USFD at SemEval-2016 - Stance Detection on Twitter with Autoencoders

Jun 13, 20161 like1,044 views

This paper describes the University of Sheffield's submission to the SemEval 2016 Twitter Stance Detection weakly supervised task (SemEval 2016 Task 6, Subtask B). In stance detection, the goal is to classify the stance of a tweet towards a target as "favor", "against", or "none". In Subtask B, the targets in the test data are different from the targets in the training data, thus rendering the task more challenging but also more realistic. To address the lack of target-specific training data, we use a large set of unlabelled tweets containing all targets and train a bag-of-words autoencoder to learn how to produce feature representations of tweets. These feature representations are then used to train a logistic regression classifier on labelled tweets, with additional features such as an indicator of whether the target is contained in the tweet. Our submitted run on the test data achieved an F1 of 0.3270. Paper: http://isabelleaugenstein.github.io/papers/SemEval2016-Stance.pdf

$Isabelle Augenstein, Andreas Vlachos, Kalina Bontcheva i.augenstein@ucl.ac.uk, {a.vlachos | k.bontcheva}@sheffield.ac.uk USFD at SemEval-2016 Task 6: Any-Target Stance Detection on Twitter with Autoencoders Stance Detection Subtask B Classify attitude of tweet towards target as “favor”, “against”, “none” Tweet: “No more Hillary Clinton” Target: Donald Trump Stance: FAVOR Subtask A training targets: Climate Change is a Real Concern, Feminist Movement, Atheism, Legalization of Abortion, Hillary Clinton Subtask B testing target: Donald Trump Challenges •  Labelled data not available for the test target •  Manual labelling of training data not allowed •  Target does not always appear in tweet Feature Extraction •  Aut-twe: Tweet auto-encoded tweet,100d feature vector •  targetInTweet: is (shortened) target contained in tweet •  Good indicator for non-neutral stance •  Other features tested (not used for final run): WordNet- Affect gazetteers, emoticon detection •  Baselines: bag of word, word2vec (trained on same data as autoencoder) Results Model Comparison (Hillary Clinton, dev) Model Comparison (Donald Trump, test) 0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 Macro F1 BoW BoW+inTwe Word2Vec Aut-twe Aut-twe+inTwe Conclusions •  It is important to detect if the target is mentioned in the tweet •  Hillary Clinton: 0.4538 F1 (inTwe) vs 0.3243 F1 (not inTwe) •  Donald Trump: 0.3745 F1 (inTwe) vs 0.2377 F1 (not inTwe) •  Autoencoder can help to detect stance towards unseen targets •  Developing method for new targets without labelled training data is challenging - discrepancies between what works for dev vs. test set •  Future work: better incorporate the target for stance detection Acknowledgements This work was partially supported by the European Union, grant agreement No. 611233 PHEME (http://www.pheme.eu) Data •  5 628 labelled train tweets about Subtask A targets •  1 278 about Hillary Clinton, used for dev •  278 013 unlabelled Donald Trump tweets •  395 212 collected unlabelled tweets about all targets •  Keywords: hillary, clinton, trump, climate, femini, aborti •  707 Donald Trump test tweets Preprocessing •  Phrase detection: Train phrase detection model on unlabelled +labelled tweets, e.g. “donald”, “trump” → “donald trump” Autoencoder •  Bag-of-word autoencoder, using 50 000 most frequent words •  trained on unlabelled+labelled tweets •  Input vector: dimensionality 50 000. For each word in vocabulary, does tweet contain the word or not •  One hidden layer (size 100), output size 100 •  Trained encoder is applied to labelled train and test data to obtain 100d features, decoder not used Model Macro F1 Majority class (oﬃcial) 0.2972 SVM n-grams (oﬃcial) 0.2843 BoW 0.3453 Aut-twe (submi6ed) 0.3307 References •  Code: https://github.com/sheffieldnlp/stance-semeval2016 •  Phrases: Mikolov et al. (2013). Distributed Representations of Words and Phrases and Their Compositionality. NIPS. Tweets “No more Hillary Clinton”, “Donald Trump”, “FAVOR” Preprocessing: [“No”, “more”, “Hillary_Clinton”] Autoencoder Training [america: 0, …, Hillary_Clinton: 1] 50 000d input [0, 0, …, 1] 100d hidden layer [0, 1, …, 1] 100d output layer Feature Extraction Autoencoder inTwe [0, 1, …, 1] 0 Logistic Regression Model Predictions “#voteTrump (…)”, “Donald Trump”, “FAVOR” “youre fired (…)” “Donald Trump”, “AGAINST”$

