Papers with Language Modeling
Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that LLMs face challenges in effectively using retrieved information . authors propose a method that considers LLM as "Information Refiner" |
| Approach: | They propose a method that considers LLMs as "Information Refiners" they propose INFO-RAG, which is low-cost and general across various tasks . |
| Outcome: | The proposed method improves performance of LLaMA2 by 9.39% relative points . it is low-cost and general across various tasks, and is robust and in-context learning is possible . |
uniblock: Scoring and Filtering Corpus with Unicode Block Information (D19-1)
Copied to clipboard
| Challenge: | Existing methods to remove sentences consisting of illegal characters are tedious and repetitive. |
| Approach: | They propose a statistical method to identify illegal characters in natural language processing . they use a fixed-size feature vector to generate a Gaussian mixture model for each sentence . |
| Outcome: | The proposed method can score sentences and filter corpus on clean corpus and improve performance. |
FQuAD2.0: French Question Answering and Learning When You Don’t Know (2022.lrec-1)
Copied to clipboard
| Challenge: | Question Answering, including Reading Comprehension, has seen significant scientific breakthroughs over the past few years . but most of these breakthroughs are centered on the English language . |
| Approach: | They propose a dataset to train Question Answering models in the French language . they extend the dataset to 17,000+ unanswerable questions annotated adversarially . |
| Outcome: | The proposed dataset makes it possible to train French Question Answering models with the ability to distinguish unanswerable questions from answerable ones. |
MOSAICo: a Multilingual Open-text Semantically Annotated Interlinked Corpus (2024.naacl-long)
Copied to clipboard
Simone Conia, Edoardo Barba, Abelardo Carlos Martinez Lorenzo, Pere-Lluís Huguet Cabot, Riccardo Orlando, Luigi Procopio, Roberto Navigli
| Challenge: | Existing approaches to integrate semantics into Natural Language Understanding (NLP) systems are cost-effective and environmental impact-related. |
| Approach: | They propose to provide semantically-annotated corpora for four NLU tasks across five languages and to drop the requirement of closed datasets. |
| Outcome: | The proposed model provides hundreds of millions of silver yet high-quality annotations for four NLU tasks across five languages. |
Minority Positive Sampling for Switching Points - an Anecdote for the Code-Mixing Language Modeling (2020.lrec-1)
Copied to clipboard
| Challenge: | Multilingual people code-mix using English phonetic typing and insertion of anglicisms in their native language. |
| Approach: | They propose to use minority positive sampling to selectively induce more sample to achieve better performance. |
| Outcome: | The proposed model performs better than other models, but switching points are the main challenge . |