paper-with-me

홈 › Papers

Learning to Transpile AMR into SPARQL

2021-12-15 · Mihaela Bornea, Ramon Fernandez Astudillo, Tahira Naseem, Nandana Mihindukulasooriya, Ibrahim Abdelaziz, Pavan Kapanipathi, Radu Florian, Salim Roukos

We propose a transition-based system to transpile Abstract Meaning Representation (AMR) into SPARQL for Knowledge Base Question Answering (KBQA). This allows us to delegate part of the semantic representation to a strongly pre-trained semantic parser, while learning transpiling with small amount of paired data. We depart from recent work relating AMR and SPARQL constructs, but rather than applying a set of rules, we teach a BART model to selectively use these relations. Further, we avoid explicitly encoding AMR but rather encode the parser state in the attention mechanism of BART, following recent semantic parsing works. The resulting model is simple, provides supporting text for its decisions, and outperforms recent approaches in KBQA across two knowledge bases: DBPedia (LC-QuAD 1.0, QALD-9) and Wikidata (WebQSP, SWQ-WD).

📄 PDF Abstract BibTeX arXiv:2112.07877

Code (0)

등록된 구현이 없습니다.

Tasks

Abstract Meaning RepresentationKnowledge Base Question AnsweringQuestion AnsweringSemantic Parsing

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Learning to Transpile AMR into SPARQL

2022-01-16 · ACL ARR January 2022 1 · Anonymous

We propose a transition-based system to transpile Abstract Meaning Representation (AMR) into SPARQL for Knowledge Base Question Answering (KBQA). This allows to delegate part of the abstraction problem to a strongly pre-…

Abstract Meaning RepresentationKnowledge Base Question AnsweringQuestion AnsweringSemantic Parsing

SPARQLing Database Queries from Intermediate Question Decompositions

2021-09-13 · EMNLP 2021 11 · Irina Saparina, Anton Osokin

To translate natural language questions into executable database queries, most approaches rely on a fully annotated training set. Annotating a large dataset with queries is difficult as it requires query-language experti…

Knowledge GraphsText to SQLText-To-SQL

AutoQGS: Auto-Prompt for Low-Resource Knowledge-based Question Generation from SPARQL

2022-08-26 · Guanming Xiong, Junwei Bao, Wen Zhao, Youzheng Wu 외

This study investigates the task of knowledge-based question generation (KBQG). Conventional KBQG works generated questions from fact triples in the knowledge graph, which could not express complex operations like aggreg…

Question GenerationQuestion-Generation

ARUQULA -- An LLM based Text2SPARQL Approach using ReAct and Knowledge Graph Exploration Utilities

2025-10-02 · Felix Brei, Lorenz Bühmann, Johannes Frey, Daniel Gerber 외 arxiv

Interacting with knowledge graphs can be a daunting task for people without a background in computer science since the query language that is used (SPARQL) has a high barrier of entry. Large language models (LLMs) can lo…

Knowledge Graphs

Simplified SPARQL REST API - CRUD on JSON Object Graphs via URI Paths

2018-05-03 · Markus Schröder, Jörn Hees, Ansgar Bernardi, Daniel Ewert 외

Within the Semantic Web community, SPARQL is one of the predominant languages to query and update RDF knowledge. However, the complexity of SPARQL, the underlying graph structure and various encodings are common sources …