Presentation of work that will be published at EMNLP 2016. Ben Eisner, Tim Rocktäschel, Isabelle Augenstein, Matko Bošnjak, Sebastian Riedel. emoji2vec: Learning Emoji Representations from their Description. SocialNLP at EMNLP 2016. https://arxiv.org/abs/1609.08359 Georgios Spithourakis, Isabelle Augenstein, Sebastian Riedel. Numerically Grounded Language Models for Semantic Error Correction. EMNLP 2016. https://arxiv.org/abs/1608.04147 Isabelle Augenstein, Tim Rocktäschel, Andreas Vlachos, Kalina Bontcheva. Stance Detection with Bidirectional Conditional Encoding. EMNLP 2016. https://arxiv.org/abs/1606.05464

Lodifier: Generating Linked Data from Unstructured TextIsabelle Augenstein

Seed Selection for Distantly Supervised Web-Based Relation ExtractionIsabelle Augenstein

Distant Supervision with Imitation LearningIsabelle Augenstein

Imitation learning is used to address the problem of distant supervision for relation extraction. It decomposes the task into named entity classification (NEC) and relation extraction (RE), allowing the models to be trained separately. Through an iterative process, imitation learning is able to learn the dependencies between NEC and RE even when only labels for RE are provided. This overcomes limitations of prior approaches that rely on distantly labeled data. Evaluation shows the approach improves over baselines by leveraging multi-stage modeling to compensate for mistakes at the NEC stage.

Relation Extraction from the Web using Distant SupervisionIsabelle Augenstein

This paper proposes using distant supervision to extract relations from web text to populate knowledge bases without requiring manual effort. It does this by using an existing knowledge base to automatically label sentences with entity relations, training a classifier on this distant supervision data. The paper describes using statistical methods to select better training data and discard noisy examples, and shows this improves precision. It also introduces methods for integrating information across sentences which improves both precision and recall of extracted relations.

Semantic Search tutorial at SemTech 2012Peter Mika

This document provides an introduction to a semantic search tutorial given by Peter Mika and Tran Duc Thanh. The agenda covers semantic web data, including the RDF data model and publishing RDF data. It also covers query processing, ranking, result presentation, evaluation, and a question period. The document discusses why semantic search is needed to address poorly solved queries and enable novel search tasks using structured data and background knowledge.

Mapping Keywords to Isabelle Augenstein

The document presents a method for mapping keywords to linked data resources for automatic query expansion. It aims to address challenges like spelling mistakes, synonyms, and lexical variations. The method learns an expanded set of keywords and ranks them by identifying concepts through labeling properties within the dataset. It was evaluated on DBpedia and showed an improvement over state-of-the-art methods, achieving a 17% increase in mean reciprocal rank. Future work is discussed to integrate multiple strategies and fine-tune the approach.

Human Neural MachineGeorgios Spithourakis

The document summarizes an experiment using human participants to simulate the functions of a neural network. The participants worked together to encode an image by describing its elements, then generated a poem by collectively proposing and voting on words and phrases. This process aimed to demonstrate how machines encode and generate text from images. The experiment showed the participants taking turns proposing words or phrases to build a poem corresponding to several different encoded images. In the conclusion, the author acknowledges contributions from researchers in the field of neural networks and natural language processing.

Question Answering over Linked Data (Reasoning Web Summer School)Andre Freitas

Information Extraction with Linked DataIsabelle Augenstein

Natural Language Processing for the Semantic WebIsabelle Augenstein

Lecture: Question AnsweringMarina Santini

Semantic Search Over The Webalierkan

This document discusses semantic search over the web. It begins by introducing semantic search and how it aims to improve search accuracy by understanding context. It then discusses several technologies used to publish structured data on the web, including Resource Description Framework (RDF), Microformats, RDFa, Microdata, and Linked Data. It also covers challenges like semantic heterogeneity and data quality when dealing with structured data on the web. Finally, it discusses approaches to storing and indexing structured RDF data, including relational and entity-based perspectives.

Management information system question and answerspradeep acharya

This document discusses management information systems and related topics. It covers external forces like competition and internal factors like the need for knowledge-intensive work that are driving changes in information systems. It also discusses the components of information systems, including input/output processes and data processing. Steps in the system development life cycle are outlined. The advantages and disadvantages of enterprise resource planning systems are listed. The distinction between system software and application software is explained. Network security defenses like firewalls and their role in protecting information are described.

Deep Learning Models for Question AnsweringSujit Pal

This document discusses deep learning models for question answering. It provides an overview of common deep learning building blocks such as fully connected networks, word embeddings, convolutional neural networks and recurrent neural networks. It then summarizes the authors' experiments using these techniques on benchmark question answering datasets like bAbI and a Kaggle science question dataset. Their best model achieved an accuracy of 76.27% by incorporating custom word embeddings trained on external knowledge sources. The authors discuss future work including trying additional models and deploying the trained systems.

