Time-series forecasting plays an essential role in domains such as finance, healthcare, and energy. Yet most existing systems operate in a unimodal setting, overlooking complementary information available from visual and textual modalities. There are surprisingly few time-series forecasting demos, and multimodal, interpretable demos are rarer still. In practice, it is difficult for users to experiment with foundation models on their own time-series data due to strict input requirements, heavy setup burdens, and limited interpretability support. We present MulTiCast, an interactive Multimodal Time series foreCasting system that enables users to combine numerical signals with visual and textual context to improve predictions. The system builds on pretrained models with lightweight adaptation, but its central contribution lies in the interactive demonstration platform. Through a web interface via Hugging Face Spaces, users can load datasets, toggle modality inclusion, and visualize forecasts together with the attention maps of each modality, providing insights into the reasoning path behind the predictions.

Shuo Yang, Caren Han, Xueqi Ma, Yan Li, Mohammad Reza Ghasemi Madani, Eduard Hovy. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Digitisation in the cultural heritage sector has produced large but fragmented repositories of museum collection data, spanning structured catalogue records, images, and unstructured descriptions. Existing museum information systems often make it difficult to integrate these sources into a unified, queryable representation that supports relation-aware exploration. We present MuseKG, an interactive knowledge graph system that organises heterogeneous museum data into a typed graph that links objects, people, organisations, images, image-derived labels, and extracted semantic entities within a coherent schema. MuseKG supports natural-language queries by grounding user questions to graph entities and retrieving a compact neighbourhood of evidence for answer generation. Through an interactive demonstration on real museum collections, we show that MuseKG supports common exploration tasks such as attribute lookup, relation exploration, and relation-aware retrieval, with answers that remain inspectable via explicit graph structures.

Esports has rapidly emerged as a global phenomenon with an ever-expanding audience on livestream platforms. However, due to the complex nature of the game, it becomes challenging for newcomers to comprehend the gaming situation. This research introduces a 3M-Game that integrates multi-modal (MM) information from the livestream platform, including chat and livestream, to uncover the event. While conventional MM models typically prioritise aligning MM data through concurrent training towards a unified objective, our framework leverages multiple independent teachers trained on different tasks to accomplish game event detection. The results show the effectiveness of the proposed framework. The code and appendix are in https://github.com/adlnlp/3m_game.

Existing Multimodal Large Language Models (MLLMs) and Visual Language Pretrained Models (VLPMs) have shown remarkable performances in general Visual Question Answering (VQA). However, these models struggle with VQA questions that require external commonsense knowledge due to the challenges in generating high-quality prompts and the high computational costs of fine-tuning. In this work, we propose a novel graph-based multimodal commonsense knowledge distillation framework that constructs a unified relational graph over commonsense knowledge, visual objects and questions through a Graph Convolutional Network (GCN) following a teacher-student environment. This proposed framework is flexible with any type of teacher and student models without further fine-tuning, and has achieved competitive performances on the ScienceQA dataset. The code is in https://github.com/adlnlp/MCKDVQA.

Retrieval augmented generation (RAG) has rapidly emerged as a cornerstone for building trustworthy and efficient generative AI systems, spanning from unimodal question answering to complex multimodal reasoning. The 1st international workshop on retrieval-driven generative AI gathers researchers and practitioners focused on the applied side of RAG-particularly for visually rich document understanding (VRDU) where text, layout, and images intertwine. New in 2025, this workshop is co located with the ScienceON AI Challenge, an open competition benchmarking the reliability of AI generated summaries over ScienceON's public OpenAPI search results. By combining a research workshop with a hands on challenge, we provide a complete pipeline from algorithms to real world evaluation. The half day event features invited keynotes, peer reviewed papers, challenge finalist talks, and a poster/demo session, catalyzing collaboration toward robust, explainable, and domain adapted generativeAI.

