Shujun Wan, Tino Kutschbach, Anke Lüdeling, Manfred Stede
This paper presents RST-Tace, a tool for automatic comparison and evaluation of RST trees. RST-Tace serves as an implementation of Iruskieta’s comparison method, which allows trees to be compared and evaluated without the influence of decisions at lower levels in a tree in terms of four factors: constituent, attachment point, nuclearity as well as relation. RST-Tace can be used regardless of the language or the size of rhetorical trees. This tool aims to measure the agreement between two annotators. The result is reflected by F-measure and inter-annotator agreement. Both the comparison table and the result of the evaluation can be obtained automatically.
{"title":"RST-Tace A tool for automatic comparison and evaluation of RST trees","authors":"Shujun Wan, Tino Kutschbach, Anke Lüdeling, Manfred Stede","doi":"10.18653/v1/W19-2712","DOIUrl":"https://doi.org/10.18653/v1/W19-2712","url":null,"abstract":"This paper presents RST-Tace, a tool for automatic comparison and evaluation of RST trees. RST-Tace serves as an implementation of Iruskieta’s comparison method, which allows trees to be compared and evaluated without the influence of decisions at lower levels in a tree in terms of four factors: constituent, attachment point, nuclearity as well as relation. RST-Tace can be used regardless of the language or the size of rhetorical trees. This tool aims to measure the agreement between two annotators. The result is reflected by F-measure and inter-annotator agreement. Both the comparison table and the result of the evaluation can be obtained automatically.","PeriodicalId":243254,"journal":{"name":"Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131073532","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}
In this exploratory study, we attempt to automatically induce PDTB-style relations from RST trees. We work with a German corpus of news commentary articles, annotated for RST trees and explicit PDTB-style relations and we focus on inducing the implicit relations in an automated way. Preliminary results look promising as a high-precision (but low-recall) way of finding implicit relations where there is no shallow structure annotated at all, but mapping proves more difficult in cases where EDUs and relation arguments overlap, yet do not seem to signal the same relation.
{"title":"Toward Cross-theory Discourse Relation Annotation","authors":"Peter Bourgonje, Olha Zolotarenko","doi":"10.18653/v1/W19-2702","DOIUrl":"https://doi.org/10.18653/v1/W19-2702","url":null,"abstract":"In this exploratory study, we attempt to automatically induce PDTB-style relations from RST trees. We work with a German corpus of news commentary articles, annotated for RST trees and explicit PDTB-style relations and we focus on inducing the implicit relations in an automated way. Preliminary results look promising as a high-precision (but low-recall) way of finding implicit relations where there is no shallow structure annotated at all, but mapping proves more difficult in cases where EDUs and relation arguments overlap, yet do not seem to signal the same relation.","PeriodicalId":243254,"journal":{"name":"Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125591918","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}
Artem Shelmanov, D. Pisarevskaya, Elena Chistova, S. Toldova, M. Kobozeva, I. Smirnov
Results of the first experimental evaluation of machine learning models trained on Ru-RSTreebank – first Russian corpus annotated within RST framework – are presented. Various lexical, quantitative, morphological, and semantic features were used. In rhetorical relation classification, ensemble of CatBoost model with selected features and a linear SVM model provides the best score (macro F1 = 54.67 ± 0.38). We discover that most of the important features for rhetorical relation classification are related to discourse connectives derived from the connectives lexicon for Russian and from other sources.
{"title":"Towards the Data-driven System for Rhetorical Parsing of Russian Texts","authors":"Artem Shelmanov, D. Pisarevskaya, Elena Chistova, S. Toldova, M. Kobozeva, I. Smirnov","doi":"10.18653/v1/W19-2711","DOIUrl":"https://doi.org/10.18653/v1/W19-2711","url":null,"abstract":"Results of the first experimental evaluation of machine learning models trained on Ru-RSTreebank – first Russian corpus annotated within RST framework – are presented. Various lexical, quantitative, morphological, and semantic features were used. In rhetorical relation classification, ensemble of CatBoost model with selected features and a linear SVM model provides the best score (macro F1 = 54.67 ± 0.38). We discover that most of the important features for rhetorical relation classification are related to discourse connectives derived from the connectives lexicon for Russian and from other sources.","PeriodicalId":243254,"journal":{"name":"Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115648595","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}
The relational status of Attribution in Rhetorical Structure Theory has been a matter of ongoing debate. Although several researchers have weighed in on the topic, and although numerous studies have relied upon attributional structures for their analyses, nothing approaching consensus has emerged. This paper identifies three basic issues that must be resolved to determine the relational status of attributions. These are identified as the Discourse Units Issue, the Nuclearity Issue, and the Relation Identification Issue. These three issues are analyzed from the perspective of classical RST. A finding of this analysis is that the nuclearity and the relational identification of attribution structures are shown to depend on the writer’s intended effect, such that attributional relations cannot be considered as a single relation, but rather as attributional instances of other RST relations.
