Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910286389182464 |
|---|---|
| author | Schneider, Phillip Klettner, Manuel Jokinen, Kristiina Simperl, Elena Matthes, Florian |
| author_facet | Schneider, Phillip Klettner, Manuel Jokinen, Kristiina Simperl, Elena Matthes, Florian |
| contents | Conversational question answering systems often rely on semantic parsing to enable interactive information retrieval, which involves the generation of structured database queries from a natural language input. For information-seeking conversations about facts stored within a knowledge graph, dialogue utterances are transformed into graph queries in a process that is called knowledge-based conversational question answering. This paper evaluates the performance of large language models that have not been explicitly pre-trained on this task. Through a series of experiments on an extensive benchmark dataset, we compare models of varying sizes with different prompting techniques and identify common issue types in the generated output. Our results demonstrate that large language models are capable of generating graph queries from dialogues, with significant improvements achievable through few-shot prompting and fine-tuning techniques, especially for smaller models that exhibit lower zero-shot performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01711 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs Schneider, Phillip Klettner, Manuel Jokinen, Kristiina Simperl, Elena Matthes, Florian Computation and Language Information Retrieval Conversational question answering systems often rely on semantic parsing to enable interactive information retrieval, which involves the generation of structured database queries from a natural language input. For information-seeking conversations about facts stored within a knowledge graph, dialogue utterances are transformed into graph queries in a process that is called knowledge-based conversational question answering. This paper evaluates the performance of large language models that have not been explicitly pre-trained on this task. Through a series of experiments on an extensive benchmark dataset, we compare models of varying sizes with different prompting techniques and identify common issue types in the generated output. Our results demonstrate that large language models are capable of generating graph queries from dialogues, with significant improvements achievable through few-shot prompting and fine-tuning techniques, especially for smaller models that exhibit lower zero-shot performance. |
| title | Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2401.01711 |