Key information extraction (KIE) from visually rich documents, such as receipts and forms, involves a deep understanding of textual, visual, and layout feature information. Transformers fine-tuned for KIE achieve state-of-the-art performance but lack generality and portability across different domains. In contrast, vision large language models (VLLMs) offer higher flexibility and zero-shot capability but fall short with domain-specific layout relations unless performing a resource-demanding supervised fine-tuning. To reach the best compromise solution between lightweight models and VLLMs, we propose KIEPrompter, a cost-effective LLM-based KIE approach that leverages the predictions of lightweight models as external knowledge injected into VLLM prompts. By incorporating these auxiliary predictions, VLLMs are guided to attend relevant multimodal content without ad hoc training. The accuracy results achieved by KIEPrompter in three benchmark document collections are superior to those of VLLMs in both zero-shot and layout-sensitive scenarios. We compare various strategies for incorporating lightweight model predictions, ranging from coarse-grained predictions without explicit confidence scores to fine-grained per-element network logits. We also demonstrate that our approach is robust to the absence of specific classes in trained lightweight models, as the VLLMs' pre-training compensates for the limited generality of lightweight models.

Identifying entities in medical text often involves dealing with discontinuous word sequences or entities sharing a common head, which pose significant challenges for traditional Named Entity Recognition (NER) systems. Current state-of-the-art discontinuous NER models typically process each sentence in isolation, overlooking valuable intra-sentence context. However, recent studies have shown that large language models (LLMs) perform exceptionally well when provided such context. In this work, we introduce DocDiscNER, a novel approach to discontinuous NER, which features (i) a context-aware document chunking method that provides contextually related segments as input for LLM-based NER models; (ii) a dataset and approach for coordination ellipses resolution, to address candidate spans sharing common heads and (iii) a self-consistency decoding strategy that uses self-ensembling and a majority voting mechanism to select the most consistent predictions as entity spans. We demonstrate the effectiveness and generalisability of our method on three discontinuous NER benchmarks, achieving new state-of-the-art (SOTA) performance on two of them–CADEC and ShARe-14 (2.48 and 2.2 absolute F1 points gain, respectively); while achieving competitive results on ShARe-13. In addition, our method surpasses previous SOTA performance specifically in recognising discontinuous mentions. A deeper analysis unveils that incorporating semantically relevant context significantly enhances overall NER performance compared to using individual sentences as input.

Transformer-based Large Language Models (LLMs) struggle with inputs exceeding their training context window due to positional outof-distribution (O.O.D.) issues that disrupt attention.Existing solutions, including finetuning and training-free methods, face challenges like inefficiency, redundant interpolation, logit outliers, or loss of local positional information.We propose Greedy Attention Logit Interpolation (GALI), a training-free method that improves length extrapolation by greedily reusing pretrained positional intervals and interpolating attention logit to eliminate outliers.GALI achieves stable and superior performance across a wide range of long-context tasks without requiring input-length-specific tuning.Our analysis further reveals that LLMs interpret positional intervals unevenly and that restricting interpolation to narrower ranges improves performance, even on short-context tasks.GALI represents a step toward more robust and generalizable long-text processing in LLMs.Our implementation of GALI, along with the experiments from our paper, is open-sourced at https://github.com/adlnlp/Gali.

Visually Rich Document Understanding (VRDU) has emerged as a critical field in document intelligence, enabling automated extraction of key information from complex documents across domains such as medical, financial, and educational applications. However, form-like documents pose unique challenges due to their complex layouts, multi-stakeholder involvement, and high structural variability. Addressing these issues, the VRD-IU Competition was introduced, focusing on extracting and localizing key information from multi-format forms within the Form-NLU dataset, which includes digital, printed, and handwritten documents. This paper presents insights from the competition, which featured two tracks: Track A, emphasizing entity-based key information retrieval, and Track B, targeting end-to-end key information localization from raw document images. With over 20 participating teams, the competition showcased various state-of-the-art methodologies, including hierarchical decomposition, transformer-based retrieval, multimodal feature fusion, and advanced object detection techniques. The top-performing models set new benchmarks in VRDU, providing valuable insights into document intelligence.

Chart question answering (ChartQA) is challenged by the heterogeneous composition of chart elements and the subtle data patterns they encode.This work introduces a novel joint multimodal scene graph framework that explicitly models the relationships among chart components and their underlying structures.The framework integrates both visual and textual graphs to capture structural and semantic characteristics, while a graph contrastive learning strategy aligns node representations across modalities-enabling their seamless incorporation into a transformer decoder as soft prompts.Moreover, a set of tailored Chain-of-Thought (CoT) prompts is proposed to enhance multimodal large language models (MLLMs) in zero-shot scenarios by mitigating hallucinations.Extensive evaluations on benchmarks including ChartQA, OpenCQA, and ChartX demonstrate significant performance improvements and validate the efficacy of the proposed approach.

