ELIT: Emory Language and Information Toolkit
- URL: http://arxiv.org/abs/2109.03903v1
- Date: Wed, 8 Sep 2021 19:50:07 GMT
- Title: ELIT: Emory Language and Information Toolkit
- Authors: Han He and Liyan Xu and Jinho D. Choi
- Abstract summary: ELIT is a comprehensive framework providing transformer-based end-to-end models for core tasks.
ELIT features an efficient Multi-Task Learning (MTL) model with many downstream tasks that include lemmatization, part-of-speech tagging, named entity recognition, dependency parsing, constituency parsing, semantic role labeling, and AMR parsing.
- Score: 15.340540198612826
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We introduce ELIT, the Emory Language and Information Toolkit, which is a
comprehensive NLP framework providing transformer-based end-to-end models for
core tasks with a special focus on memory efficiency while maintaining
state-of-the-art accuracy and speed. Compared to existing toolkits, ELIT
features an efficient Multi-Task Learning (MTL) model with many downstream
tasks that include lemmatization, part-of-speech tagging, named entity
recognition, dependency parsing, constituency parsing, semantic role labeling,
and AMR parsing. The backbone of ELIT's MTL framework is a pre-trained
transformer encoder that is shared across tasks to speed up their inference.
ELIT provides pre-trained models developed on a remix of eight datasets. To
scale up its service, ELIT also integrates a RESTful Client/Server combination.
On the server side, ELIT extends its functionality to cover other tasks such as
tokenization and coreference resolution, providing an end user with agile
research experience. All resources including the source codes, documentation,
and pre-trained models are publicly available at
https://github.com/emorynlp/elit.
Related papers
- llmNER: (Zero|Few)-Shot Named Entity Recognition, Exploiting the Power of Large Language Models [1.1196013962698619]
This paper presents llmNER, a Python library for implementing zero-shot and few-shot NER with large language models (LLMs)
llmNER can compose prompts, query the model, and parse the completion returned by the LLM.
We validated our software on two NER tasks to show the library's flexibility.
arXiv Detail & Related papers (2024-06-06T22:01:59Z) - LiPost: Improved Content Understanding With Effective Use of Multi-task Contrastive Learning [2.611731148829789]
We fine-tune a pre-trained, transformer-based LLM using multi-task contrastive learning with data from a diverse set of semantic labeling tasks.
Our model outperforms the baseline on zero shot learning and offers improved multilingual support.
This work provides a robust foundation for vertical teams across LinkedIn to customize and fine-tune the LLM to their specific applications.
arXiv Detail & Related papers (2024-05-18T17:28:29Z) - Small LLMs Are Weak Tool Learners: A Multi-LLM Agent [73.54562551341454]
Large Language Model (LLM) agents significantly extend the capabilities of standalone LLMs.
We propose a novel approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer.
This modular framework facilitates individual updates and the potential use of smaller LLMs for building each capability.
arXiv Detail & Related papers (2024-01-14T16:17:07Z) - CRAFT: Customizing LLMs by Creating and Retrieving from Specialized
Toolsets [75.64181719386497]
We present CRAFT, a tool creation and retrieval framework for large language models (LLMs)
It creates toolsets specifically curated for the tasks and equips LLMs with a component that retrieves tools from these sets to enhance their capability to solve complex tasks.
Our method is designed to be flexible and offers a plug-and-play approach to adapt off-the-shelf LLMs to unseen domains and modalities, without any finetuning.
arXiv Detail & Related papers (2023-09-29T17:40:26Z) - Recommender AI Agent: Integrating Large Language Models for Interactive
Recommendations [53.76682562935373]
We introduce an efficient framework called textbfInteRecAgent, which employs LLMs as the brain and recommender models as tools.
InteRecAgent achieves satisfying performance as a conversational recommender system, outperforming general-purpose LLMs.
arXiv Detail & Related papers (2023-08-31T07:36:44Z) - Scalable Collaborative Learning via Representation Sharing [53.047460465980144]
Federated learning (FL) and Split Learning (SL) are two frameworks that enable collaborative learning while keeping the data private (on device)
In FL, each data holder trains a model locally and releases it to a central server for aggregation.
In SL, the clients must release individual cut-layer activations (smashed data) to the server and wait for its response (during both inference and back propagation).
In this work, we present a novel approach for privacy-preserving machine learning, where the clients collaborate via online knowledge distillation using a contrastive loss.
arXiv Detail & Related papers (2022-11-20T10:49:22Z) - Task Residual for Tuning Vision-Language Models [69.22958802711017]
We propose a new efficient tuning approach for vision-language models (VLMs) named Task Residual Tuning (TaskRes)
TaskRes explicitly decouples the prior knowledge of the pre-trained models and new knowledge regarding a target task.
The proposed TaskRes is simple yet effective, which significantly outperforms previous methods on 11 benchmark datasets.
arXiv Detail & Related papers (2022-11-18T15:09:03Z) - Exploiting Features and Logits in Heterogeneous Federated Learning [0.2538209532048866]
Federated learning (FL) facilitates the management of edge devices to collaboratively train a shared model.
We propose a novel data-free FL method that supports heterogeneous client models by managing features and logits.
Unlike Felo, the server has a conditional VAE in Velo, which is used for training mid-level features and generating synthetic features according to the labels.
arXiv Detail & Related papers (2022-10-27T15:11:46Z) - Deep Transfer Learning for Multi-source Entity Linkage via Domain
Adaptation [63.24594955429465]
Multi-source entity linkage is critical in high-impact applications such as data cleaning and user stitching.
AdaMEL is a deep transfer learning framework that learns generic high-level knowledge to perform multi-source entity linkage.
Our framework achieves state-of-the-art results with 8.21% improvement on average over methods based on supervised learning.
arXiv Detail & Related papers (2021-10-27T15:20:41Z) - Enabling Un-/Semi-Supervised Machine Learning for MDSE of the Real-World
CPS/IoT Applications [0.5156484100374059]
We propose a novel approach to support domain-specific Model-Driven Software Engineering (MDSE) for the real-world use-case scenarios of smart Cyber-Physical Systems (CPS) and the Internet of Things (IoT)
We argue that the majority of available data in the nature for Artificial Intelligence (AI) are unlabeled. Hence, unsupervised and/or semi-supervised ML approaches are the practical choices.
Our proposed approach is fully implemented and integrated with an existing state-of-the-art MDSE tool to serve the CPS/IoT domain.
arXiv Detail & Related papers (2021-07-06T15:51:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.