paper-with-me

홈 › Papers

Verbal Semantics as Eventive Information: The Case of Verb “制服” and “制約” in Chinese Gigaword Corpus

2021-11-01 · PACLIC 2021 11 · Zhan Wang, Ming Ming Chiu
📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Deverbal semantics and the Montagovian generative lexicon

2014-01-25 · Livy-Maria Real-Coelho, Christian Retoré

We propose a lexical account of action nominals, in particular of deverbal nominalisations, whose meaning is related to the event expressed by their base verb. The literature about nominalisations often assumes that the …

Draw and Tell: Multimodal Descriptions Outperform Verbal- or Sketch-Only Descriptions in an Image Retrieval Task

2017-11-01 · IJCNLP 2017 11 · Ting Han, David Schlangen

While language conveys meaning largely symbolically, actual communication acts typically contain iconic elements as well: People gesture while they speak, or may even draw sketches while explaining something. Image retri…

Image DescriptionImage RetrievalRetrieval

Event Structure of Transitive Verb: A MARVS perspective

2014-02-13 · Jia-Fei Hong, Kathleen Ahrens, Chu-Ren Huang

Module-Attribute Representation of Verbal Semantics (MARVS) is a theory of the representation of verbal semantics that is based on Mandarin Chinese data (Huang et al. 2000). In the MARVS theory, there are two different t…

Attribute

Prototypical Verbalizer for Prompt-based Few-shot Tuning

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

Prompt-based tuning for pre-trained language models (PLMs) has shown its effectiveness in few-shot learning. Typically, prompt-based tuning wraps the input text into a cloze question. To make predictions, the model maps …

Contrastive LearningEntity TypingFew-Shot LearningTopic Classification

Prototypical Verbalizer for Prompt-based Few-shot Tuning

2022-03-18 · ACL 2022 5 · Ganqu Cui, Shengding Hu, Ning Ding, Longtao Huang 외

Prompt-based tuning for pre-trained language models (PLMs) has shown its effectiveness in few-shot learning. Typically, prompt-based tuning wraps the input text into a cloze question. To make predictions, the model maps …

Contrastive LearningEntity TypingFew-Shot LearningTopic Classification