https://github.com/2003pro/exesql
공식 코드ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects
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.
ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects
An Investigation of LLMs' Inefficacy in Understanding Converse Relations
Automated Concatenation of Embeddings for Structured Prediction
Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing
Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies
Identity-Guided Human Semantic Parsing for Person Re-Identification
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models
Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuning
N-LTP: An Open-source Neural Language Technology Platform for Chinese
E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL
Translate, then Parse! A strong baseline for Cross-Lingual AMR Parsing
AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry
Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
Leveraging Semantic Parsing for Relation Linking over Knowledge Bases
T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing
Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training
Rethinking Tabular Data Understanding with Large Language Models
MACT: Model-Agnostic Cross-Lingual Training for Discourse Representation Structure Parsing
Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning
AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling
OpenGrok: Enhancing SNS Data Processing with Distilled Knowledge and Mask-like Mechanisms
Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
Valid Text-to-SQL Generation with Unification-based DeepStochLog
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.