Search Results for author:
Found 24 papers, 18 papers with code
Text Role Classification in Scientific Charts Using Multimodal Transformers
The models are evaluated on various chart datasets, and results show that LayoutLMv3 outperforms UDOP in all experiments.
GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding
Language models can serve as a valuable tool for software developers to increase productivity.
Open-World Lifelong Graph Learning
We study the problem of lifelong graph learning in an open-world scenario, where a model needs to deal with new tasks and potentially unknown classes.
Fine-Tuning Language Models for Scientific Writing Support
Firstly, we propose a regression model trained on a corpus of scientific sentences extracted from peer-reviewed scientific papers and non-scientific text to assign a score that indicates the scientificness of a sentence.
The Split Matters: Flat Minima Methods for Improving the Performance of GNNs
We investigate flat minima methods and combinations of those methods for training graph neural networks (GNNs).
Memorization of Named Entities in Fine-tuned BERT Models
One such risk is training data extraction from language models that have been trained on datasets, which contain personal and privacy sensitive information.
Transformers are Short Text Classifiers: A Study of Inductive Short Text Classifiers on Benchmarks and Real-world Datasets
Short text classification is a crucial and challenging aspect of Natural Language Processing.
Ranked #1 on
Text Classification
on TREC-10
Event and Entity Extraction from Generated Video Captions
Our experiments show that it is possible to extract entities, their properties, relations between entities, and the video category from the generated captions.
Are We Really Making Much Progress in Text Classification? A Comparative Review
This study reviews and compares methods for single-label and multi-label text classification, categorized into bag-of-words, sequence-based, graph-based, and hierarchical methods.
Multi-Label Classification
Multi Label Text Classification
+2
Graph Summarization with Graph Neural Networks
A graph summary based on equivalence classes preserves pre-defined features of a graph's vertex within a $k$-hop neighborhood such as the vertex labels and edge labels.
Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes
The combination of these two challenges is particularly relevant since newly emerging classes typically resemble only a tiny fraction of the data, adding to the already skewed class distribution.
Cross-Architecture Distillation Using Bidirectional CMOW Embeddings
We match or exceed the scores of ELMo, and only fall behind more expensive models on linguistic acceptability.
General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings
We match or exceed the scores of ELMo for all tasks of the GLUE benchmark except for the sentiment analysis task SST-2 and the linguistic acceptability task CoLA.
Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP
We show that a wide multi-layer perceptron (MLP) using a Bag-of-Words (BoW) outperforms the recent graph-based models TextGCN and HeteGCN in an inductive text classification setting and is comparable with HyperGAT.
Analysis of GraphSum's Attention Weights to Improve the Explainability of Multi-Document Summarization
We observe a high correlation between the attention weights and this reference metric, especially on the the later decoding layers of the transformer architecture.
rx-anon -- A Novel Approach on the De-Identification of Heterogeneous Data based on a Modified Mondrian Algorithm
To control the influence of anonymization over unstructured textual data versus structured data attributes, we introduce a modified, parameterized Mondrian algorithm.
Recommendations for Item Set Completion: On the Semantics of Item Co-Occurrence With Data Sparsity, Input Size, and Input Modalities
In conclusion, it is crucial to consider the semantics of the item co-occurrence for the choice of an appropriate recommendation model and carefully decide which metadata to exploit.
A Comparison of Deep-Learning Methods for Analysing and Predicting Business Processes
In contrast to existing studies, we evaluate our models' performance at different stages of a process, determined by quartiles of the number of events and normalized quarters of the case duration.
Online Learning of Graph Neural Networks: When Can Data Be Permanently Deleted
In most cases, i. e., 15 out 18 experiments, we even observe that a temporal window of size 1 is sufficient to retain at least 90%.
Lifelong Learning of Graph Neural Networks for Open-World Node Classification
Graph neural networks (GNNs) have emerged as the standard method for numerous tasks on graph-structured data such as node classification.
Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels
We present multi-modal adversarial autoencoders for recommendation and evaluate them on two different tasks: citation recommendation and subject label recommendation.
Can Graph Neural Networks Go "Online"? An Analysis of Pretraining and Inference
In this setup, we compare adapting pretrained graph neural networks against retraining from scratch.
CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model
In order to address this shortcoming, we propose a learning algorithm for the Continuous Matrix Space Model, which we call Continual Multiplication of Words (CMOW).
Using Titles vs. Full-text as Source for Automated Semantic Document Annotation
For the first time, we offer a systematic comparison of classification approaches to investigate how far semantic annotations can be conducted using just the metadata of the documents such as titles published as labels on the Linked Open Data cloud.