Discontinuous Named Entity Recognition (DNER) presents a challenging problem where entities may be scattered across multiple non-adjacent tokens, making traditional sequence labelling approaches inadequate. Existing methods predominantly rely on custom tagging schemes to handle these discontinuous entities, resulting in models tightly coupled to specific tagging strategies and lacking generalisability across diverse datasets. To address these challenges, we propose TriG-NER, a novel Triplet-Grid Framework that introduces a generalisable approach to learning robust token-level representations for discontinuous entity extraction. Our framework applies triplet loss at the token level, where similarity is defined by word pairs existing within the same entity, effectively pulling together similar and pushing apart dissimilar ones. This approach enhances entity boundary detection and reduces the dependency on specific tagging schemes by focusing on word-pair relationships within a flexible grid structure. We evaluate TriG-NER on three benchmark DNER datasets and demonstrate significant improvements over existing grid-based architectures. These results underscore our framework's effectiveness in capturing complex entity structures and its adaptability to various tagging schemes, setting a new benchmark for discontinuous entity extraction.

With the introduction of large language models, chatbots are becoming more conversational to communicate effectively and capable of handling increasingly complex tasks. To make a chatbot more relatable and engaging, we propose a new language model idea that maps the human-like personality. In this paper, we propose a systematic Personality-Enhanced Language Model (PELM) approach by using a joint learning mechanism of personality classification and language generation tasks. The proposed PELM leverages a dataset of defined personality typology, Myers-Briggs Type Indicator, and produces a Personality-Enhanced Language Model by using a joint learning and cross-teaching structure consisting of a classification and language modelling to incorporate personalities via both distinctive types and textual information. The results show that PELM can generate better personality-based outputs than baseline models.

The significance of mental health classification is paramount in contemporary society, where digital platforms serve as crucial sources for monitoring individuals' well-being. However, existing social media mental health datasets primarily consist of text-only samples, potentially limiting the efficacy of models trained on such data. Recognising that humans utilise cross-modal information to comprehend complex situations or issues, we present a novel approach to address the limitations of current methodologies. In this work, we introduce a Multimodal and Multi-Teacher Knowledge Distillation model for Mental Health Classification, leveraging insights from cross-modal human understanding. Unlike conventional approaches that often rely on simple concatenation to integrate diverse features, our model addresses the challenge of appropriately representing inputs of varying natures (e.g., texts and sounds). To mitigate the computational complexity associated with integrating all features into a single model, we employ a multimodal and multi-teacher architecture. By distributing the learning process across multiple teachers, each specialising in a particular feature extraction aspect, we enhance the overall mental health classification performance. Through experimental validation, we demonstrate the efficacy of our model in achieving improved performance.

Automatic Chart Question Answering (ChartQA) is challenging due to the complex distribution of chart elements with patterns of the underlying data not explicitly displayed in charts. To address this challenge, we design a joint multimodal scene graph for charts to explicitly represent the relationships between chart elements and their patterns. Our proposed multimodal scene graph includes a visual graph and a textual graph to jointly capture the structural and semantical knowledge from the chart. This graph module can be easily integrated with different vision transformers as inductive bias. Our experiments demonstrate that incorporating the proposed graph module enhances the understanding of charts' elements' structure and semantics, thereby improving performance on publicly available benchmarks, ChartQA and OpenCQA.

Visual storytelling aims to automatically generate a coherent story based on a given image sequence.Unlike tasks like image captioning, visual stories should contain factual descriptions, worldviews, and human social commonsense to put disjointed elements together to form a coherent and engaging human-writeable story.However, most models mainly focus on applying factual information and using taxonomic/lexical external knowledge when attempting to create stories.This paper introduces SCO-VIST, a framework representing the image sequence as a graph with objects and relations that includes human action motivation and its social interaction commonsense knowledge.SCO-VIST then takes this graph representing plot points and creates bridges between plot points with semantic and occurrence-based edge weights.This weighted story graph produces the storyline in a sequence of events using Floyd-Warshall's algorithm.Our proposed framework produces stories superior across multiple metrics in terms of visual grounding, coherence, diversity, and humanness, per both automatic and human evaluations.