Intro to Deep Learning for Question AnsweringTraian Rebedea

Talent Sourcing and Matching - Artificial Intelligence and Black Box Semantic...Glen Cathey

A deep dive into resume and LinkedIn sourcing and matching solutions claiming to use artificial intelligence, semantic search, and NLP, including how they work, their pros, cons, and limitations, and examples of what sourcers and recruiters can do that even the most advanced automated search and match algorithms can't do. Topics covered include human capital data information retrieval and analysis (HCDIR & A), Boolean and extended Boolean, semantic search, dynamic inference, dark matter resumes and social network profiles, and what I believe to be the ideal resume search and matching solution.

Web 3.0 The Semantic WebHatem Mahmoud

The document discusses the Semantic Web as Web 3.0. It explains that while current web pages use HTML to describe structure, not meaning, the Semantic Web aims to allow computers to understand the meaning behind information by recognizing things like people, places, events. This is done through techniques like embedding semantic annotations directly into data using standards like RDFa, microformats, and querying data with SPARQL. The Semantic Web will enable new applications by making the web more machine-readable.

Beyond Fact Checking — Modelling Information Change in Scientific CommunicationIsabelle Augenstein

The document discusses modelling information change in scientific communication. It begins by noting how science is often communicated through journalists to the public, and how the message can change and become exaggerated or misleading along the way. It then discusses developing models to detect exaggeration by predicting the strength of causal claims, such as distinguishing between correlational and causal language. Pattern exploiting training is explored as a way to leverage large language models for this task in a semi-supervised manner. Finally, it proposes generally modelling information change by comparing original research to how it is communicated elsewhere, such as in news articles and tweets, using semantic matching techniques. Experiments are discussed on newly created datasets to benchmark performance of models on this task.

Automatically Detecting Scientific MisinformationIsabelle Augenstein

The document discusses automatically detecting scientific misinformation and exaggeration. It introduces work on cite-worthiness detection to improve scientific document understanding, and on detecting exaggeration in health science press releases. It describes generating scientific claims from citations for zero-shot scientific fact checking. The talk covers claim detection and generation, cite-worthiness detection, scientific claim generation, and exaggeration detection.

Accountable and Robust Automatic Fact CheckingIsabelle Augenstein

The past decade has seen a substantial rise in the amount of mis- and disinformation online, from targeted disinformation campaigns to influence politics, to the unintentional spreading of misinformation about public health. This development has spurred research in the area of automatic fact checking, a knowledge-intensive and complex reasoning task. Most existing fact checking models predict a claim’s veracity with black-box models, which often lack explanations of the reasons behind their predictions and contain hidden vulnerabilities. The lack of transparency in fact checking systems and ML models, in general, has been exacerbated by increased model size and by “the right…to obtain an explanation of the decision reached” enshrined in European law. This talk presents some first solutions to generating explanations for fact checking models. It then examines how to assess the generated explanations using diagnostic properties, and how further optimising for these diagnostic properties can improve the quality of the generating explanations. Finally, the talk examines how to systemically reveal vulnerabilities of black-box fact checking models.

Determining the Credibility of Science CommunicationIsabelle Augenstein

Most work on scholarly document processing assumes that the information processed is trustworthy and factually correct. However, this is not always the case. There are two core challenges, which should be addressed: 1) ensuring that scientific publications are credible -- e.g. that claims are not made without supporting evidence, and that all relevant supporting evidence is provided; and 2) that scientific findings are not misrepresented, distorted or outright misreported when communicated by journalists or the general public. I will present some first steps towards addressing these problems and outline remaining challenges.

Towards Explainable Fact Checking (DIKU Business Club presentation)Isabelle Augenstein

Outline: - Fact checking – what is it and why do we need it? - False information online - Content-based automatic fact checking - Explainability – what is it and why do we need it? - Making the right predictions for the right reasons - Model training pipeline - Explainable fact checking – some first solutions - Rationale selection - Generating free-text explanations - Wrap-up

Explainability for NLPIsabelle Augenstein

Tutorial on 'Explainability for NLP' given at the first ALPS (Advanced Language Processing) winter school: http://lig-alps.imag.fr/index.php/schedule/ The talk introduces the concepts of 'model understanding' as well as 'decision understanding' and provides examples of approaches from the areas of fact checking and text classification. Exercises to go with the tutorial are available here: https://github.com/copenlu/ALPS_2021

