https://github.com/danielhers/synsem
공식 코드Content Differences in Syntactic and Semantic Representations
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Semantic Parsing is the task of transducing natural language utterances into formal meaning representations. The target meaning representations can be defined according to a wide variety of formalisms. This include linguistically-motivated semantic representations that are designed to capture the meaning of any sentence such as λ-calculus or the abstract meaning representations. Alternatively, for more task-driven approaches to Semantic Parsing, it is common for meaning representations to represent executable programs such as SQL queries, robotic commands, smart phone instructions, and even general-purpose programming languages like Python and Java.
Source: Tranx: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Content Differences in Syntactic and Semantic Representations
Transition-based Semantic Dependency Parsing with Pointer Networks
Shift-Reduce Task-Oriented Semantic Parsing with Stack-Transformers
The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing
Evaluating Inter-Bilingual Semantic Parsing for Indian Languages
SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL
Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing
Semantic Parsing for Conversational Question Answering over Knowledge Graphs
LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsing
Compositional generalization in semantic parsing with pretrained transformers
Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models
Calibrated Interpretation: Confidence Estimation in Semantic Parsing
Calibrated Interpretation: Confidence Estimation in Semantic Parsing
BookSQL: A Large Scale Text-to-SQL Dataset for Accounting Domain
Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog
TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.