Search Results for author:
Found 40 papers, 24 papers with code
RoViST: Learning Robust Metrics for Visual Storytelling
We measure the reliability of our metric sets by analysing its correlation with human judgement scores on a sample of machine stories obtained from 4 state-of-the-arts models trained on the Visual Storytelling Dataset (VIST).
Do Text-to-Vis Benchmarks Test Real Use of Visualisations?
Large language models are able to generate code for visualisations in response to user requests.
3M-Health: Multimodal Multi-Teacher Knowledge Distillation for Mental Health Detection
The significance of mental health classification is paramount in contemporary society, where digital platforms serve as crucial sources for monitoring individuals' well-being.
Game-MUG: Multimodal Oriented Game Situation Understanding and Commentary Generation Dataset
In addition, we also propose a new audience conversation augmented commentary dataset by covering the game situation and audience conversation understanding, and introducing a robust joint multimodal dual learning model as a baseline.
MM-EMOG: Multi-Label Emotion Graph Representation for Mental Health Classification on Social Media
Then, it is trained by multi-label emotions and conducts a graph propagation for harmonising heterogeneous emotional information, and is applied to a textual graph mental health classification.
3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding
This paper presents a groundbreaking multimodal, multi-task, multi-teacher joint-grained knowledge distillation model for visually-rich form document understanding.
SCO-VIST: Social Interaction Commonsense Knowledge-based Visual Storytelling
This weighted story graph produces the storyline in a sequence of events using Floyd-Warshall's algorithm.
Re-Temp: Relation-Aware Temporal Representation Learning for Temporal Knowledge Graph Completion
Temporal Knowledge Graph Completion (TKGC) under the extrapolation setting aims to predict the missing entity from a fact in the future, posing a challenge that aligns more closely with real-world prediction problems.
MC-DRE: Multi-Aspect Cross Integration for Drug Event/Entity Extraction
Extracting meaningful drug-related information chunks, such as adverse drug events (ADE), is crucial for preventing morbidity and saving many lives.
Workshop on Document Intelligence Understanding
Document understanding and information extraction include different tasks to understand a document and extract valuable information automatically.
Tri-level Joint Natural Language Understanding for Multi-turn Conversational Datasets
We present a novel tri-level joint natural language understanding approach, adding domain, and explicitly exchange semantic information between all levels.
SimCGNN: Simple Contrastive Graph Neural Network for Session-based Recommendation
Session-based recommendation (SBR) problem, which focuses on next-item prediction for anonymous users, has received increasingly more attention from researchers.
StockEmotions: Discover Investor Emotions for Financial Sentiment Analysis and Multivariate Time Series
There has been growing interest in applying NLP techniques in the financial domain, however, resources are extremely limited.
Emotion Classification
Multivariate Time Series Forecasting
+2
Spoken Language Understanding for Conversational AI: Recent Advances and Future Direction
This tutorial will discuss how the joint task is set up and introduce Spoken Language Understanding/Natural Language Understanding (SLU/NLU) with Deep Learning techniques.
SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering
To make explicit teaching of the relations between the two modalities, we proposed and integrated two attention modules, namely a scene graph-based semantic relation-aware attention and a positional relation-aware attention.
Optical Character Recognition
Optical Character Recognition (OCR)
+3
SG-Shuffle: Multi-aspect Shuffle Transformer for Scene Graph Generation
Scene Graph Generation (SGG) serves a comprehensive representation of the images for human understanding as well as visual understanding tasks.
An Analysis of Deep Reinforcement Learning Agents for Text-based Games
Text-based games(TBG) are complex environments which allow users or computer agents to make textual interactions and achieve game goals. In TBG agent design and training process, balancing the efficiency and performance of the agent models is a major challenge.
SUPER-Rec: SUrrounding Position-Enhanced Representation for Recommendation
Collaborative filtering problems are commonly solved based on matrix completion techniques which recover the missing values of user-item interaction matrices.
Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis
Recognizing the layout of unstructured digital documents is crucial when parsing the documents into the structured, machine-readable format for downstream applications.
Understanding Attention for Vision-and-Language Tasks
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.
A Quantitative and Qualitative Analysis of Suicide Ideation Detection using Deep Learning
For preventing youth suicide, social media platforms have received much attention from researchers.
InducT-GCN: Inductive Graph Convolutional Networks for Text Classification
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?
RoViST:Learning Robust Metrics for Visual Storytelling
We measure the reliability of our metric sets by analysing its correlation with human judgement scores on a sample of machine stories obtained from 4 state-of-the-arts models trained on the Visual Storytelling Dataset (VIST).
ME-GCN: Multi-dimensional Edge-Embedded Graph Convolutional Networks for Semi-supervised Text Classification
Our ME-GCN can integrate a rich source of graph edge information of the entire text corpus.
Understanding Graph Convolutional Networks for Text Classification
Graph Convolutional Networks (GCN) have been effective at tasks that have rich relational structure and can preserve global structure information of a dataset in graph embeddings.
Bi-directional Joint Neural Networks for Intent Classification and Slot Filling
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.
GLocal-K: Global and Local Kernels for Recommender Systems
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.
Ranked #1 on
Recommendation Systems
on Douban Monti
FedNLP: An interpretable NLP System to Decode Federal Reserve Communications
The Federal Reserve System (the Fed) plays a significant role in affecting monetary policy and financial conditions worldwide.
CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection
Accompanying the dataset is a thorough in-game toxicity analysis, which provides comprehensive understanding of context at utterance, token, and dual levels.
Local Interpretations for Explainable Natural Language Processing: A Survey
As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models.
Deep Structured Feature Networks for Table Detection and Tabular Data Extraction from Scanned Financial Document Images
The main contributions of this paper are proposing the Financial Documents dataset with table-area annotations, the superior detection model and the rule-based layout segmentation technique for the tabular data extraction from PDF files.
Optical Character Recognition
Optical Character Recognition (OCR)
+1
Event-Driven LSTM For Forex Price Prediction
The majority of studies in the field of AI guided financial trading focus on purely applying machine learning algorithms to continuous historical price and technical analysis data.
A Survey on Extraction of Causal Relations from Natural Language Text
Existing causality extraction techniques include knowledge-based, statistical machine learning(ML)-based, and deep learning-based approaches.
VICTR: Visual Information Captured Text Representation for Text-to-Vision Multimodal Tasks
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.
Detect All Abuse! Toward Universal Abusive Language Detection Models
Online abusive language detection (ALD) has become a societal issue of increasing importance in recent years.
VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks
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.
Ranked #23 on
Text-to-Image Generation
on MS COCO
(Inception score metric)
REXUP: I REason, I EXtract, I UPdate with Structured Compositional Reasoning for Visual Question Answering
Visual question answering (VQA) is a challenging multi-modal task that requires not only the semantic understanding of both images and questions, but also the sound perception of a step-by-step reasoning process that would lead to the correct answer.
AMI-Net+: A Novel Multi-Instance Neural Network for Medical Diagnosis from Incomplete and Imbalanced Data
In medical real-world study (RWS), how to fully utilize the fragmentary and scarce information in model training to generate the solid diagnosis results is a challenging task.
Attention-based Multi-instance Neural Network for Medical Diagnosis from Incomplete and Low Quality Data
However, in many real-world cases, data is often of low-quality due to a variety of reasons, such as data consistency, integrity, completeness, accuracy, etc.
CNN based Multi-Instance Multi-Task Learning for Syndrome Differentiation of Diabetic Patients
Inspired from it, we employ multi-instance multi-task learning combined with the convolutional neural network (MIMT-CNN) for syndrome differentiation, which takes region proposals as input and output image labels directly.
