Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023)最新文献

DiscoFlan: Instruction Fine-tuning and Refined Text Generation for Discourse Relation Label Classification 话语关系标签分类的指令微调与精细化文本生成

Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023) Pub Date : 1900-01-01 DOI: 10.18653/v1/2023.disrpt-1.2

Kaveri Anuranjana

{"title":"DiscoFlan: Instruction Fine-tuning and Refined Text Generation for Discourse Relation Label Classification","authors":"Kaveri Anuranjana","doi":"10.18653/v1/2023.disrpt-1.2","DOIUrl":"https://doi.org/10.18653/v1/2023.disrpt-1.2","url":null,"abstract":"This paper introduces DiscoFlan, a multilingual discourse relation classifier submitted for DISRPT 2023. Our submission represents the first attempt at building a multilingual discourse relation classifier for the DISRPT 2023 shared task. By our model addresses the issue to mismatches caused by hallucination in a seq2seq model by utilizing the label distribution information for label generation. In contrast to the previous state-of-the-art model, our approach eliminates the need for hand-crafted features in computing the discourse relation classes. Furthermore, we propose a novel label generation mechanism that anchors the labels to a fixed set by selectively enhancing training on the decoder model. Our experimental results demonstrate that our model surpasses the current state-of-the-art performance in 11 out of the 26 datasets considered, however the submitted model compatible with provided evaluation scripts is better in 7 out of 26 considered datasets, while demonstrating competitive results in the rest. Overall, DiscoFlan showcases promising advancements in multilingual discourse relation classification for the DISRPT 2023 shared task.","PeriodicalId":107248,"journal":{"name":"Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132587547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DisCut and DiscReT: MELODI at DISRPT 2023 DisCut and discrete: MELODI at DISRPT 2023

Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023) Pub Date : 1900-01-01 DOI: 10.18653/v1/2023.disrpt-1.3

Eleni (Lena) Metheniti, Chloé Braud, Philippe Muller, Laura Rivière

{"title":"DisCut and DiscReT: MELODI at DISRPT 2023","authors":"Eleni (Lena) Metheniti, Chloé Braud, Philippe Muller, Laura Rivière","doi":"10.18653/v1/2023.disrpt-1.3","DOIUrl":"https://doi.org/10.18653/v1/2023.disrpt-1.3","url":null,"abstract":"This paper presents the results obtained by the MELODI team for the three tasks proposed within the DISRPT 2023 shared task on discourse: segmentation, connective identification, and relation classification. The competition involves corpora in various languages in several underlying frameworks, and proposes two tracks depending on the presence or not of annotations of sentence boundaries and syntactic information. For these three tasks, we rely on a transformer-based architecture, and investigate several optimizations of the models, including hyper-parameter search and layer freezing.For discourse relations, we also explore the use of adapters—a lightweight solution for model fine-tuning—and introduce relation mappings to partially deal with the label set explosion we are facing within the setting of the shared task in a multi-corpus perspective. In the end, we propose one single architecture for segmentation and connectives, based on XLM-RoBERTa large, freezed at lower layers, with new state-of-the-art results for segmentation, and we propose 3 different models for relations, since the task makes it harder to generalize across all corpora.","PeriodicalId":107248,"journal":{"name":"Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131161208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

The DISRPT 2023 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation Classification 基于基本话语单元分割、连接检测和关系分类的DISRPT 2023共享任务

Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023) Pub Date : 1900-01-01 DOI: 10.18653/v1/2023.disrpt-1.1

Chloé Braud, Yang Janet Liu, Eleni (Lena) Metheniti, Philippe Muller, Laura Rivière, Attapol T. Rutherford, Amir Zeldes

引用次数: 2

HITS at DISRPT 2023: Discourse Segmentation, Connective Detection, and Relation Classification 会话分割，连接检测和关系分类

Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023) Pub Date : 1900-01-01 DOI: 10.18653/v1/2023.disrpt-1.4

Wei Liu, Yi Fan, M. Strube

引用次数: 0