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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
TARGET: Benchmarking Table Retrieval for Generative Tasks
Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System
Bridging Queries and Tables through Entities in Table Retrieval
Tailoring Table Retrieval from a Field-aware Hybrid Matching Perspective
Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval
MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL
Simulating Users in Interactive Web Table Retrieval
Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrieval
The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents
cTBLS: Augmenting Large Language Models with Conversational Tables
Bridge the Gap between Language models and Tabular Understanding
Table Retrieval May Not Necessitate Table-specific Model Design
End-to-End Table Question Answering via Retrieval-Augmented Generation
StruBERT: Structure-aware BERT for Table Search and Matching
CLTR: An End-to-End, Transformer-Based System for Cell Level Table Retrieval and Table Question Answering
Semantic Table Retrieval using Keyword and Table Queries
WTR: A Test Collection for Web Table Retrieval
Retrieving Complex Tables with Multi-Granular Graph Representation Learning
Table Search Using a Deep Contextualized Language Model
Leveraging Schema Labels to Enhance Dataset Search
Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval
Question Answering via Web Extracted Tables and Pipelined Models
Ad Hoc Table Retrieval using Semantic Similarity
Content-Based Table Retrieval for Web Queries
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.