📰 Workshop on Representation Learning for NLP 2021 — accepted papers

Workshop on Representation Learning for NLP 2021 is the 2021 edition of the Workshop on Representation Learning for NLP, held in Online, August 2021 (publisher: Association for Computational Linguistics). The ACL Anthology lists 32 papers of it; our library holds 2 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

Most cited papers

By their OpenAlex citations; a paper with our summary links to its page here, the others to the original.

1. In-Batch Negatives for Knowledge Distillation with Tightly-Coupled Teachers for Dense RetrievalSheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin122 citations
2. Larger-Scale Transformers for Multilingual Masked Language ModelingNaman Goyal, Jingfei Du, Myle Ott et al.83 citations · our summary
3. Scaling Deep Contrastive Learning Batch Size under Memory Limited SetupLuyu Gao, Yunyi Zhang, Jiawei Han et al.64 citations · our summary
4. Entity and Evidence Guided Document-Level Relation ExtractionKevin Huang, Peng Qi, Guangtao Wang et al.39 citations
5. Deriving Contextualised Semantic Features from BERT (and Other Transformer Model) EmbeddingsJacob Turton, Robert Elliott Smith, David Vinson29 citations
6. Preserving Cross-Linguality of Pre-trained Models via Continual LearningZihan Liu, Genta Indra Winata, Andrea Madotto et al.14 citations
7. Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational AssumptionsDamai Dai, Hua Zheng, Fuli Luo et al.13 citations
8. Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language ModelsMatteo Alleman, Jonathan Mamou, Miguel A Del Rio et al.11 citations
9. NPVec1: Word Embeddings for Nepali - Construction and EvaluationPravesh Koirala, Nobal B. Niraula10 citations
10. Probing Multilingual Language Models for DiscourseMurathan Kurfalı, Robert Östling10 citations

All accepted papers (32)

The most cited first; 2 with our summary link to their page here, the others to the original.

1. In-Batch Negatives for Knowledge Distillation with Tightly-Coupled Teachers for Dense RetrievalSheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin122 citations
2. Larger-Scale Transformers for Multilingual Masked Language ModelingNaman Goyal, Jingfei Du, Myle Ott et al.83 citations · our summary
3. Scaling Deep Contrastive Learning Batch Size under Memory Limited SetupLuyu Gao, Yunyi Zhang, Jiawei Han et al.64 citations · our summary
4. Entity and Evidence Guided Document-Level Relation ExtractionKevin Huang, Peng Qi, Guangtao Wang et al.39 citations
5. Deriving Contextualised Semantic Features from BERT (and Other Transformer Model) EmbeddingsJacob Turton, Robert Elliott Smith, David Vinson29 citations
6. Preserving Cross-Linguality of Pre-trained Models via Continual LearningZihan Liu, Genta Indra Winata, Andrea Madotto et al.14 citations
7. Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational AssumptionsDamai Dai, Hua Zheng, Fuli Luo et al.13 citations
8. Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language ModelsMatteo Alleman, Jonathan Mamou, Miguel A Del Rio et al.11 citations
9. NPVec1: Word Embeddings for Nepali - Construction and EvaluationPravesh Koirala, Nobal B. Niraula10 citations
10. Probing Multilingual Language Models for DiscourseMurathan Kurfalı, Robert Östling10 citations
11. Revisiting Pretraining with AdaptersSeungwon Kim, Alex Shum, Nathan Susanj et al.9 citations
12. Structure-aware Sentence Encoder in Bert-Based Siamese NetworkQiwei Peng, David Weir, Julie Weeds7 citations
13. X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic ParsingZihan Liu, Genta Indra Winata, Peng Xu et al.7 citations
14. Comprehension Based Question Answering using Bloom's TaxonomyPritish Sahu, Michael Cogswell, Ajay Divakaran et al.6 citations
15. An Overview of Uncertainty Calibration for Text Classification and the Role of DistillationHan Guo, Ramakanth Pasunuru, Mohit Bansal5 citations
16. Direction is what you need: Improving Word Embedding Compression in Large Language ModelsKlaudia Bałazy, Mohammadreza Banaei, Rémi Lebret et al.5 citations
17. Zero-shot Sequence Labeling for Transformer-based Sentence ClassifiersKamil Bujel, Helen Yannakoudakis, Marek Rei5 citations
18. Knodle: Modular Weakly Supervised Learning with PyTorchAnastasiia Sedova, Andreas Stephan, Marina Speranskaya et al.4 citations
19. Knowledge Informed Semantic Parsing for Conversational Question AnsweringRaghuveer Thirukovalluru, Mukund Sridhar, Dung Thai et al.4 citations
20. Improving Cross-lingual Text Classification with Zero-shot Instance-WeightingIrene Li, Prithviraj Sen, Huaiyu Zhu et al.3 citations
21. Learning Sparse Sentence Encoding without Supervision: An Exploration of Sparsity in Variational AutoencodersVictor Prokhorov, Yingzhen Li, Ehsan Shareghi et al.3 citations
22. Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic DatasetsLan Zhang, Victor Prokhorov, Ehsan Shareghi3 citations
23. Box-To-Box Transformations for Modeling Joint HierarchiesShib Sankar Dasgupta, Xiang Lorraine Li, Michael Boratko et al.2 citations
24. Deriving Word Vectors from Contextualized Language Models using Topic-Aware Mention SelectionYixiao Wang, Zied Bouraoui, Luis Espinosa Anke et al.2 citations
25. Predicting the Success of Domain Adaptation in Text SimilarityNick Pogrebnyakov, Shohreh Shaghaghian2 citations

See all 32 papers in Workshop on Representation Learning for NLP 2021 — accepted papers →

📄 Papers with our summary in our library (2)

The most cited first (OpenAlex citations plus our library's).

1. Larger-Scale Transformers for Multilingual Masked Language ModelingNaman Goyal, Jingfei Du, Myle Ott, et al.2021 · 160 citations
2. Scaling Deep Contrastive Learning Batch Size under Memory Limited SetupLuyu Gao, Yunyi Zhang, Jiawei Han, et al.2021 · 130 citations

🧭 Top topics

Topics of its works in our library, with the number of works on each.

🧠Language models & pretraining (1)🌍Multilingual & cross-lingual NLP (1)

📚 Fields

🎭Arts and Humanities (2)🖥️Computer Science (2)

🧑‍🔬 Top authors

Authors with a page who published here most often: their works here, and the citations of those works.

🏛️ Top institutions

Institutions on the bylines of its works here, by the number of works.

🎓University of Illinois Urbana-ChampaignUrbana · United States1 work here🎓Carnegie Mellon UniversityPittsburgh · United States1 work here

Place and dates from the event's site or the ACL Anthology; works and citations from OpenAlex and our library.

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/venues/repl4nlp/2021/