Vision-language (V+L) pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text. While existing vision-language pretraining models primarily focus on understanding objects in images or entities in text, they often ignore the alignment at the level of events and their argument structures. % In this work, we propose a contrastive learning framework to enforce vision-language pretraining models to comprehend events and associated argument (participant) roles. To achieve this, we take advantage of text information extraction technologies to obtain event structural knowledge, and utilize multiple prompt functions to contrast difficult negative descriptions by manipulating event structures. We also design an event graph alignment loss based on optimal transport to capture event argument structures. In addition, we collect a large event-rich dataset (106,875 images) for pretraining, which provides a more challenging image retrieval benchmark to assess the understanding of complicated lengthy sentences. Experiments show that our zero-shot CLIP-Event outperforms the state-of-the-art supervised model in argument extraction on Multimedia Event Extraction, achieving more than 5\% absolute F-score gain in event extraction, as well as significant improvements on a variety of downstream tasks under zero-shot settings.

Aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis. To better comprehend long complicated sentences and obtain accurate aspect-specific information, linguistic and commonsense knowledge are generally required in this task. However, most methods employ complicated and inefficient approaches to incorporate external knowledge, e.g., directly searching the graph nodes. Additionally, the complementarity between external knowledge and linguistic information has not been thoroughly studied. To this end, we propose a knowledge graph augmented network (KGAN), which aims to effectively incorporate external knowledge with explicitly syntactic and contextual information. In particular, KGAN captures the sentiment feature representations from multiple different perspectives, i.e., context-, syntax- and knowledge-based. First, KGAN learns the contextual and syntactic representations in parallel to fully extract the semantic features. Then, KGAN integrates the knowledge graphs into the embedding space, based on which the aspect-specific knowledge representations are further obtained via an attention mechanism. Last, we propose a hierarchical fusion module to complement these multiview representations in a local-to-global manner. Extensive experiments on three popular ABSA benchmarks demonstrate the effectiveness and robustness of our KGAN. Notably, with the help of the pretrained model of RoBERTa, KGAN achieves a new record of state-of-the-art performance.

Natural Language Processing (NLP) is an area in computer science that studies the interactions between computers and human languages. It is the technology behind search engines such as Google. The analysis of language can be done manually, and it has been done for centuries. But technology continues to evolve, which is especially true in natural language processing (NLP). The Machine and Deep Learning communities have been actively pursuing Natural Language Processing (NLP) through various techniques.

Conventional machine learning (ML) relies heavily on manual design from machine learning experts to decide learning tasks, data, models, optimization algorithms, and evaluation metrics, which is labor-intensive, time-consuming, and cannot learn autonomously like humans. In education science, self-directed learning, where human learners select learning tasks and materials on their own without requiring hands-on guidance, has been shown to be more effective than passive teacher-guided learning. Inspired by the concept of self-directed human learning, we introduce the principal concept of Self-directed Machine Learning (SDML) and propose a framework for SDML. Specifically, we design SDML as a self-directed learning process guided by self-awareness, including internal awareness and external awareness. Our proposed SDML process benefits from self task selection, self data selection, self model selection, self optimization strategy selection and self evaluation metric selection through self-awareness without human guidance. Meanwhile, the learning performance of the SDML process serves as feedback to further improve self-awareness. We propose a mathematical formulation for SDML based on multi-level optimization. Furthermore, we present case studies together with potential applications of SDML, followed by discussing future research directions. We expect that SDML could enable machines to conduct human-like self-directed learning and provide a new perspective towards artificial general intelligence.

Send us an email at info@cantortrading.fi if you'd like to talk.

Frame shift is a cross-linguistic phenomenon in translation which results in corresponding pairs of linguistic material evoking different frames. The ability to predict frame shifts enables automatic creation of multilingual FrameNets through annotation projection. Here, we propose the Frame Shift Prediction task and demonstrate that graph attention networks, combined with auxiliary training, can learn cross-linguistic frame-to-frame correspondence and predict frame shifts.

This blog post summarizes our paper Screen Parsing: Towards Reverse Engineering of UI Models from Screenshots, which was published in the proceedings of UIST 2021. Machines that understand and operate user interfaces (UIs) on behalf of users could offer many benefits. For example, a screen reader (e.g., VoiceOver and TalkBack) could facilitate access to UIs for blind and visually impaired users, and task automation agents (e.g., Siri Shortcuts and IFTTT) could allow users to automate repetitive or complex tasks with their devices more efficiently. These benefits are gated on how well these systems can understand an underlying app's UI by reasoning about 1) the functionality present, 2) how its different components work together, and 3) how it can be operated to accomplish some goal. Many rely on the availability of UI metadata (e.g., the view hierarchy and the accessibility hierarchy), which provide some information about what elements are present and their properties.

A frequency count of all the names in a document; think of a dictionary containing the frequency of all words in a document. Often use for autocompleting and resolving word ambiguity (e.g. is watch in the document a verb or a noun?) "Also called shallow parsing, chunking aims at labeling segments of a sentence with syntactic constituents such as noun or verb phrases (NP or VP). Each word is assigned only one unique tag, often encoded as a begin-chunk (e.g., B-NP) or inside-chunk tag (e.g., I-NP)" (Collobert et al.). An entity is a thing that belongs to a noun family (e.g. the car, the chef, the plant). A named entity is an entity that has a proper name (e.g.

Mississippi mother Marie Sanderson and former New Jersey school nurse Erin Pein joined'Fox & Friends' to discuss the surfaced emails. A Virginia teachers union has faced ridicule online after it sent a letter riddled with grammatical and typographical errors. The union president explained that the union mistakenly published a draft, rather than the completed letter. "On behalf of the members of the Arlington Education Association, this dire expression lends great concerns for Arlington Public Schools (APS) return plan for January 3rd, 2022," begins the letter, which Arlington Education Association (AEA) President Ingrid Grant sent to Arlington Public Schools Superintendent Francisco Duran on Dec. 30, 2021. The letter raised concerns about the omicron variant of the coronavirus behind the COVID-19 pandemic, a more contagious variant that has spread rapidly throughout the U.S. Ellen Gallery, a homeschooling mother of three who lives in the area, claimed that she and her kids had gone through the letter, correcting mistakes.

Many tasks in Natural Language Processing (NLP) and Computer Vision (CV) offer evidence that humans disagree, from objective tasks such as part-of-speech tagging to more subjective tasks such as classifying an image or deciding whether a proposition follows from certain premises. While most learning in artificial intelligence (AI) still relies on the assumption that a single (gold) interpretation exists for each item, a growing body of research aims to develop learning methods that do not rely on this assumption. In this survey, we review the evidence for disagreements on NLP and CV tasks, focusing on tasks for which substantial datasets containing this information have been created. We discuss the most popular approaches to training models from datasets containing multiple judgments potentially in disagreement. We systematically compare these different approaches by training them with each of the available datasets, considering several ways to evaluate the resulting models. Finally, we discuss the results in depth, focusing on four key research questions, and assess how the type of evaluation and the characteristics of a dataset determine the answers to these questions. Our results suggest, first of all, that even if we abandon the assumption of a gold standard, it is still essential to reach a consensus on how to evaluate models. This is because the relative performance of the various training methods is critically affected by the chosen form of evaluation. Secondly, we observed a strong dataset effect. With substantial datasets, providing many judgments by high-quality coders for each item, training directly with soft labels achieved better results than training from aggregated or even gold labels. This result holds for both hard and soft evaluation. But when the above conditions do not hold, leveraging both gold and soft labels generally achieved the best results in the hard evaluation. All datasets and models employed in this paper are freely available as supplementary materials.