Papers with Code 아카이브

Dialogue State Tracking

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 0
평가표: 7
보존된 평가 기록: 39

Dialogue state tacking consists of determining at each turn of a dialogue the full representation of what the user wants at that point in the dialogue, which contains a goal constraint, a set of requested slots, and the user's dialogue act.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/lvyufeng/bert4ms

https://github.com/milmor/GPT

https://github.com/mindspore-ai/models/blob/master/research/nlp/gpt2

https://github.com/minimaxir/gpt-2-simple

https://github.com/openai/gpt-2

https://github.com/qbxlvnf11/MultiWOZ2.1-Parser

MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines

https://github.com/ramanakshay/nanogpt

https://github.com/varun-suresh/experiments-with-gpt2

https://github.com/vzhong/gazp

Grounded Adaptation for Zero-shot Executable Semantic Parsing

https://github.com/xubuvd/guesswhat

Visual Dialogue State Tracking for Question Generation

https://github.com/yangyucheng000/Paper-3/tree/main/acm-mm-2023-picr-master

PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models

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