paper-with-me

Papers

Exploring Unsupervised Pretraining and Sentence Structure Modelling for Winograd Schema Challenge

2019-04-22 · Yu-Ping Ruan, Xiaodan Zhu, Zhen-Hua Ling, Zhan Shi, Quan Liu, Si Wei

Winograd Schema Challenge (WSC) was proposed as an AI-hard problem in testing computers' intelligence on common sense representation and reasoning. This paper presents the new state-of-theart on WSC, achieving an accuracy of 71.1%. We demonstrate that the leading performance benefits from jointly modelling sentence structures, utilizing knowledge learned from cutting-edge pretraining models, and performing fine-tuning. We conduct detailed analyses, showing that fine-tuning is critical for achieving the performance, but it helps more on the simpler associative problems. Modelling sentence dependency structures, however, consistently helps on the harder non-associative subset of WSC. Analysis also shows that larger fine-tuning datasets yield better performances, suggesting the potential benefit of future work on annotating more Winograd schema sentences.

📄 PDF Abstract BibTeX arXiv:1904.09705

Code (0)

등록된 구현이 없습니다.

Tasks

Common Sense ReasoningSentence

Similar Papers 제목 키워드 기반

Exploring Unsupervised Pretraining Objectives for Machine Translation

2021-06-10 · Findings (ACL) 2021 8 · Christos Baziotis, Ivan Titov, Alexandra Birch, Barry Haddow

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to se…

DecoderLanguage ModelingLanguage ModellingMachine Translation+3

MDAPT: Multilingual Domain Adaptive Pretraining in a Single Model

2021-09-14 · Findings (EMNLP) 2021 11 · Rasmus Kær Jørgensen, Mareike Hartmann, Xiang Dai, Desmond Elliott

Domain adaptive pretraining, i.e. the continued unsupervised pretraining of a language model on domain-specific text, improves the modelling of text for downstream tasks within the domain. Numerous real-world application…

Language ModelingLanguage Modellingnamed-entity-recognitionNamed Entity Recognition+3

Pretraining Reward-Free Representations for Data-Efficient Reinforcement Learning

2021-03-09 · ICLR Workshop SSL-RL 2021 5 · Max Schwarzer, Nitarshan Rajkumar, Michael Noukhovitch, Ankesh Anand 외

Data efficiency poses a major challenge for deep reinforcement learning. We approach this issue from the perspective of self-supervised representation learning, leveraging reward-free exploratory data to pretrain encoder…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Document-level Neural Machine Translation Using Dependency RST Structure

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

Document-level machine translation (MT) extends the translation unit from the sentence to the whole document. Intuitively, discourse structure can be useful for document-level MT for its helpfulness in long-range depende…

DecoderDocument Level Machine TranslationMachine TranslationNMT+2

Unsupervised Context Aware Sentence Representation Pretraining for Multi-lingual Dense Retrieval

2022-06-07 · Ning Wu, Yaobo Liang, Houxing Ren, Linjun Shou 외

Recent research demonstrates the effectiveness of using pretrained language models (PLM) to improve dense retrieval and multilingual dense retrieval. In this work, we present a simple but effective monolingual pretrainin…

Language ModellingPassage RetrievalRetrievalSentence+3