Papers with Code 아카이브
Semantic Parsing
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 20
- 보존된 평가 기록
- 78
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
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/felix01189/seed
공식 코드https://github.com/filipposventirozos/towards-end-user-development-for-iot
공식 코드https://github.com/flitternie/graphq_ir
공식 코드https://github.com/flyingfeather/dea-sql
공식 코드Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm
https://github.com/frankaging/recogs
공식 코드ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation
https://github.com/freesunshine0316/sembleu
공식 코드https://github.com/gc974517/autoformalization
공식 코드Towards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofs
https://github.com/georgeto20/counterfactual_explanations
공식 코드https://github.com/givoli/TechnionNLI
공식 코드https://github.com/glee4810/EHRSQL
공식 코드EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records
https://github.com/goodbai-nlp/amr-domainadaptation
공식 코드https://github.com/google-research-datasets/hinglish-top-dataset
공식 코드https://github.com/google-research/google-research
공식 코드https://github.com/google-research/google-research/tree/master/cfq
공식 코드Measuring Compositional Generalization: A Comprehensive Method on Realistic Data
https://github.com/google-research/google-research/tree/master/cfq_pt_vs_sa
공식 코드Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
https://github.com/google-research/google-research/tree/master/meta_reward_learning
공식 코드Learning to Generalize from Sparse and Underspecified Rewards
https://github.com/google-research/language
공식 코드Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations
https://github.com/google-research/language/tree/master/language/casper
공식 코드https://github.com/google-research/language/tree/master/language/nqg
공식 코드https://github.com/google-research/tapas
공식 코드https://github.com/google-research/xtreme-up
공식 코드XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages
https://github.com/google/overcoming-conflicting-data
공식 코드Overcoming Conflicting Data when Updating a Neural Semantic Parser
https://github.com/google/sling
공식 코드https://github.com/google/uncertainty-baselines
공식 코드https://github.com/gt-salt/subs
공식 코드SUBS: Subtree Substitution for Compositional Semantic Parsing
https://github.com/guotong1988/NL2SQL-BERT
공식 코드https://github.com/guotong1988/NL2SQL-RULE
공식 코드https://github.com/guotong1988/Rule-SQL
공식 코드Using Database Rule for Weak Supervised Text-to-SQL Generation
https://github.com/guotong1988/table2answer
공식 코드https://github.com/headacheboy/IGSQL
공식 코드https://github.com/headacheboy/cross-lingual-amr-parsing
공식 코드Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing
https://github.com/heegyukim/flex
공식 코드FLEX: Expert-level False-Less EXecution Metric for Reliable Text-to-SQL Benchmark
https://github.com/heidelberg-nlp/amrparseeval
공식 코드Better Smatch = Better Parser? AMR evaluation is not so simple anymore
https://github.com/hexuandeng/hexp4uds
공식 코드https://github.com/hirupert/sede
공식 코드Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.