RST-style discourse parsing plays a vital role in many NLP tasks, revealing the underlying semantic/pragmatic structure of potentially complex and diverse documents. Despite its importance, one of the most prevailing limitations in modern day discourse parsing is the lack of large-scale datasets. To overcome the data sparsity issue, distantly supervised approaches from tasks like sentiment analysis and summarization have been recently proposed. Here, we extend this line of research by exploiting distant supervision from topic segmentation, which can arguably provide a strong and oftentimes complementary signal for high-level discourse structures. Experiments on two human-annotated discourse treebanks confirm that our proposal generates accurate tree structures on sentence and paragraph level, consistently outperforming previous distantly supervised models on the sentence-to-document task and occasionally reaching even higher scores on the sentence-to-paragraph level.

This posts describes, along with Python code, an analysis of the readers' comments open dataset from Rome's libraries made publicly available by "Istituzione Biblioteche di Roma"¹. The analysis leverages topic modeling techniques to find recurring topics among readers' comments, and thus determine, by inference, the themes of the borrowed books and the interests of the readers. Moreover, sentiment analysis is performed to determine whether customers comments are positive or negative. Finally, readers data (age and occupation) are used to achieve customers segmentation via clustering techniques. This provides insights on the topics of borrowed books, the readers sentiment and different readers clusters.

Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest for efficiency. While showing strong performance on some generation tasks, they don't generalize across all generation tasks. In this work, we show that prompt based conditional text generation can be improved with simple and efficient methods that simulate modeling the discourse structure of human written text. We introduce two key design choices: First we show that a higher-level discourse structure of human written text can be modelled with \textit{hierarchical blocking} on prefix parameters that enable spanning different parts of the input and output text and yield more coherent output generations. Second, we propose sparse prefix tuning by introducing \textit{attention sparsity} on the prefix parameters at different layers of the network and learn sparse transformations on the softmax-function, respectively. We find that sparse attention enables the prefix-tuning to better control of the input contents (salient facts) yielding more efficient tuning of the prefix-parameters. Experiments on a wide-variety of text generation tasks show that structured design of prefix parameters can achieve comparable results to fine-tuning all parameters while outperforming standard prefix-tuning on all generation tasks even in low-resource settings.

Sentiment analysis is a methodology for analysing text data and classifying the sentiment contained within it. It is a useful technique for every customer facing industry (retail, finance, telco, utilities, etc) which needs to understand how consumers are thinking about them and their products, features and services. Sentiment analysis is a key feature in understanding and predicting churn, developing more accurate customer segmentations and creating recommender systems which have a good take-up of product and service offerings. Today, organisations have access to vast amounts of digital data from multiple platforms, including social media, review platforms, chatbots and influencer marketing campaigns, as well as internal CRM and Enterprise Marketing Systems. This heterogeneous data environment means that multiple types of sentiment model may be needed to truly understand customers, with different models used for understanding emotions, opinions, future intent or what aspects of a product or service are liked or disliked.

In media news today, CNN and Chris Cuomo issue scathing statements against each other, the former anchor announces he's leaving his SiriusXM radio show, and a New York Times op-ed gets mocked for fearing free library is contributing to gentrification. Pollster Nate Silver on Monday savaged the analytics behind a recent Washington Post column claiming President Biden was being treated just as badly, or worse, by the media than former President Trump. In the piece published last week, liberal columnist Dana Milbank complained about Biden's media coverage being overly tough and implored journalists to do "soul-searching" and "think about what it is we're delivering to people." In a series of tweets, Silver argued the piece's "sentiment analysis" measuring the positivity and negativity of particular articles written about Trump and Biden was "complete crap," and gave examples to show how the data could be skewed more positively or negatively than it should have been. "To this good thread explaining why the'sentiment analysis' cited in the [Dana Milbank] WaPo article this weekend is complete crap--the analysis was used to make the claim that the press is just negative toward Biden as Trump--I'll also add a couple of comments based on their data," Silver wrote.

Sentiment analysis of free-text documents is a common task in the field of text mining. In sentiment analysis predefined sentiment labels, such as "positive" or "negative" are assigned to texts. Texts (here called documents) can be reviews about products or movies, articles, tweets, etc. In this article, we show you how to assign predefined sentiment labels to documents, using the KNIME Text Processing extension in combination with traditional KNIME learner and predictor nodes. A set of 2000 documents has been sampled from the training set of the Large Movie Review Dataset v1.0.

We propose a UNITER(Chen et al. 2020)-based model for The goal of Situated and Interactive Multimodal Conversation SIMMC 2.0. UNITER is proposed in computer vision (CV) (SIMMC) 2.0 (Kottur et al. 2021) is to aid the conversational for universal embeddings for image and text. To achieve this AI community in developing successful multimodal goal, UNITER is pre-trained with masked language modelling, assistant agents capable of handling real-world multimodal masked region modelling and word-region alignment dialog inputs.

Rep. Elise Stefanik, R-NY, reacts to the former CNN anchor being fired over his role in former Gov. Andrew Cuomo's sexual harassment scandal. White House chief of staff Ronald Klain confused readers Sunday as he promoted a Washington Post op-ed that argued President Biden gets worse media treatment than his predecessor, former President Trump, whose verbal duels with the press were weekly staples during his four-year residency at 1600 Penn. "For your consideration," Klain tweeted with a link to the op-ed from Dana Millbank, titled, "The media treats Biden as badly as - or worse than - Trump. WHITE HOUSE'S RON KLAIN PANNED FOR RETWEETING POST ON'ULTIMATE WORK AROUND' FOR FEDERAL VACCINE MANDATE Millbank's "proof" was research from Forge.ai, a data analytics unit of the information company FiscalNote. The study used algorithms focused on adjectives and their placement in articles - more than 200,000 of them - to rate the coverage Biden received in the first 11 months of 2021 and the coverage Trump got in the first 11 months of 2020. The process was referred to as "sentiment analysis." "My colleagues in the media are serving as accessories to the murder of democracy," Millbank said. "Too many journalists are caught in a mindless neutrality between democracy and its saboteurs, between fact and fiction.

This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks. Although some CL techniques have been proposed for document sentiment classification, we are not aware of any CL work on ASC. A CL system that incrementally learns a sequence of ASC tasks should address the following two issues: (1) transfer knowledge learned from previous tasks to the new task to help it learn a better model, and (2) maintain the performance of the models for previous tasks so that they are not forgotten. This paper proposes a novel capsule network based model called B-CL to address these issues. B-CL markedly improves the ASC performance on both the new task and the old tasks via forward and backward knowledge transfer. The effectiveness of B-CL is demonstrated through extensive experiments.

This paper studies continual learning (CL) of a sequence of aspect sentiment classification(ASC) tasks in a particular CL setting called domain incremental learning (DIL). Each task is from a different domain or product. The DIL setting is particularly suited to ASC because in testing the system needs not know the task/domain to which the test data belongs. To our knowledge, this setting has not been studied before for ASC. This paper proposes a novel model called CLASSIC. The key novelty is a contrastive continual learning method that enables both knowledge transfer across tasks and knowledge distillation from old tasks to the new task, which eliminates the need for task ids in testing. Experimental results show the high effectiveness of CLASSIC.