Papers with Code 아카이브

Data-to-Text Generation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크
3
평가표
26
보존된 평가 기록
122

A classic problem in natural-language generation (NLG) involves taking structured data, such as a table, as input, and producing text that adequately and fluently describes this data as output. Unlike machine translation, which aims for complete transduction of the sentence to be translated, this form of NLG is usually taken to require addressing (at least) two separate challenges: what to say, the selection of an appropriate subset of the input data to discuss, and how to say it, the surface realization of a generation.

<span style="color:grey; opacity: 0.6">( Image credit: Data-to-Text Generation with Content Selection and Planning )</span>

평가 결과

데이터셋과 평가 조건을 선택해 성능·논문·코드를 비교하세요. 보존된 Papers with Code 기록으로, 최신 순위는 아닙니다.

WebNLG ru

원본 태스크: Text Generation / Data-to-Text Generation

평가 기록 2건

AMR3.0

원본 태스크: Text Generation / Data-to-Text Generation

평가 기록 1건

ENT-DESC

원본 태스크: Text Generation / Data-to-Text Generation / KG-to-Text Generation

평가 기록 1건

GenWiki

원본 태스크: Text Generation / Data-to-Text Generation

평가 기록 1건

VG graph-text

원본 태스크: Text Generation / Data-to-Text Generation / Unsupervised KG-to-Text Generation

평가 기록 1건

WebNLG v2.1

원본 태스크: Text Generation / Data-to-Text Generation / Unsupervised KG-to-Text Generation

평가 기록 1건

WikiOFGraph

원본 태스크: Text Generation / Data-to-Text Generation

평가 기록 1건

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.