This tutorial explores recent advancements in multimodal pretrained and large models, capable of integrating and processing diverse data forms such as text, images, audio, and video. Participants will gain an understanding of the foundational concepts of multimodality, the evolution of multimodal research, and the key technical challenges addressed by these models. We will cover the latest multimodal datasets and pretrained models, including those beyond vision and language. Additionally, the tutorial will delve into the intricacies of multimodal large models and instruction tuning strategies to optimise performance for specific tasks. Hands-on laboratories will offer practical experience with state-of-the-art multimodal models, demonstrating real-world applications like visual storytelling and visual question answering. This tutorial aims to equip researchers, practitioners, and newcomers with the knowledge and skills to leverage multimodal AI. ACM Multimedia 2024 is the ideal venue for this tutorial, aligning perfectly with our goal of understanding multimodal pretrained and large language models, and their tuning mechanisms.

Phishing attacks are a prevailing problem in cybersecurity. In many data breaches, the initial entry can be traced back to phishing. URL-based phishing detection is one of the many ways of phishing attempt detection where solely the properties of the URLs are used to decide whether a given URL is phishing or not. While there are multiple existing works that use machine learning and deep learning to detect phishing URLs, in this paper, we show that such methods lack generalisation (i.e., they work effectively only when the test sets are split from the same training dataset). This is a significant issue since the vast majority of phishing attempts are short-lived and use freshly created domain names. Also, many network vantage points and middleboxes record URLs in slightly different formats and as such, URL data collected at various companies may be different. To address this, we propose an Unsupervised Domain Adaptation-based framework to increase the model transferability between datasets. We evaluate our approach using three datasets and show that the increase in cross-dataset F1 score performance is 0.06 on average and in some cases approximately as high as 0.2.

In-game toxic language becomes the hot potato in the gaming industry and community. There have been several online game toxicity analysis frameworks and models proposed. However, it is still challenging to detect toxicity due to the nature of in-game chat, which has extremely short length. In this paper, we describe how the in-game toxic language shared task has been established using the real-world in-game chat data. In addition, we propose and introduce the model/framework for toxic language token tagging (slot filling) from the in-game chat. The data and code will be released.

Document understanding and information extraction include different tasks to understand a document and extract valuable information automatically. Recently, there has been a rising demand for developing document understanding among different domains, including business, law, and medicine, to boost the efficiency of work that is associated with a large number of documents. This workshop aims to bring together researchers and industry developers in the field of document intelligence and understanding diverse document types to boost automatic document processing and understanding techniques. We also release a data challenge on the recently introduced document-level VQA dataset, PDFVQA. The PDFVQA challenge examines the model's structural and contextual understandings on the natural full document level of multiple consecutive document pages by including questions with a sequence of answers extracted from multi-pages of the full document. This task helps to boost the document understanding step from the single-page level to the full document level understanding.

Extracting meaningful drug-related information chunks, such as adverse drug events (ADE), is crucial for preventing morbidity and saving many lives. Most ADEs are reported via an unstructured conversation with the medical context, so applying a general entity recognition approach is not sufficient enough. In this paper, we propose a new multi-aspect cross-integration framework for drug entity/event detection by capturing and aligning different context/language/knowledge properties from drug-related documents. We first construct multi-aspect encoders to describe semantic, syntactic, and medical document contextual information by conducting those slot tagging tasks, main drug entity/event detection, part-of-speech tagging, and general medical named entity recognition. Then, each encoder conducts cross-integration with other contextual information in three ways: the key-value cross, attention cross, and feedforward cross, so the multi-encoders are integrated in depth. Our model outperforms all SOTA on two widely used tasks, flat entity detection and discontinuous event extraction.

Natural language understanding typically maps single utterances to a dual level semantic frame, sentence level intent and slot labels at the word level. The best performing models force explicit interaction between intent detection and slot filling. We present a novel tri-level joint natural language understanding approach, adding domain, and explicitly exchange semantic information between all levels. This approach enables the use of multi-turn datasets which are a more natural conversational environment than single utterance. We evaluate our model on two multi-turn datasets for which we are the first to conduct joint slot-filling and intent detection. Our model outperforms state-of-the-art joint models in slot filling and intent detection on multi-turn data sets. We provide an analysis of explicit interaction locations between the layers. We conclude that including domain information improves model performance.

