Search Results for author:
Found 19 papers, 7 papers with code
A Study on Entity Linking Across Domains”:" Which Data is Best for Fine-Tuning?
In particular, we represent the entities of different KGs in a joint vector space and address the questions of which data is best suited for creating and fine-tuning that space, and whether fine-tuning harms performance on the general domain.
Discourse-Aware In-Context Learning for Temporal Expression Normalization
In this work, we explore the feasibility of proprietary and open-source large language models (LLMs) for TE normalization using in-context learning to inject task, document, and example information into the model.
Rehearsal-Free Modular and Compositional Continual Learning for Language Models
Continual learning aims at incrementally acquiring new knowledge while not forgetting existing knowledge.
GradSim: Gradient-Based Language Grouping for Effective Multilingual Training
However, not all languages positively influence each other and it is an open research question how to select the most suitable set of languages for multilingual training and avoid negative interference among languages whose characteristics or data distributions are not compatible.
TADA: Efficient Task-Agnostic Domain Adaptation for Transformers
Our broad evaluation in 4 downstream tasks for 14 domains across single- and multi-domain setups and high- and low-resource scenarios reveals that TADA is an effective and efficient alternative to full domain-adaptive pre-training and adapters for domain adaptation, while not introducing additional parameters or complex training steps.
NLNDE at SemEval-2023 Task 12: Adaptive Pretraining and Source Language Selection for Low-Resource Multilingual Sentiment Analysis
In this work, we propose to leverage language-adaptive and task-adaptive pretraining on African texts and study transfer learning with source language selection on top of an African language-centric pretrained language model.
Multilingual Normalization of Temporal Expressions with Masked Language Models
The detection and normalization of temporal expressions is an important task and preprocessing step for many applications.
CLIN-X: pre-trained language models and a study on cross-task transfer for concept extraction in the clinical domain
The field of natural language processing (NLP) has recently seen a large change towards using pre-trained language models for solving almost any task.
Boosting Transformers for Job Expression Extraction and Classification in a Low-Resource Setting
In this paper, we explore possible improvements of transformer models in a low-resource setting.
Enriched Attention for Robust Relation Extraction
The performance of relation extraction models has increased considerably with the rise of neural networks.
To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning
For this, we study the effects of model transfer on sequence labeling across various domains and tasks and show that our methods based on model similarity and support vector machines are able to predict promising sources, resulting in performance increases of up to 24 F1 points.
NLNDE at CANTEMIST: Neural Sequence Labeling and Parsing Approaches for Clinical Concept Extraction
The recognition and normalization of clinical information, such as tumor morphology mentions, is an important, but complex process consisting of multiple subtasks.
A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios
Deep neural networks and huge language models are becoming omnipresent in natural language applications.
NLNDE: Enhancing Neural Sequence Taggers with Attention and Noisy Channel for Robust Pharmacological Entity Detection
Named entity recognition has been extensively studied on English news texts.
NLNDE: The Neither-Language-Nor-Domain-Experts' Way of Spanish Medical Document De-Identification
Natural language processing has huge potential in the medical domain which recently led to a lot of research in this field.
Closing the Gap: Joint De-Identification and Concept Extraction in the Clinical Domain
Exploiting natural language processing in the clinical domain requires de-identification, i. e., anonymization of personal information in texts.
On the Choice of Auxiliary Languages for Improved Sequence Tagging
Recent work showed that embeddings from related languages can improve the performance of sequence tagging, even for monolingual models.
Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text
Although temporal tagging is still dominated by rule-based systems, there have been recent attempts at neural temporal taggers.
Ranked #1 on
Temporal Tagging
on Catalan TimeBank 1.0
