Search Results for author:
Found 13 papers, 4 papers with code
Beyond Text: Incorporating Metadata and Label Structure for Multi-Label Document Classification using Heterogeneous Graphs
The other is label heterogeneous graph, which is constructed based on both the labels’ hierarchy and their statistical dependencies.
Implicit Sentiment Analysis with Event-centered Text Representation
Implicit sentiment analysis, aiming at detecting the sentiment of a sentence without sentiment words, has become an attractive research topic in recent years.
A Novel Framework Based on Medical Concept Driven Attention for Explainable Medical Code Prediction via External Knowledge
Medical code prediction from clinical notes aims at automatically associating medical codes with the clinical notes.
A Multi-label Multi-hop Relation Detection Model based on Relation-aware Sequence Generation
Therefore, in this paper, multi-hop relation detection is considered as a multi-label learning problem.
A Divide-And-Conquer Approach for Multi-label Multi-hop Relation Detection in Knowledge Base Question Answering
However, most of existing approaches only detect one single path to obtain the answer without considering other correct paths, which might affect the final performance.
Pre-training and Fine-tuning Neural Topic Model: A Simple yet Effective Approach to Incorporating External Knowledge
Recent years have witnessed growing interests in incorporating external knowledge such as pre-trained word embeddings (PWEs) or pre-trained language models (PLMs) into neural topic modeling.
Temporal Knowledge Graph Completion with Approximated Gaussian Process Embedding
Due to their incompleteness, a fundamental task for KGs, which is known as Knowledge Graph Completion (KGC), is to perform link prediction and infer new facts based on the known facts.
Fine-grainedly Synthesize Streaming Data Based On Large Language Models With Graph Structure Understanding For Data Sparsity
Due to the sparsity of user data, sentiment analysis on user reviews in e-commerce platforms often suffers from poor performance, especially when faced with extremely sparse user data or long-tail labels.
Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment
In specific, causal intervention is implemented by designing the prompts without accessing the parameters and logits of LLMs. The chain-of-thoughts generated by LLMs are employed as the mediator variable and the causal effect between the input prompt and the output answers is calculated through front-door adjustment to mitigate model biases.
Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment
Conventional multi-hop fact verification models are prone to rely on spurious correlations from the annotation artifacts, leading to an obvious performance decline on unbiased datasets.
DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference
However, most of the present debiasing methods focus on single-variable causal inference, which is not suitable for ABSA with two input variables (the target aspect and the review).
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models
For poor model calibration, we incorporate the regularization method during LoRA training to keep the model from being over-confident, and the Monte-Carlo dropout mechanism is employed to enhance the uncertainty estimation.
SEE-Few: Seed, Expand and Entail for Few-shot Named Entity Recognition
Current few-shot NER methods focus on leveraging existing datasets in the rich-resource domains which might fail in a training-from-scratch setting where no source-domain data is used.