Towards Explainable Fact CheckingIsabelle Augenstein

Automatic fact checking is one of the more involved NLP tasks currently researched: not only does it require sentence understanding, but also an understanding of how claims relate to evidence documents and world knowledge. Moreover, there is still no common understanding in the automatic fact checking community of how the subtasks of fact checking — claim check-worthiness detection, evidence retrieval, veracity prediction — should be framed. This is partly owing to the complexity of the task, despite efforts to formalise the task of fact checking through the development of benchmark datasets. The first part of the talk will be on automatically generating textual explanations for fact checking, thereby exposing some of the reasoning processes these models follow. The second part of the talk will be on re-examining how claim check-worthiness is defined, and how check-worthy claims can be detected; followed by how to automatically generate claims which are hard to fact-check automatically.

Tracking False Information OnlineIsabelle Augenstein

Talk on 'Tracking False Information Online' at W-NUT workshop at EMNLP 2019. ========= Digital media enables fast sharing of information and discussions among users. While this comes with many benefits to today’s society, such as broadening information access, the manner in which information is disseminated also has obvious downsides. Since fast access to information is expected by many users and news outlets are often under financial pressure, speedy access often comes at the expense of accuracy, which leads to misinformation. Moreover, digital media can be misused by campaigns to intentionally spread false information, i.e. disinformation, about events, individuals or governments. In this talk, I will present on different ways false information is spread online, including misinformation and disinformation. I will then report findings from our recent and ongoing work on automatic fact checking, stance detection and framing attitudes.

What can typological knowledge bases and language representations tell us abo...Isabelle Augenstein

One of the core challenges in typology is to record properties of languages in a structured way. As a result of manual efforts, typological knowledge bases have emerged, which contains information about languages’ phonological, morphological and syntactic properties; as well as information about language families. Ideally, such typological knowledge bases would provide useful information for multilingual NLP models to learn how to selectively share parameters. A related area of research suggests a different way of encoding properties of languages, namely to learn language representation vectors directly from text documents. In this talk, I will analyse and contrast these two ways of encoding linguistic properties, as well as present research on how the two can benefit one another.

Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate ...Isabelle Augenstein

Paper presented at NAACL 2018. Link: https://arxiv.org/abs/1802.09913 Abstract: ============ We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and auxiliary, annotated datasets. We evaluate our approach on a variety of sequence classification tasks with disparate label spaces. We outperform strong single and multi-task baselines and achieve a new state-of-the-art for topic-based sentiment analysis.

Learning with limited labelled data in NLP: multi-task learning and beyondIsabelle Augenstein

When labelled training data for certain NLP tasks or languages is not readily available, different approaches exist to leverage other resources for the training of machine learning models. Those are commonly either instances from a related task or unlabelled data. An approach that has been found to work particularly well when only limited training data is available is multi-task learning. There, a model learns from examples of multiple related tasks at the same time by sharing hidden layers between tasks, and can therefore benefit from a larger overall number of training instances and extend the models' generalisation performance. In the related paradigm of semi-supervised learning, unlabelled data as well as labelled data for related tasks can be easily utilised by transferring labels from labelled instances to unlabelled ones in order to essentially extend the training dataset. In this talk, I will present my recent and ongoing work in the space of learning with limited labelled data in NLP, including our NAACL 2018 papers 'Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces [1] and 'From Phonology to Syntax: Unsupervised Linguistic Typology at Different Levels with Language Embeddings’ [2]. [1] https://t.co/A5jHhFWrdw [2] https://arxiv.org/abs/1802.09375 ========== Bio from my website http://isabelleaugenstein.github.io/index.html: I am a tenure-track assistant professor at the University of Copenhagen, Department of Computer Science since July 2017, affiliated with the CoAStAL NLP group and work in the general areas of Statistical Natural Language Processing and Machine Learning. My main research interests are weakly supervised and low-resource learning with applications including information extraction, machine reading and fact checking. Before starting a faculty position, I was a postdoctoral research associate in Sebastian Riedel's UCL Machine Reading group, mainly investigating machine reading from scientific articles. Prior to that, I was a Research Associate in the Sheffield NLP group, a PhD Student in the University of Sheffield Computer Science department, a Research Assistant at AIFB, Karlsruhe Institute of Technology and a Computational Linguistics undergraduate student at the Department of Computational Linguistics, Heidelberg University.

Learning to read for automated fact checkingIsabelle Augenstein

Spreading of mis- and disinformation is growing and is having a big impact on interpersonal communications, politics and even science. Traditional methods, e.g. manual fact-checking by reporters cannot keep up with the growth of information. On the other hand, there has been much progress in natural language processing recently, partly due to the resurgence of neural methods. How can natural language processing methods fill this gap and help to automatically check facts? This talk will explore different ways to frame fact checking and detail our ongoing work on learning to encode documents for automated fact checking, as well as describe future challenges.

