematic analysis revealed that positive sentiments highlighted the affordability and time-saving benefits of OTC hearing aids as alternatives to prescription models. Negative sentiments centered on sound quality, challenges with customer service, and inadequate amplification for those with severe hearing loss. Customers generally viewed OTC hearing aids positively, while mixed experiences were present. When used as indicated for adults with mild to moderate hearing loss, OTC hearing aids may offer a viable alternative to prescription devices, improving accessibility and affordability.

In coreference resolution, span representations play a key role to predict coreference links accurately. We present a thorough examination of the span representation derived by applying BERT on coreference resolution (Joshi et al., 2019) using a probing model. Our results show that the span representation is able to encode a significant amount of coreference information. In addition, we find that the head-finding attention mechanism involved in creating the spans is crucial in encoding coreference knowledge. Last, our analysis shows that the span representation cannot capture non-local coreference as efficiently as local coreference.

In this paper we present our first attempt on anaphora resolution for a resource poor language, namely Bengali. We address the issue of adapting a state-of-the-art system, BART, which was originally developed for English. Overall performance of co-reference resolution greatly depends on the high accurate mention detectors. We develop a number of models based on the heuristics used as well as on the particular machine learning employed. Thereafter we perform a series of experiments for adapting BART for Bengali. Our evaluation shows, a language-dependant system (designed primarily for English) can achieve a good performance level when re-trained and tested on a new language with proper subsets of features. The system produces the recall, precision and F-measure values of 56.00%, 46.50% and 50.80%, respectively. The contribution of this work is two-fold, viz. (i). attempt to build a machine learning based anaphora resolution system for a resource-poor Indian language; and (ii). domain adaptation of a state-of-the-art English co-reference resolution system for Bengali, which has completely different orthography and characteristics.

Under statistical learning framework, the paper focuses on how to use traditional linguistic findings on anaphora resolution as a guide for mining and organizing contextual features for Chinese co-reference resolution. The main achievements are as follows. (1) In order to simulate "syntactic and semantic parallelism factor", we extract "bags of word form and POS" feature and "bag of semes" feature from the contexts of the entity mentions and incorporate them into the baseline feature set. (2) Because it is too coarse to use the feature of bags of word form, POS tag and seme to determine the syntactic and semantic parallelism between two entity mentions, we propose a method for contextual feature reconstruction based on semantic similarity computation, in order that the reconstructed contextual features could better approximate the anaphora resolution factor of "Syntactic and Semantic Parallelism Preferences". (3) We use an entity-mention-based contextual feature representation instead of isolated word-based contextual feature representation, and expand the size of the contextual windows in addition, in order to approximately simulate "the selectional restriction factor" for anaphora resolution. The experiments show that the multi-level contextual features are useful for co-reference resolution, and the statistical system incorporated with these features performs well on the standard ACE datasets.

In the modern information society, there is an ever-growing need for improved natural language processing and human language technologies.This book presents the proceedings of the Sixth International Conference 'Human Language Technologies The Baltic Perspective' (Baltic HLT 2014) held in Kaunas, Lithuania in September 2014. The Baltic HLT conferences provide an important forum for gathering and consolidating ideas, and are an opportunity for the Baltic countries to present important research results to an international audience. The book contains 39 long and short papers presented at the conference. These cover a wide range of topics: syntactic analysis, sentiment analysis, co-reference resolution, authorship attribution, information extraction, document clustering, machine translation, corpus and parallel corpus compiling, speech recognition, synthesis and others. The book is divided into three main sections: speech technology, methods in computational linguistics, and preparation of language resources. This book will be of interest to anyone whose work involves the use and application of computational linguistics and related disciplines.