Search Results for author:
Found 28 papers, 13 papers with code
基于风格化嵌入的中文文本风格迁移(Chinese text style transfer based on stylized embedding)
“对话风格能够反映对话者的属性, 例如情感、性别和教育背景等。在对话系统中, 通过理解用户的对话风格, 能够更好地对用户进行建模。同样的, 面对不同背景的用户, 对话机器人也应该使用不同的语言风格与之交流。语言表达风格是文本的内在属性, 然而现有的大多数文本风格迁移研究, 集中在英文领域, 在中文领域则研究较少。本文构建了三个可用于中文文本风格迁移研究的数据集, 并将多种已有的文本风格迁移方法应用于该数据集。同时, 本文提出了基于DeepStyle算法与Transformer的风格迁移模型, 通过预训练可以获得不同风格的隐层向量表示。并基于Transformer构建生成端模型, 在解码阶段, 通过重建源文本的方式, 保留生成文本的内容信息, 并且引入对立风格的嵌入表示, 使得模型能够生成不同风格的文本。实验结果表明, 本文提出的模型在构建的中文数据集上均优于现有模型。”
Efficient Training of Multi-task Neural Solver with Multi-armed Bandits
Efficiently training a multi-task neural solver for various combinatorial optimization problems (COPs) has been less studied so far.
Targeted Analysis of High-Risk States Using an Oriented Variational Autoencoder
Variational autoencoder (VAE) neural networks can be trained to generate power system states that capture both marginal distribution and multivariate dependencies of historical data.
ASP: Learn a Universal Neural Solver!
Applying machine learning to combinatorial optimization problems has the potential to improve both efficiency and accuracy.
Comprehensive Analysis of Over-smoothing in Graph Neural Networks from Markov Chains Perspective
Results show that our proposed sufficient condition can effectively improve over-smoothing problem in operator-inconsistent GNN and enhance the performance of the model.
Benchmarking Language Models for Code Syntax Understanding
Our key observation is that existing language models pretrained on code still lack the understanding of code syntax.
PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion
For instance, we outperform the fully finetuning approaches on a KG completion benchmark by tuning only 1% of the parameters.
Ranked #5 on
Link Prediction
on UMLS
IELM: An Open Information Extraction Benchmark for Pre-Trained Language Models
Instead of focusing on pre-defined relations, we create an OIE benchmark aiming to fully examine the open relational information present in the pre-trained LMs.
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
In this work, we take the first step to exploit the pre-trained (unfine-tuned) weights to mitigate backdoors in fine-tuned language models.
Joint Language Semantic and Structure Embedding for Knowledge Graph Completion
Unlike previous approaches that rely on either the structures or semantics of the knowledge graphs, we propose to jointly embed the semantics in the natural language description of the knowledge triplets with their structure information.
Ranked #3 on
Link Prediction
on UMLS
Generating Contextual Load Profiles Using a Conditional Variational Autoencoder
Generating power system states that have similar distribution and dependency to the historical ones is essential for the tasks of system planning and security assessment, especially when the historical data is insufficient.
DeepStruct: Pretraining of Language Models for Structure Prediction
We introduce a method for improving the structural understanding abilities of language models.
Ranked #1 on
Named Entity Recognition (NER)
on ACE2005
Protecting Intellectual Property of Language Generation APIs with Lexical Watermark
Nowadays, due to the breakthrough in natural language generation (NLG), including machine translation, document summarization, image captioning, etc NLG models have been encapsulated in cloud APIs to serve over half a billion people worldwide and process over one hundred billion word generations per day.
A Game-Theoretic Approach for Improving Generalization Ability of TSP Solvers
In this paper, we introduce a two-player zero-sum framework between a trainable \emph{Solver} and a \emph{Data Generator} to improve the generalization ability of deep learning-based solvers for Traveling Salesman Problem (TSP).
Generating Multivariate Load States Using a Conditional Variational Autoencoder
In this paper, a multivariate load state generating model on the basis of a conditional variational autoencoder (CVAE) neural network is proposed.
Zero-Shot Information Extraction as a Unified Text-to-Triple Translation
We cast a suite of information extraction tasks into a text-to-triple translation framework.
Ranked #1 on
Open Information Extraction
on OIE2016
(using extra training data)
Learning Graph Representation by Aggregating Subgraphs via Mutual Information Maximization
For this purpose, we propose a universal framework to generate subgraphs in an auto-regressive way and then using these subgraphs to guide the learning of graph representation by Graph Neural Networks.
Language Models are Open Knowledge Graphs
This paper shows how to construct knowledge graphs (KGs) from pre-trained language models (e. g., BERT, GPT-2/3), without human supervision.
Training Strategies for Autoencoder-based Detection of False Data Injection Attacks
The security of energy supply in a power grid critically depends on the ability to accurately estimate the state of the system.
Detection of False Data Injection Attacks Using the Autoencoder Approach
State estimation is of considerable significance for the power system operation and control.
Transformer on a Diet
Transformer has been widely used thanks to its ability to capture sequence information in an efficient way.
Meta-Path Constrained Random Walk Inference for Large-Scale Heterogeneous Information Networks
It is impractical for users to provide the meta-path(s) to support the large scale inference, and biased examples will result in incorrect meta-path based inference, thus limit the power of the meta-path.
PoD: Positional Dependency-Based Word Embedding for Aspect Term Extraction
Dependency context-based word embedding jointly learns the representations of word and dependency context, and has been proved effective in aspect term extraction.
GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating).
Language Models with Transformers
In this paper, we explore effective Transformer architectures for language model, including adding additional LSTM layers to better capture the sequential context while still keeping the computation efficient.
Ranked #2 on
Language Modelling
on Penn Treebank (Word Level)
(using extra training data)
CROWD-IN-THE-LOOP: A Hybrid Approach for Annotating Semantic Roles
Crowdsourcing has proven to be an effective method for generating labeled data for a range of NLP tasks.
World Knowledge as Indirect Supervision for Document Clustering
We provide three ways to specify the world knowledge to domains by resolving the ambiguity of the entities and their types, and represent the data with world knowledge as a heterogeneous information network.
