https://github.com/FeiWang96/GTR
공식 코드Retrieving Complex Tables with Multi-Granular Graph Representation Learning
Papers with Code 아카이브
Table Retrieval
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 5
When given a query, the goal of this task is to retrieve a relevant table from a (potentially large) collection of tables. The query could be a single sentence (such as a question), or it could also be a conversation. As for the retrieval, the tables could be in the raw form (i.e. the values of each cells), the metadata (such as the title, description), or summary statistics.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/IBM/row-column-intersection
공식 코드https://github.com/McGill-NLP/statcan-dialogue-dataset
공식 코드The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents
https://github.com/Zhiyu-Chen/Web-Table-Retrieval-Benchmark
공식 코드https://github.com/avalab-gt/ctbls
공식 코드cTBLS: Augmenting Large Language Models with Conversational Tables
https://github.com/iai-group/sigir2019-table2vec
공식 코드Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval
https://github.com/iai-group/table-retrieval
공식 코드https://github.com/iai-group/www2018-table
공식 코드https://github.com/irgroup/simiir-wtr
공식 코드https://github.com/medtray/StruBERT
공식 코드StruBERT: Structure-aware BERT for Table Search and Matching
https://github.com/nzjin/odtqa
공식 코드Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrieval
https://github.com/thedatastation/pneuma
공식 코드Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System
https://github.com/zhxlia/murre
공식 코드MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL
https://github.com/zorazrw/nqt-retrieval
공식 코드Table Retrieval May Not Necessitate Table-specific Model Design
https://github.com/Dahny/IN4325-Core-IR-Project
https://github.com/Zhiyu-Chen/SIGIR2020-BERT-Table-Search
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.