Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916839670415360 |
|---|---|
| author | Saparina, Irina Lapata, Mirella |
| author_facet | Saparina, Irina Lapata, Mirella |
| contents | Handling ambiguity and underspecification is an important challenge in natural language interfaces, particularly for tasks like text-to-SQL semantic parsing. We propose a modular approach that resolves ambiguity using natural language interpretations before mapping these to logical forms (e.g., SQL queries). Although LLMs excel at parsing unambiguous utterances, they show strong biases for ambiguous ones, typically predicting only preferred interpretations. We constructively exploit this bias to generate an initial set of preferred disambiguations and then apply a specialized infilling model to identify and generate missing interpretations. To train the infilling model, we introduce an annotation method that uses SQL execution to validate different meanings. Our approach improves interpretation coverage and generalizes across datasets with different annotation styles, database structures, and ambiguity types. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18448 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing Saparina, Irina Lapata, Mirella Computation and Language Artificial Intelligence Handling ambiguity and underspecification is an important challenge in natural language interfaces, particularly for tasks like text-to-SQL semantic parsing. We propose a modular approach that resolves ambiguity using natural language interpretations before mapping these to logical forms (e.g., SQL queries). Although LLMs excel at parsing unambiguous utterances, they show strong biases for ambiguous ones, typically predicting only preferred interpretations. We constructively exploit this bias to generate an initial set of preferred disambiguations and then apply a specialized infilling model to identify and generate missing interpretations. To train the infilling model, we introduce an annotation method that uses SQL execution to validate different meanings. Our approach improves interpretation coverage and generalizes across datasets with different annotation styles, database structures, and ambiguity types. |
| title | Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.18448 |