Papers with domain-specific language models

7 papers
Knowledge-enhanced Response Generation in Dialogue Systems: Current Advancements and Emerging Horizons (2024.lrec-tutorials)

Copied to clipboard

Challenge: Knowledge-enhanced Dialogue Systems (KEDS) are a new approach to enhancing human-machine interaction through natural language.
Approach: This tutorial provides an in-depth exploration of Knowledge-enhanced Dialogue Systems (KEDS) it aims to elucidate their significance, highlight advances made using deep learning, and pinpoint the current challenges.
Outcome: The tutorial aims to give attendees a comprehensive understanding of KEDS, and highlight advances made using deep learning and pinpoint the current challenges.
Evaluating Pretraining Strategies for Clinical BERT Models (2022.lrec-1)

Copied to clipboard

Challenge: Existing generic language models in specialized domains may be sub-optimal due to domain differences.
Approach: They propose various strategies for adapting a generic language model to the target domain and various forms of vocabulary modifications to fine-tune it.
Outcome: The proposed strategies outperform a general-domain language model but little difference in performance between the models.
BUSTER: a “BUSiness Transaction Entity Recognition” dataset (2023.emnlp-industry)

Copied to clipboard

Challenge: Natural Language Processing has seen major breakthroughs in the last few years, but transferring these advances into industry applications can be difficult.
Approach: They propose to use a BUSiness Transaction Entity Recognition dataset to support industry-oriented research by exploiting both general-purpose and domain-specific language models.
Outcome: The proposed model is the best performing model and an additional silver corpus to BUSTER.
MedDistant19: Towards an Accurate Benchmark for Broad-Coverage Biomedical Relation Extraction (2022.coling-1)

Copied to clipboard

Challenge: Relation extraction in the biomedical domain is challenging due to the lack of labeled data and high annotation costs.
Approach: They propose to use distant supervision to pair knowledge graph relationships with raw texts to tackle the scarcity of annotated data and to validate their results.
Outcome: The proposed benchmarks are more accurate and consistent with existing benchmarks and show that there is no train-test leakage.
EconBERTa: Towards Robust Extraction of Named Entities in Economics (2023.findings-emnlp)

Copied to clipboard

Challenge: Adapting general-purpose language models to specific domains has proven to be effective in tackling downstream tasks such as impact evaluation.
Approach: They propose to use EconBERTa, a large language model pretrained on scientific publications in economics, and ECON-IE, based on an expert-annotated dataset of economics abstracts for Named Entity Recognition (NER).
Outcome: The proposed model outperforms EconBERTa on the downstream NER task and ECON-IE on the economics abstracts.
VE-KD: Vocabulary-Expansion Knowledge-Distillation for Training Smaller Domain-Specific Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: VE-KD is a method that balances knowledge distillation and vocabulary expansion with the aim of training efficient domain-specific language models.
Approach: They propose a method that balances knowledge distillation and vocabulary expansion with the aim of training efficient domain-specific language models.
Outcome: VE-KD outperforms DistilBERT and Adapt-and-Distill in biomedical domain tasks . compared with other methods, it outperformed Distilbert and adapted-and distill .
PPORTAL_ner: An Annotated Corpus of Portuguese Literary Entities (2024.lrec-main)

Copied to clipboard

Challenge: Annotated corpus of 25 literary texts provides a rich set of annotations for Named Entity Recognition models.
Approach: They propose an annotation dataset that simplifies the development of Named Entity Recognition models for Portuguese literary texts.
Outcome: The proposed dataset simplifies the development of Named Entity Recognition models for Portuguese literary works.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations