Knowledge in Triples for LLMs: Enhancing Table QA Accuracy with Semantic Extraction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917822132649984 |
|---|---|
| author | Sholehrasa, Hossein Norouzi, Sanaz Saki Hitzler, Pascal Jaberi-Douraki, Majid |
| author_facet | Sholehrasa, Hossein Norouzi, Sanaz Saki Hitzler, Pascal Jaberi-Douraki, Majid |
| contents | Integrating structured knowledge from tabular formats poses significant challenges within natural language processing (NLP), mainly when dealing with complex, semi-structured tables like those found in the FeTaQA dataset. These tables require advanced methods to interpret and generate meaningful responses accurately. Traditional approaches, such as SQL and SPARQL, often fail to fully capture the semantics of such data, especially in the presence of irregular table structures like web tables. This paper addresses these challenges by proposing a novel approach that extracts triples straightforward from tabular data and integrates it with a retrieval-augmented generation (RAG) model to enhance the accuracy, coherence, and contextual richness of responses generated by a fine-tuned GPT-3.5-turbo-0125 model. Our approach significantly outperforms existing baselines on the FeTaQA dataset, particularly excelling in Sacre-BLEU and ROUGE metrics. It effectively generates contextually accurate and detailed long-form answers from tables, showcasing its strength in complex data interpretation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_14192 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Knowledge in Triples for LLMs: Enhancing Table QA Accuracy with Semantic Extraction Sholehrasa, Hossein Norouzi, Sanaz Saki Hitzler, Pascal Jaberi-Douraki, Majid Computation and Language Information Retrieval Integrating structured knowledge from tabular formats poses significant challenges within natural language processing (NLP), mainly when dealing with complex, semi-structured tables like those found in the FeTaQA dataset. These tables require advanced methods to interpret and generate meaningful responses accurately. Traditional approaches, such as SQL and SPARQL, often fail to fully capture the semantics of such data, especially in the presence of irregular table structures like web tables. This paper addresses these challenges by proposing a novel approach that extracts triples straightforward from tabular data and integrates it with a retrieval-augmented generation (RAG) model to enhance the accuracy, coherence, and contextual richness of responses generated by a fine-tuned GPT-3.5-turbo-0125 model. Our approach significantly outperforms existing baselines on the FeTaQA dataset, particularly excelling in Sacre-BLEU and ROUGE metrics. It effectively generates contextually accurate and detailed long-form answers from tables, showcasing its strength in complex data interpretation. |
| title | Knowledge in Triples for LLMs: Enhancing Table QA Accuracy with Semantic Extraction |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2409.14192 |