{"title":"The Rhetorical Structure of Attribution","authors":"Andrew Potter","doi":"10.18653/v1/W19-2706","DOIUrl":"https://doi.org/10.18653/v1/W19-2706","url":null,"abstract":"The relational status of Attribution in Rhetorical Structure Theory has been a matter of ongoing debate. Although several researchers have weighed in on the topic, and although numerous studies have relied upon attributional structures for their analyses, nothing approaching consensus has emerged. This paper identifies three basic issues that must be resolved to determine the relational status of attributions. These are identified as the Discourse Units Issue, the Nuclearity Issue, and the Relation Identification Issue. These three issues are analyzed from the perspective of classical RST. A finding of this analysis is that the nuclearity and the relational identification of attribution structures are shown to depend on the writer’s intended effect, such that attributional relations cannot be considered as a single relation, but rather as attributional instances of other RST relations.","PeriodicalId":243254,"journal":{"name":"Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129827361","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}
We investigate the relationship between the notion of nuclearity as proposed in Rhetorical Structure Theory (RST) and the signalling of coherence relations. RST relations are categorized as either mononuclear (comprising a nucleus and a satellite span) or multinuclear (comprising two or more nuclei spans). We examine how mononuclear relations (e.g., Antithesis, Condition) and multinuclear relations (e.g., Contrast, List) are indicated by relational signals, more particularly by discourse markers (e.g., because, however, if, therefore). We conduct a corpus study, examining the distribution of either type of relations in the RST Discourse Treebank (Carlson et al., 2002) and the distribution of discourse markers for those relations in the RST Signalling Corpus (Das et al., 2015). Our results show that discourse markers are used more often to signal multinuclear relations than mononuclear relations. The findings also suggest a complex relationship between the relation types and syntactic categories of discourse markers (subordinating and coordinating conjunctions).
{"title":"Nuclearity in RST and signals of coherence relations","authors":"Debopam Das","doi":"10.18653/v1/W19-2705","DOIUrl":"https://doi.org/10.18653/v1/W19-2705","url":null,"abstract":"We investigate the relationship between the notion of nuclearity as proposed in Rhetorical Structure Theory (RST) and the signalling of coherence relations. RST relations are categorized as either mononuclear (comprising a nucleus and a satellite span) or multinuclear (comprising two or more nuclei spans). We examine how mononuclear relations (e.g., Antithesis, Condition) and multinuclear relations (e.g., Contrast, List) are indicated by relational signals, more particularly by discourse markers (e.g., because, however, if, therefore). We conduct a corpus study, examining the distribution of either type of relations in the RST Discourse Treebank (Carlson et al., 2002) and the distribution of discourse markers for those relations in the RST Signalling Corpus (Das et al., 2015). Our results show that discourse markers are used more often to signal multinuclear relations than mononuclear relations. The findings also suggest a complex relationship between the relation types and syntactic categories of discourse markers (subordinating and coordinating conjunctions).","PeriodicalId":243254,"journal":{"name":"Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116017034","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}
Segmentation is the first step in building practical discourse parsers, and is often neglected in discourse parsing studies. The goal is to identify the minimal spans of text to be linked by discourse relations, or to isolate explicit marking of discourse relations. Existing systems on English report F1 scores as high as 95%, but they generally assume gold sentence boundaries and are restricted to English newswire texts annotated within the RST framework. This article presents a generic approach and a system, ToNy, a discourse segmenter developed for the DisRPT shared task where multiple discourse representation schemes, languages and domains are represented. In our experiments, we found that a straightforward sequence prediction architecture with pretrained contextual embeddings is sufficient to reach performance levels comparable to existing systems, when separately trained on each corpus. We report performance between 81% and 96% in F1 score. We also observed that discourse segmentation models only display a moderate generalization capability, even within the same language and discourse representation scheme.
