Search Results for author:
Found 17 papers, 9 papers with code
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.
Form-NLU: Dataset for the Form Language Understanding
Compared to general document analysis tasks, form document structure understanding and retrieval are challenging.
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.
PiggyBack: Pretrained Visual Question Answering Environment for Backing up Non-deep Learning Professionals
We propose a PiggyBack, a Visual Question Answering platform that allows users to apply the state-of-the-art visual-language pretrained models easily.
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.
Vision-and-Language Pretrained Models: A Survey
Pretrained models have produced great success in both Computer Vision (CV) and Natural Language Processing (NLP).
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
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.
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 #24 on
Text-to-Image Generation
on COCO
(Inception score metric)
