Search Results for author:
Found 35 papers, 23 papers with code
Discrete Opinion Tree Induction for Aspect-based Sentiment Analysis
Dependency trees have been intensively used with graph neural networks for aspect-based sentiment classification.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Inducing Target-Specific Latent Structures for Aspect Sentiment Classification
Aspect-level sentiment analysis aims to recognize the sentiment polarity of an aspect or a target in a comment.
Multi-scale 2D Temporal Map Diffusion Models for Natural Language Video Localization
Our method involves the direct generation of a global 2D temporal map via a conditional denoising diffusion process, based on the input video and language query.
Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks
This finding motivates us to present a novel method that aims to harden GCNs by automatically learning Latent Homophilic Structures over heterophilic graphs.
Ranked #3 on
Node Classification
on Actor
How Well Do Text Embedding Models Understand Syntax?
Text embedding models have significantly contributed to advancements in natural language processing by adeptly capturing semantic properties of textual data.
GLoRE: Evaluating Logical Reasoning of Large Language Models
Recently, large language models (LLMs), including notable models such as GPT-4 and burgeoning community models, have showcased significant general language understanding abilities.
Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
Large language models (LLMs) have shown the ability to produce fluent and cogent content, presenting both productivity opportunities and societal risks.
Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis
Multimodal relation extraction (MRE) is the task of identifying the semantic relationships between two entities based on the context of the sentence image pair.
Exploring Self-supervised Logic-enhanced Training for Large Language Models
Existing efforts to improve logical reasoning ability of language models have predominantly relied on supervised fine-tuning, hindering generalization to new domains and/or tasks.
Non-Autoregressive Document-Level Machine Translation
However, current NAT models still have a significant performance gap compared to their AT counterparts.
LogiCoT: Logical Chain-of-Thought Instruction-Tuning
LogiCoT serves as an instruction set for teaching models of logical reasoning and elicits general reasoning skills.
Target-Side Augmentation for Document-Level Machine Translation
Document-level machine translation faces the challenge of data sparsity due to its long input length and a small amount of training data, increasing the risk of learning spurious patterns.
Token-Level Fitting Issues of Seq2seq Models
Sequence-to-sequence (seq2seq) models have been widely used for natural language processing, computer vision, and other deep learning tasks.
Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4
With the release of Generative Pretrained Transformer 4 (GPT-4), highlighted as "advanced" at reasoning tasks, we are eager to learn the GPT-4 performance on various logical reasoning tasks.
Contrastive Latent Variable Models for Neural Text Generation
Experiments on various text generation benchmarks show the effectiveness of our proposed method.
YATO: Yet Another deep learning based Text analysis Open toolkit
Designed in a hierarchical structure, YATO supports free combinations of three types of widely used features including 1) traditional neural networks (CNN, RNN, etc.
METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweets
To further investigate tweet users' attitudes toward specific entities, 4 types of entities (Person, Organization, Drug, and Vaccine) are selected and annotated with user sentiments, resulting in a targeted sentiment dataset with 9, 101 entities (in 5, 278 tweets).
Pre-Training a Graph Recurrent Network for Language Representation
Transformer-based pre-trained models have gained much advance in recent years, becoming one of the most important backbones in natural language processing.
Solving Aspect Category Sentiment Analysis as a Text Generation Task
Aspect category sentiment analysis has attracted increasing research attention.
G-Transformer for Document-level Machine Translation
However, study shows that when we further enlarge the translation unit to a whole document, supervised training of Transformer can fail.
SemGloVe: Semantic Co-occurrences for GloVe from BERT
In this paper, we propose SemGloVe, which distills semantic co-occurrences from BERT into static GloVe word embeddings.
End-to-End Chinese Parsing Exploiting Lexicons
Chinese parsing has traditionally been solved by three pipeline systems including word-segmentation, part-of-speech tagging and dependency parsing modules.
Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation
With the help of these strategies, we are able to train a model with fewer parameters while maintaining the model capacity.
Dialogue State Induction Using Neural Latent Variable Models
Dialogue state modules are a useful component in a task-oriented dialogue system.
Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning
We focus on graph-to-sequence learning, which can be framed as transducing graph structures to sequences for text generation.
Two Local Models for Neural Constituent Parsing
Non-local features have been exploited by syntactic parsers for capturing dependencies between sub output structures.
Combining Discrete and Neural Features for Sequence Labeling
Our results on standard benchmarks show that state-of-the-art neural models can give accuracies comparable to the best discrete models in the literature for most tasks and combing discrete and neural features unanimously yield better results.
Head-Lexicalized Bidirectional Tree LSTMs
In this paper, we propose a method for automatic head-lexicalization for tree-structure LSTMs, propagating head words from leaf nodes to every constituent node.
Measuring the Information Content of Financial News
Measuring the information content of news text is useful for decision makers in their investments since news information can influence the intrinsic values of companies.
Bidirectional Tree-Structured LSTM with Head Lexicalization
In this paper, we propose a method for automatic head-lexicalization for tree-structure LSTMs, propagating head words from leaf nodes to every constituent node.
LibN3L:A Lightweight Package for Neural NLP
We present a light-weight machine learning tool for NLP research.