{"title":"ToNy: Contextual embeddings for accurate multilingual discourse segmentation of full documents","authors":"Philippe Muller, Chloé Braud, Mathieu Morey","doi":"10.18653/v1/W19-2715","DOIUrl":"https://doi.org/10.18653/v1/W19-2715","url":null,"abstract":"Segmentation is the first step in building practical discourse parsers, and is often neglected in discourse parsing studies. The goal is to identify the minimal spans of text to be linked by discourse relations, or to isolate explicit marking of discourse relations. Existing systems on English report F1 scores as high as 95%, but they generally assume gold sentence boundaries and are restricted to English newswire texts annotated within the RST framework. This article presents a generic approach and a system, ToNy, a discourse segmenter developed for the DisRPT shared task where multiple discourse representation schemes, languages and domains are represented. In our experiments, we found that a straightforward sequence prediction architecture with pretrained contextual embeddings is sufficient to reach performance levels comparable to existing systems, when separately trained on each corpus. We report performance between 81% and 96% in F1 score. We also observed that discourse segmentation models only display a moderate generalization capability, even within the same language and discourse representation scheme.","PeriodicalId":243254,"journal":{"name":"Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019","volume":"200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122160711","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}
Discourse information is crucial for a better understanding of the text structure and it is also necessary to describe which part of an opinionated text is more relevant or to decide how a text span can change the polarity (strengthen or weaken) of other span by means of coherence relations. This work presents the first results on the annotation of the Basque Opinion Corpus using Rhetorical Structure Theory (RST). Our evaluation results and analysis show us the main avenues to improve on a future annotation process. We have also extracted the subjectivity of several rhetorical relations and the results show the effect of sentiment words in relations and the influence of each relation in the semantic orientation value.
{"title":"Towards discourse annotation and sentiment analysis of the Basque Opinion Corpus","authors":"J. Alkorta, Koldo Gojenola, Mikel Iruskieta","doi":"10.18653/v1/W19-2718","DOIUrl":"https://doi.org/10.18653/v1/W19-2718","url":null,"abstract":"Discourse information is crucial for a better understanding of the text structure and it is also necessary to describe which part of an opinionated text is more relevant or to decide how a text span can change the polarity (strengthen or weaken) of other span by means of coherence relations. This work presents the first results on the annotation of the Basque Opinion Corpus using Rhetorical Structure Theory (RST). Our evaluation results and analysis show us the main avenues to improve on a future annotation process. We have also extracted the subjectivity of several rhetorical relations and the results show the effect of sentiment words in relations and the influence of each relation in the semantic orientation value.","PeriodicalId":243254,"journal":{"name":"Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128012669","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}
Xinhao Wang, Binod Gyawali, James V. Bruno, Hillary R. Molloy, Keelan Evanini, K. Zechner
This study aims to model the discourse structure of spontaneous spoken responses within the context of an assessment of English speaking proficiency for non-native speakers. Rhetorical Structure Theory (RST) has been commonly used in the analysis of discourse organization of written texts; however, limited research has been conducted to date on RST annotation and parsing of spoken language, in particular, non-native spontaneous speech. Due to the fact that the measurement of discourse coherence is typically a key metric in human scoring rubrics for assessments of spoken language, we conducted research to obtain RST annotations on non-native spoken responses from a standardized assessment of academic English proficiency. Subsequently, automatic parsers were trained on these annotations to process non-native spontaneous speech. Finally, a set of features were extracted from automatically generated RST trees to evaluate the discourse structure of non-native spontaneous speech, which were then employed to further improve the validity of an automated speech scoring system.