More Related Content

Viewers also liked (10)

Question Answering over Linked Data (Reasoning Web Summer School)Andre Freitas

Information Extraction with Linked DataIsabelle Augenstein

Natural Language Processing for the Semantic WebIsabelle Augenstein

Lecture: Question AnsweringMarina Santini

Semantic Search Over The Webalierkan

Management information system question and answerspradeep acharya

Deep Learning Models for Question AnsweringSujit Pal

Intro to Deep Learning for Question AnsweringTraian Rebedea

Talent Sourcing and Matching - Artificial Intelligence and Black Box Semantic...Glen Cathey

Web 3.0 The Semantic WebHatem Mahmoud

Question Answering over Linked Data (Reasoning Web Summer School)Andre Freitas

Information Extraction with Linked DataIsabelle Augenstein

Natural Language Processing for the Semantic WebIsabelle Augenstein

Lecture: Question AnsweringMarina Santini

Semantic Search Over The Webalierkan

Management information system question and answerspradeep acharya

Deep Learning Models for Question AnsweringSujit Pal

Intro to Deep Learning for Question AnsweringTraian Rebedea

Talent Sourcing and Matching - Artificial Intelligence and Black Box Semantic...Glen Cathey

Web 3.0 The Semantic WebHatem Mahmoud

More from Isabelle Augenstein (17)

Beyond Fact Checking — Modelling Information Change in Scientific CommunicationIsabelle Augenstein

Automatically Detecting Scientific MisinformationIsabelle Augenstein

Accountable and Robust Automatic Fact CheckingIsabelle Augenstein

Determining the Credibility of Science CommunicationIsabelle Augenstein

Towards Explainable Fact Checking (DIKU Business Club presentation)Isabelle Augenstein

Explainability for NLPIsabelle Augenstein

Towards Explainable Fact CheckingIsabelle Augenstein

Tracking False Information OnlineIsabelle Augenstein

What can typological knowledge bases and language representations tell us abo...Isabelle Augenstein

Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate ...Isabelle Augenstein

Learning with limited labelled data in NLP: multi-task learning and beyondIsabelle Augenstein

Learning to read for automated fact checkingIsabelle Augenstein

SemEval 2017 Task 10: ScienceIE – Extracting Keyphrases and Relations from Sc...Isabelle Augenstein

Shared task summary for SemEval 2017 Task 10: ScienceIE – Extracting Keyphrases and Relations from Scientific Publications Paper: https://arxiv.org/abs/1704.02853 Abstract: We describe the SemEval task of extracting keyphrases and relations between them from scientific documents, which is crucial for understanding which publications describe which processes, tasks and materials. Although this was a new task, we had a total of 26 submissions across 3 evaluation scenarios. We expect the task and the findings reported in this paper to be relevant for researchers working on understanding scientific content, as well as the broader knowledge base population and information extraction communities.

1st Workshop for Women and Underrepresented Minorities (WiNLP) at ACL 2017 - ...Isabelle Augenstein

The document summarizes the history and goals of the WiNLP workshop, which aims to promote and support women and underrepresented groups in natural language processing. It discusses the growth of WiNLP from its inception in 2016 to the 2017 workshop with over 130 participants. It outlines WiNLP's mission to increase awareness of work by underrepresented groups and build community. It also notes challenges such as underrepresentation, bias, and lack of resources that WiNLP addresses through mentoring, funding, and community building.

Machine Reading Using Neural Machines (talk at Microsoft Research Faculty Sum...Isabelle Augenstein

The document discusses machine reading using neural machines. It presents goals of fact checking claims and understanding scientific publications. It outlines challenges in tasks like stance detection on tweets and summarizing scientific papers. These include interpreting statements based on the target or headline, handling unseen targets, and the small size of benchmark datasets which makes neural machine reading computationally costly.