Compared to general document analysis tasks, form document structure understanding and retrieval are challenging. Form documents are typically made by two types of authors; A form designer, who develops the form structure and keys, and a form user, who fills out form values based on the provided keys. Hence, the form values may not be aligned with the form designer's intention (structure and keys) if a form user gets confused. In this paper, we introduce Form-NLU, the first novel dataset for form structure understanding and its key and value information extraction, interpreting the form designer's intent and the alignment of user-written value on it. It consists of 857 form images, 6k form keys and values, and 4k table keys and values. Our dataset also includes three form types: digital, printed, and handwritten, which cover diverse form appearances and layouts. We propose a robust positional and logical relation-based form key-value information extraction framework. Using this dataset, Form-NLU, we first examine strong object detection models for the form layout understanding, then evaluate the key information extraction task on the dataset, providing fine-grained results for different types of forms and keys. Furthermore, we examine it with the off-the-shelf pdf layout extraction tool and prove its feasibility in real-world cases.

We propose a PiggyBack, a Visual Question Answering platform that allows users to apply the state-of-the-art visual-language pretrained models easily. We integrate visual-language models, pretrained by HuggingFace, an open-source API platform of deep learning technologies; however, it cannot be runnable without programming skills or deep learning understanding. Hence, our PiggyBack supports an easy-to-use browser-based user interface with several deep-learning visual language pretrained models for general users and domain experts. The PiggyBack includes the following benefits: Portability due to web-based and thus runs on almost any platform, A comprehensive data creation and processing technique, and ease of use on visual language pretrained models. The demo video can be found at https://youtu.be/iz44RZ1lF4s.

Attention mechanism has been used as an important component across Vision-and-Language(VL) tasks in order to bridge the semantic gap between visual and textual features. While attention has been widely used in VL tasks, it has not been examined the capability of different attention alignment calculation in bridging the semantic gap between visual and textual clues. In this research, we conduct a comprehensive analysis on understanding the role of attention alignment by looking into the attention score calculation methods and check how it actually represents the visual region’s and textual token’s significance for the global assessment. We also analyse the conditions which attention score calculation mechanism would be more (or less) interpretable, and which may impact the model performance on three different VL tasks, including visual question answering, text-to-image generation, text-and-image matching (both sentence and image retrieval). Our analysis is the first of its kind and provides useful insights of the importance of each attention alignment score calculation when applied at the training phase of VL tasks, commonly ignored in attention-based cross modal models, and/or pretrained models. Our code is available at: https://github.com/adlnlp/Attention_VL

Online hate speech detection has become an important issue due to the growth of online content, but resources in languages other than English are extremely limited. We introduce K-MHaS, a new multi-label dataset for hate speech detection that effectively handles Korean language patterns. The dataset consists of 109k utterances from news comments and provides a multi-label classification using 1 to 4 labels, and handles subjectivity and intersectionality. We evaluate strong baselines on K-MHaS. KR-BERT with a sub-character tokenizer outperforms others, recognizing decomposed characters in each hate speech class.

Recognizing the layout of unstructured digital documents is crucial when parsing the documents into the structured, machine-readable format for downstream applications. Recent studies in Document Layout Analysis usually rely on visual cues to understand documents while ignoring other information, such as contextual information or the relationships between document layout components, which are vital to boost better layout analysis performance. Our Doc-GCN presents an effective way to harmonize and integrate heterogeneous aspects for Document Layout Analysis. We construct different graphs to capture the four main features aspects of document layout components, including syntactic, semantic, density, and appearance features. Then, we apply graph convolutional networks to enhance each aspect of features and apply the node-level pooling for integration. Finally, we concatenate features of all aspects and feed them into the 2-layer MLPs for document layout component classification. Our Doc-GCN achieves state-of-the-art results on three widely used DLA datasets: PubLayNet, FUNSD, and DocBank. The code will be released at https://github.com/adlnlp/doc_gcn

We propose V-Doc, a question-answering tool using document images and PDF, mainly for researchers and general non-deep learning experts looking to generate, process, and understand the document visual question answering tasks. The V-Doc supports generating and using both extractive and abstractive question-answer pairs using documents images. The extractive QA selects a subset of tokens or phrases from the document contents to predict the answers, while the abstractive QA recognises the language in the content and generates the answer based on the trained model. Both aspects are crucial to understanding the documents, especially in an image format. We include a detailed scenario of question generation for the abstractive QA task. V-Doc supports a wide range of datasets and models, and is highly extensible through a declarative, framework-agnostic platform.11Data and demo video: https://github.com/usydnlp/vdoc