{"title":"Using Rhetorical Structure Theory to Assess Discourse Coherence for Non-native Spontaneous Speech","authors":"Xinhao Wang, Binod Gyawali, James V. Bruno, Hillary R. Molloy, Keelan Evanini, K. Zechner","doi":"10.18653/v1/W19-2719","DOIUrl":"https://doi.org/10.18653/v1/W19-2719","url":null,"abstract":"This study aims to model the discourse structure of spontaneous spoken responses within the context of an assessment of English speaking proficiency for non-native speakers. Rhetorical Structure Theory (RST) has been commonly used in the analysis of discourse organization of written texts; however, limited research has been conducted to date on RST annotation and parsing of spoken language, in particular, non-native spontaneous speech. Due to the fact that the measurement of discourse coherence is typically a key metric in human scoring rubrics for assessments of spoken language, we conducted research to obtain RST annotations on non-native spoken responses from a standardized assessment of academic English proficiency. Subsequently, automatic parsers were trained on these annotations to process non-native spontaneous speech. Finally, a set of features were extracted from automatically generated RST trees to evaluate the discourse structure of non-native spontaneous speech, which were then employed to further improve the validity of an automated speech scoring system.","PeriodicalId":243254,"journal":{"name":"Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127798580","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}
Development of discourse parsers to annotate the relational discourse structure of a text is crucial for many downstream tasks. However, most of the existing work focuses on English, assuming a quite large dataset. Discourse data have been annotated for Basque, but training a system on these data is challenging since the corpus is very small. In this paper, we create the first demonstrator based on RST for Basque, and we investigate the use of data in another language to improve the performance of a Basque discourse parser. More precisely, we build a monolingual system using the small set of data available and investigate the use of multilingual word embeddings to train a system for Basque using data annotated for another language. We found that our approach to building a system limited to the small set of data available for Basque allowed us to get an improvement over previous approaches making use of many data annotated in other languages. At best, we get 34.78 in F1 for the full discourse structure. More data annotation is necessary in order to improve the results obtained with these techniques. We also describe which relations match with the gold standard, in order to understand these results.
{"title":"EusDisParser: improving an under-resourced discourse parser with cross-lingual data","authors":"Mikel Iruskieta, Chloé Braud","doi":"10.18653/v1/w19-2709","DOIUrl":"https://doi.org/10.18653/v1/w19-2709","url":null,"abstract":"Development of discourse parsers to annotate the relational discourse structure of a text is crucial for many downstream tasks. However, most of the existing work focuses on English, assuming a quite large dataset. Discourse data have been annotated for Basque, but training a system on these data is challenging since the corpus is very small. In this paper, we create the first demonstrator based on RST for Basque, and we investigate the use of data in another language to improve the performance of a Basque discourse parser. More precisely, we build a monolingual system using the small set of data available and investigate the use of multilingual word embeddings to train a system for Basque using data annotated for another language. We found that our approach to building a system limited to the small set of data available for Basque allowed us to get an improvement over previous approaches making use of many data annotated in other languages. At best, we get 34.78 in F1 for the full discourse structure. More data annotation is necessary in order to improve the results obtained with these techniques. We also describe which relations match with the gold standard, in order to understand these results.","PeriodicalId":243254,"journal":{"name":"Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122263546","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}
This paper presents a new system for open-ended discourse relation signal annotation in the framework of Rhetorical Structure Theory (RST), implemented on top of an online tool for RST annotation. We discuss existing projects annotating textual signals of discourse relations, which have so far not allowed simultaneously structuring and annotating words signaling hierarchical discourse trees, and demonstrate the design and applications of our interface by extending existing RST annotations in the freely available GUM corpus.
{"title":"A Discourse Signal Annotation System for RST Trees","authors":"Luke Gessler, Yang Janet Liu, Amir Zeldes","doi":"10.18653/v1/W19-2708","DOIUrl":"https://doi.org/10.18653/v1/W19-2708","url":null,"abstract":"This paper presents a new system for open-ended discourse relation signal annotation in the framework of Rhetorical Structure Theory (RST), implemented on top of an online tool for RST annotation. We discuss existing projects annotating textual signals of discourse relations, which have so far not allowed simultaneously structuring and annotating words signaling hierarchical discourse trees, and demonstrate the design and applications of our interface by extending existing RST annotations in the freely available GUM corpus.","PeriodicalId":243254,"journal":{"name":"Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116710749","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：