Extracting Relations between Non-Standard Entities using Distant Supervision ...Isabelle Augenstein

Beyond Fact Checking — Modelling Information Change in Scientific CommunicationIsabelle Augenstein

Automatically Detecting Scientific MisinformationIsabelle Augenstein

Accountable and Robust Automatic Fact CheckingIsabelle Augenstein

Determining the Credibility of Science CommunicationIsabelle Augenstein

Towards Explainable Fact Checking (DIKU Business Club presentation)Isabelle Augenstein

Explainability for NLPIsabelle Augenstein

Towards Explainable Fact CheckingIsabelle Augenstein

Tracking False Information OnlineIsabelle Augenstein

What can typological knowledge bases and language representations tell us abo...Isabelle Augenstein

Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate ...Isabelle Augenstein

Learning with limited labelled data in NLP: multi-task learning and beyondIsabelle Augenstein

Learning to read for automated fact checkingIsabelle Augenstein

SemEval 2017 Task 10: ScienceIE – Extracting Keyphrases and Relations from Sc...Isabelle Augenstein

1st Workshop for Women and Underrepresented Minorities (WiNLP) at ACL 2017 - ...Isabelle Augenstein

Machine Reading Using Neural Machines (talk at Microsoft Research Faculty Sum...Isabelle Augenstein

Extracting Relations between Non-Standard Entities using Distant Supervision ...Isabelle Augenstein

Recently uploaded (20)

2025-05-Q4-2024-Investor-Presentation.pptxSamuele Fogagnolo

Linux Professional Institute LPIC-1 Exam.pdfRHCSA Guru

Manifest Pre-Seed Update | A Humanoid OEM Deeptech In Francechb3

Andrew Marnell: Transforming Business Strategy Through Data-Driven InsightsAndrew Marnell

Noah Loul Shares 5 Steps to Implement AI Agents for Maximum Business Efficien...Noah Loul

Artificial intelligence is changing how businesses operate. Companies are using AI agents to automate tasks, reduce time spent on repetitive work, and focus more on high-value activities. Noah Loul, an AI strategist and entrepreneur, has helped dozens of companies streamline their operations using smart automation. He believes AI agents aren't just tools—they're workers that take on repeatable tasks so your human team can focus on what matters. If you want to reduce time waste and increase output, AI agents are the next move.

Into The Box Conference Keynote Day 1 (ITB2025)Ortus Solutions, Corp

Rusty Waters: Elevating Lakehouses Beyond Sparkcarlyakerly1

Spark is a powerhouse for large datasets, but when it comes to smaller data workloads, its overhead can sometimes slow things down. What if you could achieve high performance and efficiency without the need for Spark? At S&P Global Commodity Insights, having a complete view of global energy and commodities markets enables customers to make data-driven decisions with confidence and create long-term, sustainable value. 🌍 Explore delta-rs + CDC and how these open-source innovations power lightweight, high-performance data applications beyond Spark! 🚀

Massive Power Outage Hits Spain, Portugal, and France: Causes, Impact, and On...Aqusag Technologies

Cybersecurity Identity and Access Solutions using Azure ADVICTOR MAESTRE RAMIREZ

SAP Modernization: Maximizing the Value of Your SAP S/4HANA Migration.pdfPrecisely

Technology Trends in 2025: AI and Big Data AnalyticsInData Labs

At InData Labs, we have been keeping an ear to the ground, looking out for AI-enabled digital transformation trends coming our way in 2025. Our report will provide a look into the technology landscape of the future, including: -Artificial Intelligence Market Overview -Strategies for AI Adoption in 2025 -Anticipated drivers of AI adoption and transformative technologies -Benefits of AI and Big data for your business -Tips on how to prepare your business for innovation -AI and data privacy: Strategies for securing data privacy in AI models, etc. Download your free copy nowand implement the key findings to improve your business.

AI Changes Everything – Talk at Cardiff Metropolitan University, 29th April 2...Alan Dix

Talk at the final event of Data Fusion Dynamics: A Collaborative UK-Saudi Initiative in Cybersecurity and Artificial Intelligence funded by the British Council UK-Saudi Challenge Fund 2024, Cardiff Metropolitan University, 29th April 2025 https://alandix.com/academic/talks/CMet2025-AI-Changes-Everything/ Is AI just another technology, or does it fundamentally change the way we live and think? Every technology has a direct impact with micro-ethical consequences, some good, some bad. However more profound are the ways in which some technologies reshape the very fabric of society with macro-ethical impacts. The invention of the stirrup revolutionised mounted combat, but as a side effect gave rise to the feudal system, which still shapes politics today. The internal combustion engine offers personal freedom and creates pollution, but has also transformed the nature of urban planning and international trade. When we look at AI the micro-ethical issues, such as bias, are most obvious, but the macro-ethical challenges may be greater. At a micro-ethical level AI has the potential to deepen social, ethnic and gender bias, issues I have warned about since the early 1990s! It is also being used increasingly on the battlefield. However, it also offers amazing opportunities in health and educations, as the recent Nobel prizes for the developers of AlphaFold illustrate. More radically, the need to encode ethics acts as a mirror to surface essential ethical problems and conflicts. At the macro-ethical level, by the early 2000s digital technology had already begun to undermine sovereignty (e.g. gambling), market economics (through network effects and emergent monopolies), and the very meaning of money. Modern AI is the child of big data, big computation and ultimately big business, intensifying the inherent tendency of digital technology to concentrate power. AI is already unravelling the fundamentals of the social, political and economic world around us, but this is a world that needs radical reimagining to overcome the global environmental and human challenges that confront us. Our challenge is whether to let the threads fall as they may, or to use them to weave a better future.

