paper-with-me

홈 › Papers

Zero-Shot Script Parsing

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Script knowledge (shrank, 1977) proved useful to a variety of NLP tasks. However, existing resources only covering a small number of activities, limiting its practical usefulness. In this work, we propose a zero-shot learning approach to script parsing, the task of tagging texts with pre-defined, scenario-specific event and participant types, which makes it possible to acquire script knowledge without domain-specific annotations. We (1) learn representations of potential event and participant mentions by promoting cluster consistency according to the annotated data; (2) perform clustering on the event / participant candidates from unannotated texts that belongs to an unseen scenario. We further exploit dependency and coreference information. The model achieves 68.1/74.4 average F1 for event / participant parsing, respectively, outperforming a previous CRF model that has access to domain-specific supervision.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringZero-Shot Learning

Methods 이 논문이 사용한 방법론

CRF Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is…

Similar Papers 제목 키워드 기반

Zero-shot Script Parsing

2022-10-01 · COLING 2022 10 · Fangzhou Zhai, Vera Demberg, Alexander Koller

Script knowledge is useful to a variety of NLP tasks. However, existing resources only cover a small number of activities, limiting its practical usefulness. In this work, we propose a zero-shot learning approach to scri…

Zero-Shot Learning

ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language Models

2022-12-21 · Dheeraj Mekala, Jason Wolfe, Subhro Roy

We explore the use of large language models (LLMs) for zero-shot semantic parsing. Semantic parsing involves mapping natural language utterances to task-specific meaning representations. Language models are generally tra…

Extractive Question-AnsweringLanguage ModelingLanguage ModellingQuestion Answering+2

ChatGPT is a Potential Zero-Shot Dependency Parser

2023-10-25 · Boda Lin, Xinyi Zhou, Binghao Tang, Xiaocheng Gong 외

Pre-trained language models have been widely used in dependency parsing task and have achieved significant improvements in parser performance. However, it remains an understudied question whether pre-trained language mod…

Dependency Parsing

SEQZERO: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Recent research showed promising results on combining pretrained language models (LMs) with canonical utterance for few-shot semantic parsing.The canonical utterance is often lengthy and complex due to the compositional …

Out-of-Distribution GeneralizationSemantic Parsing

SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models

2022-05-15 · Findings (NAACL) 2022 7 · Jingfeng Yang, Haoming Jiang, Qingyu Yin, Danqing Zhang 외

Recent research showed promising results on combining pretrained language models (LMs) with canonical utterance for few-shot semantic parsing. The canonical utterance is often lengthy and complex due to the compositional…

Out-of-Distribution GeneralizationSemantic Parsing