📰 GEM 2022: all accepted papers

45 papers · the most cited first · ← GEM 2022

1. Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam SearchDaniel King, Zejiang Shen, Nishant Subramani et al.26 citations
2. Control Prefixes for Parameter-Efficient Text GenerationJordan Clive, Kris Cao, Marek Rei20 citations
3. What Makes Data-to-Text Generation Hard for Pretrained Language Models?Moniba Keymanesh, Adrian Benton, Mark Dredze12 citations
4. Factual Error Correction for Abstractive Summaries Using Entity RetrievalHwanhee Lee, Cheoneum Park, Seunghyun Yoon et al.10 citations
5. Improving abstractive summarization with energy-based re-rankingDiogo Pernes, Afonso Mendes, André F. T. Martins9 citations
6. Semantic Similarity as a Window into Vector- and Graph-Based MetricsWai Ching Leung, Shira Wein, Nathan Schneider8 citations
7. Analyzing Multi-Task Learning for Abstractive Text SummarizationFrederic Kirstein, Jan Philip Wahle, Terry Ruas et al.7 citations
8. Weakly Supervised Context-based Interview Question GenerationSamiran Pal, Kaamraan Khan, Avinash Kumar Singh et al.7 citations
9. Enhancing and Evaluating the Grammatical Framework Approach to Logic-to-Text GenerationEduardo Calò, Elze van der Werf, Albert Gatt et al.6 citations
10. Human perceiving behavior modeling in evaluation of code generation modelsSergey Kovalchuk, Vadim Lomshakov, Artem Aliev6 citations
11. Measuring the Measuring Tools: An Automatic Evaluation of Semantic Metrics for Text CorporaGeorge Kour, Samuel Ackerman, Eitan Daniel Farchi et al.6 citations
12. T5QL: Taming language models for SQL generationSamuel David Arcadinho, David Aparicio, Hugo Veiga et al.6 citations
13. A Survey of Recent Error Annotation Schemes for Automatically Generated TextRudali Huidrom, Anya Belz5 citations
14. Answerability: A custom metric for evaluating chatbot performancePranav Gupta, Anand A. Rajasekar, Amisha Patel et al.5 citations
15. Revisiting text decomposition methods for NLI-based factuality scoring of summariesJohn Glover, Federico Fancellu, Vasudevan Jagannathan et al.5 citations
16. Nearest Neighbor Language Models for Stylistic Controllable GenerationSeverino Trotta, Lucie Flek, Charles Welch4 citations
17. Improved Evaluation of Automatic Source Code SummarisationJesse Phillips, David Bowes, Mahmoud El-Haj et al.3 citations
18. Most NLG is Low-Resource: here's what we can do about itDavid M. Howcroft, Dimitra Gkatzia3 citations
19. Narrative Why-Question Answering: A Review of Challenges and DatasetsEmil Kalbaliyev, Kairit Sirts3 citations
20. On reporting scores and agreement for error annotation tasksMaja Popović, Anya Belz3 citations
21. Unsupervised Token-level Hallucination Detection from Summary Generation By-productsAndreas Marfurt, James Henderson3 citations
22. 20Q: Overlap-Free World Knowledge Benchmark for Language ModelsMaxime De Bruyn, Ehsan Lotfi, Jeska Buhmann et al.2 citations
23. Error Analysis of ToTTo Table-to-Text Neural NLG ModelsBarkavi Sundararajan, Somayajulu Sripada, Ehud Reiter2 citations
24. Evaluation of Response Generation Models: Shouldn't It Be Shareable and Replicable?Seyed Mahed Mousavi, Gabriel Roccabruna, Michela Lorandi et al.2 citations
25. Generating Coherent Narratives with Subtopic Planning to Answer How-to QuestionsPengshan Cai, Mo Yu, Fei Liu et al.2 citations
26. Plug-and-Play Recipe Generation with Content PlanningYinhong Liu, Yixuan Su, Ehsan Shareghi et al.2 citations
27. Template-based Contact Email Generation for Job RecommendationQiuchi Li, Christina Lioma2 citations
28. Towards Attribute-Entangled Controllable Text Generation: A Pilot Study of Blessing GenerationShulin Huang, Shirong Ma, Yinghui Li et al.2 citations
29. WikiOmnia: filtration and evaluation of the generated QA corpus on the whole Russian WikipediaDina Pisarevskaya, Tatiana Shavrina2 citations
30. Assessing Inter-metric Correlation for Multi-document Summarization EvaluationMichael Ridenour, Ameeta Agrawal, Olubusayo Olabisi1 citation
31. CLSE: Corpus of Linguistically Significant EntitiesAleksandr Chuklin, Justin Zhao, Mihir Kale1 citation
32. Coherent Long Text Generation by Contrastive Soft PromptGuandan Chen, Jiashu Pu, Yadong Xi et al.1 citation
33. Improving Dialogue Act Recognition with Augmented DataKhyati Mahajan, Soham Parikh, Quaizar Vohra et al.1 citation · our summary
34. Towards In-Context Non-Expert Evaluation of Reflection Generation for Counselling ConversationsZixiu Wu, Simone Balloccu, Rim Helaoui et al.1 citation
35. Transfer learning for multilingual vacancy text generationAnna Lorincz, David Graus, Dor Lavi et al.1 citation
36. What Was Your Name Again? Interrogating Generative Conversational Models For Factual Consistency EvaluationEhsan Lotfi, Maxime De Bruyn, Jeska Buhmann et al.1 citation
37. A Corpus and Evaluation for Predicting Semi-Structured Human AnnotationsAndreas Marfurt, Ashley Thornton, David Sylvan et al.
38. Are Abstractive Summarization Models truly `Abstractive'? An Empirical Study to Compare the two Forms of SummarizationVinayshekhar Bannihatti Kumar, Rashmi Gangadharaiah
39. Controllable Text Generation for All Ages: Evaluating a Plug-and-Play Approach to Age-Adapted DialogueLennert Jansen, Štěpán Lars Laichter, Arabella Sinclair et al.
40. Do Decoding Algorithms Capture Discourse Structure in Multi-Modal Tasks? A Case Study of Image Paragraph GenerationNikolai Ilinykh, Simon Dobnik
41. Exploring a POS-based Two-stage Approach for Improving Low-Resource AMR-to-Text GenerationMarco Antonio Sobrevilla Cabezudo, Thiago Pardo
42. GiCCS: A German in-Context Conversational Similarity BenchmarkShima Asaadi, Zahra Kolagar, Alina Liebel et al.
43. Multilingual Social Media Text Generation and Evaluation with Few-Shot PromptingMack Blackburn
44. Task-driven augmented data evaluationOlga Golovneva, Pan Wei, Khadige Abboud et al.
45. What's in a (dataset's) name? The case of BigPatentSilvia Casola, Alberto Lavelli, Horacio Saggion

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/venues/gem/2022/papers/