Cyber Awareness overview for 2025 month of securityriccardosl1

Procurement Insights Cost To Value Guide.pptxJon Hansen

Special Meetup Edition - TDX Bengaluru Meetup #52.pptxshyamraj55

HCL Nomad Web – Best Practices and Managing Multiuser Environmentspanagenda

Webinar Recording: https://www.panagenda.com/webinars/hcl-nomad-web-best-practices-and-managing-multiuser-environments/ HCL Nomad Web is heralded as the next generation of the HCL Notes client, offering numerous advantages such as eliminating the need for packaging, distribution, and installation. Nomad Web client upgrades will be installed “automatically” in the background. This significantly reduces the administrative footprint compared to traditional HCL Notes clients. However, troubleshooting issues in Nomad Web present unique challenges compared to the Notes client. Join Christoph and Marc as they demonstrate how to simplify the troubleshooting process in HCL Nomad Web, ensuring a smoother and more efficient user experience. In this webinar, we will explore effective strategies for diagnosing and resolving common problems in HCL Nomad Web, including - Accessing the console - Locating and interpreting log files - Accessing the data folder within the browser’s cache (using OPFS) - Understand the difference between single- and multi-user scenarios - Utilizing Client Clocking

TrsLabs - Fintech Product & Business ConsultingTrs Labs

Hybrid Growth Mandate Model with TrsLabs Strategic Investments, Inorganic Growth, Business Model Pivoting are critical activities that business don't do/change everyday. In cases like this, it may benefit your business to choose a temporary external consultant. An unbiased plan driven by clearcut deliverables, market dynamics and without the influence of your internal office equations empower business leaders to make right choices. Getting things done within a budget within a timeframe is key to Growing Business - No matter whether you are a start-up or a big company Talk to us & Unlock the competitive advantage

#StandardsGoals for 2025: Standards & certification roundup - Tech Forum 2025BookNet Canada

Book industry standards are evolving rapidly. In the first part of this session, we’ll share an overview of key developments from 2024 and the early months of 2025. Then, BookNet’s resident standards expert, Tom Richardson, and CEO, Lauren Stewart, have a forward-looking conversation about what’s next. Link to recording, transcript, and accompanying resource: https://bnctechforum.ca/sessions/standardsgoals-for-2025-standards-certification-roundup/ Presented by BookNet Canada on May 6, 2025 with support from the Department of Canadian Heritage.

Greenhouse_Monitoring_Presentation.pptx.hpbmnnxrvb

AI EngineHost Review: Revolutionary USA Datacenter-Based Hosting with NVIDIA ...SOFTTECHHUB

I started my online journey with several hosting services before stumbling upon Ai EngineHost. At first, the idea of paying one fee and getting lifetime access seemed too good to pass up. The platform is built on reliable US-based servers, ensuring your projects run at high speeds and remain safe. Let me take you step by step through its benefits and features as I explain why this hosting solution is a perfect fit for digital entrepreneurs.

2025-05-Q4-2024-Investor-Presentation.pptxSamuele Fogagnolo

Linux Professional Institute LPIC-1 Exam.pdfRHCSA Guru

Manifest Pre-Seed Update | A Humanoid OEM Deeptech In Francechb3

Andrew Marnell: Transforming Business Strategy Through Data-Driven InsightsAndrew Marnell

Noah Loul Shares 5 Steps to Implement AI Agents for Maximum Business Efficien...Noah Loul

Into The Box Conference Keynote Day 1 (ITB2025)Ortus Solutions, Corp

Rusty Waters: Elevating Lakehouses Beyond Sparkcarlyakerly1

Massive Power Outage Hits Spain, Portugal, and France: Causes, Impact, and On...Aqusag Technologies

Cybersecurity Identity and Access Solutions using Azure ADVICTOR MAESTRE RAMIREZ

SAP Modernization: Maximizing the Value of Your SAP S/4HANA Migration.pdfPrecisely

Technology Trends in 2025: AI and Big Data AnalyticsInData Labs

AI Changes Everything – Talk at Cardiff Metropolitan University, 29th April 2...Alan Dix