Text classification aims to assign labels to textual units by making use of global information. Recent studies have applied graph neural network (GNN) to capture the global word co-occurrence in a corpus. Existing approaches require that all the nodes (training and test) in a graph are present during training, which are transductive and do not naturally generalise to unseen nodes. To make those models inductive, they use extra resources, like pretrained word embedding. However, high-quality resource is not always available and hard to train. Under the extreme settings with no extra resource and limited amount of training set, can we still learn an inductive graph-based text classification model? In this paper, we introduce a novel inductive graph-based text classification framework, InducT-GCN (InducTive Graph Convolutional Networks for Text classification). Compared to transductive models that require test documents in training, we construct a graph based on the statistics of training documents only and represent document vectors with a weighted sum of word vectors. We then conduct one-directional GCN propagation during testing. Across five text classification benchmarks, our InducT-GCN outperformed state-of-the-art methods that are either transductive in nature or pre-trained additional resources. We also conducted scalability testing by gradually increasing the data size and revealed that our InducT-GCN can reduce the time and space complexity. The code is available on: https://github.com/usydnlp/InductTGCN.

Pretrained models have produced great success in both Computer Vision (CV) and Natural Language Processing (NLP). This progress leads to learning joint representations of vision and language pretraining by feeding visual and linguistic contents into a multi-layer transformer, Visual-Language Pretrained Models (VLPMs). In this paper, we present an overview of the major advances achieved in VLPMs for producing joint representations of vision and language. As the preliminaries, we briefly describe the general task definition and genetic architecture of VLPMs. We first discuss the language and vision data encoding methods and then present the mainstream VLPM structure as the core content. We further summarise several essential pretraining and fine-tuning strategies. Finally, we highlight three future directions for both CV and NLP researchers to provide insightful guidance.

Image-text retrieval task is a challenging task. It aims to measure the visual-semantic correspondence between an image and a text caption. This is tough mainly because the image lacks semantic context information as in its corresponding text caption, and the text representation is very limited to fully describe the details of an image. In this paper, we introduce Graph-based Dual-modal Representations (GraDual), including Vision-Integrated Text Embedding (VITE) and Context-Integrated Visual Embedding (CIVE), for image-text retrieval. The GraDual improves the coverage of each modality by exploiting textual context semantics for the image representation, and using visual features as a guidance for the text representation. To be specific, we design: 1) a dual-modal graph representation mechanism to solve the lack of coverage issue for each modality. 2) an intermediate graph embedding integration strategy to enhance the important pattern across other modality global features. 3) a dual-modal driven crossmodal matching network to generate a filtered representation of another modality. Extensive experiments on two benchmark datasets, MS-COCO and Flickr30K, demonstrates the superiority of the proposed GraDual in comparison to state-of-the-art methods.

Abstract As an essential component of human cognition, cause–effect relations appear frequently in text, and curating cause–effect relations from text helps in building causal networks for predictive tasks. Existing causality extraction techniques include knowledge-based, statistical machine learning (ML)-based, and deep learning-based approaches. Each method has its advantages and weaknesses. For example, knowledge-based methods are understandable but require extensive manual domain knowledge and have poor cross-domain applicability. Statistical machine learning methods are more automated because of natural language processing (NLP) toolkits. However, feature engineering is labor-intensive, and toolkits may lead to error propagation. In the past few years, deep learning techniques attract substantial attention from NLP researchers because of its powerful representation learning ability and the rapid increase in computational resources. Their limitations include high computational costs and a lack of adequate annotated training data. In this paper, we conduct a comprehensive survey of causality extraction. We initially introduce primary forms existing in the causality extraction: explicit intra-sentential causality, implicit causality, and inter-sentential causality. Next, we list benchmark datasets and modeling assessment methods for causal relation extraction. Then, we present a structured overview of the three techniques with their representative systems. Lastly, we highlight existing open challenges with their potential directions.