Cyber Awareness overview for 2025 month of securityriccardosl1

Procurement Insights Cost To Value Guide.pptxJon Hansen

Special Meetup Edition - TDX Bengaluru Meetup #52.pptxshyamraj55

HCL Nomad Web – Best Practices and Managing Multiuser Environmentspanagenda

TrsLabs - Fintech Product & Business ConsultingTrs Labs

#StandardsGoals for 2025: Standards & certification roundup - Tech Forum 2025BookNet Canada

Greenhouse_Monitoring_Presentation.pptx.hpbmnnxrvb

AI EngineHost Review: Revolutionary USA Datacenter-Based Hosting with NVIDIA ...SOFTTECHHUB

USFD at SemEval-2016 - Stance Detection on Twitter with Autoencoders

1. Isabelle Augenstein, Andreas Vlachos, Kalina Bontcheva [email protected], {a.vlachos | k.bontcheva}@sheffield.ac.uk USFD at SemEval-2016 Task 6: Any-Target Stance Detection on Twitter with Autoencoders Stance Detection Subtask B Classify attitude of tweet towards target as “favor”, “against”, “none” Tweet: “No more Hillary Clinton” Target: Donald Trump Stance: FAVOR Subtask A training targets: Climate Change is a Real Concern, Feminist Movement, Atheism, Legalization of Abortion, Hillary Clinton Subtask B testing target: Donald Trump Challenges •  Labelled data not available for the test target •  Manual labelling of training data not allowed •  Target does not always appear in tweet Feature Extraction •  Aut-twe: Tweet auto-encoded tweet,100d feature vector •  targetInTweet: is (shortened) target contained in tweet •  Good indicator for non-neutral stance •  Other features tested (not used for final run): WordNet- Affect gazetteers, emoticon detection •  Baselines: bag of word, word2vec (trained on same data as autoencoder) Results Model Comparison (Hillary Clinton, dev) Model Comparison (Donald Trump, test) 0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 Macro F1 BoW BoW+inTwe Word2Vec Aut-twe Aut-twe+inTwe Conclusions •  It is important to detect if the target is mentioned in the tweet •  Hillary Clinton: 0.4538 F1 (inTwe) vs 0.3243 F1 (not inTwe) •  Donald Trump: 0.3745 F1 (inTwe) vs 0.2377 F1 (not inTwe) •  Autoencoder can help to detect stance towards unseen targets •  Developing method for new targets without labelled training data is challenging - discrepancies between what works for dev vs. test set •  Future work: better incorporate the target for stance detection Acknowledgements This work was partially supported by the European Union, grant agreement No. 611233 PHEME (http://www.pheme.eu) Data •  5 628 labelled train tweets about Subtask A targets •  1 278 about Hillary Clinton, used for dev •  278 013 unlabelled Donald Trump tweets •  395 212 collected unlabelled tweets about all targets •  Keywords: hillary, clinton, trump, climate, femini, aborti •  707 Donald Trump test tweets Preprocessing •  Phrase detection: Train phrase detection model on unlabelled +labelled tweets, e.g. “donald”, “trump” → “donald trump” Autoencoder •  Bag-of-word autoencoder, using 50 000 most frequent words •  trained on unlabelled+labelled tweets •  Input vector: dimensionality 50 000. For each word in vocabulary, does tweet contain the word or not •  One hidden layer (size 100), output size 100 •  Trained encoder is applied to labelled train and test data to obtain 100d features, decoder not used Model Macro F1 Majority class (oﬃcial) 0.2972 SVM n-grams (oﬃcial) 0.2843 BoW 0.3453 Aut-twe (submi6ed) 0.3307 References •  Code: https://github.com/sheffieldnlp/stance-semeval2016 •  Phrases: Mikolov et al. (2013). Distributed Representations of Words and Phrases and Their Compositionality. NIPS. Tweets “No more Hillary Clinton”, “Donald Trump”, “FAVOR” Preprocessing: [“No”, “more”, “Hillary_Clinton”] Autoencoder Training [america: 0, …, Hillary_Clinton: 1] 50 000d input [0, 0, …, 1] 100d hidden layer [0, 1, …, 1] 100d output layer Feature Extraction Autoencoder inTwe [0, 1, …, 1] 0 Logistic Regression Model Predictions “#voteTrump (…)”, “Donald Trump”, “FAVOR” “youre fired (…)” “Donald Trump”, “AGAINST”

USFD at SemEval-2016 - Stance Detection on Twitter with Autoencoders

Recommended

More Related Content

Viewers also liked (10)

More from Isabelle Augenstein (17)

Recently uploaded (20)

USFD at SemEval-2016 - Stance Detection on Twitter with Autoencoders