Recommender systems typically operate on high-dimensional sparse user-item matrices. Matrix completion is a very challenging task to predict one's interest based on millions of other users having each seen a small subset of thousands of items. We propose a G lobal-Local Kernel-based matrix completion framework, named GLocal-K, that aims to generalise and represent a high-dimensional sparse user-item matrix entry into a low dimensional space with a small number of important features. Our GLocal-K can be divided into two major stages. First, we pre-train an auto encoder with the local kernelised weight matrix, which transforms the data from one space into the feature space by using a 2d-RBF kernel. Then, the pre-trained auto encoder is fine-tuned with the rating matrix, produced by a convolution-based global kernel, which captures the characteristics of each item. We apply our GLocal-K model under the extreme low-resource setting, which includes only a user-item rating matrix, with no side information. Our model outperforms the state-of-the-art baselines on three collaborative filtering benchmarks: ML-100K, ML-1M, and Douban.

Intent classification and slot filling are two critical tasks for natural language understanding.Traditionally the two tasks proceeded independently.However, more recently joint models for intent classification and slot filling have achieved state-of-theart performance, and have proved that there exists a strong relationship between the two tasks.In this paper, we propose a bi-directional joint model for intent classification and slot filling, which includes a multi-stage hierarchical process via BERT and bi-directional joint natural language understanding mechanisms, including intent2slot and slot2intent, to obtain mutual performance enhancement between intent classification and slot filling.The evaluations show that our model achieves state-ofthe-art results on intent classification accuracy, slot filling F1, and significantly improves sentence-level semantic frame accuracy when applied to publicly available benchmark datasets, ATIS (88.6%) and SNIPS (92.8%).

The Federal Reserve System (the Fed) plays a significant role in affecting monetary policy and financial conditions worldwide. Although it is important to analyse the Fed's communications to extract useful information, it is generally long-form and complex due to the ambiguous and esoteric nature of content. In this paper, we present FedNLP, an interpretable multi-component Natural Language Processing (NLP) system to decode Federal Reserve communications. This system is designed for end-users to explore how NLP techniques can assist their holistic understanding of the Fed's communications with NO coding. Behind the scenes, FedNLP uses multiple NLP models from traditional machine learning algorithms to deep neural network architectures in each downstream task. The demonstration shows multiple results at once including sentiment analysis, summary of the document, prediction of the Federal Funds Rate movement and visualization for interpreting the prediction model's result. Our application system and demonstration are available at https://fednlp.net.

Text-to-image multimodal tasks, generating/retrieving an image from a given text description, are extremely challenging tasks since raw text descriptions cover quite limited information in order to fully describe visually realistic images.We propose a new visual contextual text representation for text-to-image multimodal tasks, VICTR, which captures rich visual semantic information of objects from the text input.First, we use the text description as initial input and conduct dependency parsing to extract the syntactic structure and analyse the semantic aspect, including object quantities, to extract the scene graph.Then, we train the extracted objects, attributes, and relations in the scene graph and the corresponding geometric relation information using Graph Convolutional Networks, and it generates text representation which integrates textual and visual semantic information.The text representation is aggregated with word-level and sentencelevel embedding to generate both visual contextual word and sentence representation.For the evaluation, we attached VICTR to the state-of-the-art models in text-to-image generation.VICTR is easily added to existing models and improves across both quantitative and qualitative aspects 1 .

Online abusive language detection (ALD) has become a societal issue of increasing importance in recent years.Several previous works in online ALD focused on solving a single abusive language problem in a single domain, like Twitter, and have not been successfully transferable to the general ALD task or domain.In this paper, we introduce a new generic ALD framework, MACAS, which is capable of addressing several types of ALD tasks across different domains.Our generic framework covers multi-aspect abusive language embeddings that represent the target and content aspects of abusive language and applies a textual graph embedding that analyses the user's linguistic behaviour.Then, we propose and use the cross-attention gate flow mechanism to embrace multiple aspects of abusive language.Quantitative and qualitative evaluation results show that our ALD algorithm rivals or exceeds the six state-of-the-art ALD algorithms across seven ALD datasets covering multiple aspects of abusive language and different online community domains.The code can be downloaded from https://github.com/usydnlp/MACAS.

Responding to social issues is very crucial because their impact can be significant to organizations or individuals. In this paper, we focus on proposing the method that identifies the personalized relevance of social issues to targets, such as individuals or organizations. To achieve this aim, we first collected trending social issues from Google Trends, micro- blog, and Internet news. Then, we obtained the well-structured document management system as a target domain that contains all activities regarding target objects. We applied the Term Frequency Inverse Document Frequency to obtain the personalized relevance weight of the social issue to a target.