Pub Date : 2020-11-20DOI: 10.18653/v1/2020.codi-1.9
Laurine Huber, Chaker Memmadi, Mathilde Dargnat, Y. Toussaint
We introduce four tasks designed to determine which sentence encoders best capture discourse properties of sentences from scientific abstracts, namely coherence and cohesion between clauses of a sentence, and discourse relations within sentences. We show that even if contextual encoders such as BERT or SciBERT encodes the coherence in discourse units, they do not help to predict three discourse relations commonly used in scientific abstracts. We discuss what these results underline, namely that these discourse relations are based on particular phrasing that allow non-contextual encoders to perform well.
{"title":"Do sentence embeddings capture discourse properties of sentences from Scientific Abstracts ?","authors":"Laurine Huber, Chaker Memmadi, Mathilde Dargnat, Y. Toussaint","doi":"10.18653/v1/2020.codi-1.9","DOIUrl":"https://doi.org/10.18653/v1/2020.codi-1.9","url":null,"abstract":"We introduce four tasks designed to determine which sentence encoders best capture discourse properties of sentences from scientific abstracts, namely coherence and cohesion between clauses of a sentence, and discourse relations within sentences. We show that even if contextual encoders such as BERT or SciBERT encodes the coherence in discourse units, they do not help to predict three discourse relations commonly used in scientific abstracts. We discuss what these results underline, namely that these discourse relations are based on particular phrasing that allow non-contextual encoders to perform well.","PeriodicalId":332037,"journal":{"name":"Proceedings of the First Workshop on Computational Approaches to Discourse","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133936090","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}
Pub Date : 2020-11-01DOI: 10.18653/v1/2020.codi-1.17
Grigorii Guz, G. Carenini
We present preliminary results on investigating the benefits of coreference resolution features for neural RST discourse parsing by considering different levels of coupling of the discourse parser with the coreference resolver. In particular, starting with a strong baseline neural parser unaware of any coreference information, we compare a parser which utilizes only the output of a neural coreference resolver, with a more sophisticated model, where discourse parsing and coreference resolution are jointly learned in a neural multitask fashion. Results indicate that these initial attempts to incorporate coreference information do not boost the performance of discourse parsing in a statistically significant way.
{"title":"Coreference for Discourse Parsing: A Neural Approach","authors":"Grigorii Guz, G. Carenini","doi":"10.18653/v1/2020.codi-1.17","DOIUrl":"https://doi.org/10.18653/v1/2020.codi-1.17","url":null,"abstract":"We present preliminary results on investigating the benefits of coreference resolution features for neural RST discourse parsing by considering different levels of coupling of the discourse parser with the coreference resolver. In particular, starting with a strong baseline neural parser unaware of any coreference information, we compare a parser which utilizes only the output of a neural coreference resolver, with a more sophisticated model, where discourse parsing and coreference resolution are jointly learned in a neural multitask fashion. Results indicate that these initial attempts to incorporate coreference information do not boost the performance of discourse parsing in a statistically significant way.","PeriodicalId":332037,"journal":{"name":"Proceedings of the First Workshop on Computational Approaches to Discourse","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125512759","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}
Pub Date : 2020-11-01DOI: 10.18653/v1/2020.codi-1.1
Shuyuan Cao
With their huge speaking populations in the world, Spanish and Chinese occupy important positions in linguistic studies. Since the two languages come from different language systems, the translation between Spanish and Chinese is complicated. A comparative study for the language pair can discover the discourse differences between Spanish and Chinese, and can benefit the Spanish-Chinese translation. In this work, based on a Spanish-Chinese parallel corpus annotated with discourse information, we compare the annotation results between the language pair and analyze how discourse affects Spanish-Chinese translation. The research results in our study can help human translators who work with the language pair.
{"title":"How does discourse affect Spanish-Chinese Translation? A case study based on a Spanish-Chinese parallel corpus","authors":"Shuyuan Cao","doi":"10.18653/v1/2020.codi-1.1","DOIUrl":"https://doi.org/10.18653/v1/2020.codi-1.1","url":null,"abstract":"With their huge speaking populations in the world, Spanish and Chinese occupy important positions in linguistic studies. Since the two languages come from different language systems, the translation between Spanish and Chinese is complicated. A comparative study for the language pair can discover the discourse differences between Spanish and Chinese, and can benefit the Spanish-Chinese translation. In this work, based on a Spanish-Chinese parallel corpus annotated with discourse information, we compare the annotation results between the language pair and analyze how discourse affects Spanish-Chinese translation. The research results in our study can help human translators who work with the language pair.","PeriodicalId":332037,"journal":{"name":"Proceedings of the First Workshop on Computational Approaches to Discourse","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133891415","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}
Pub Date : 2020-11-01DOI: 10.18653/v1/2020.codi-1.7
René Knaebel, Manfred Stede
This paper studies a novel model that simplifies the disambiguation of connectives for explicit discourse relations. We use a neural approach that integrates contextualized word embeddings and predicts whether a connective candidate is part of a discourse relation or not. We study the influence of those context-specific embeddings. Further, we show the benefit of training the tasks of connective disambiguation and sense classification together at the same time. The success of our approach is supported by state-of-the-art results.
{"title":"Contextualized Embeddings for Connective Disambiguation in Shallow Discourse Parsing","authors":"René Knaebel, Manfred Stede","doi":"10.18653/v1/2020.codi-1.7","DOIUrl":"https://doi.org/10.18653/v1/2020.codi-1.7","url":null,"abstract":"This paper studies a novel model that simplifies the disambiguation of connectives for explicit discourse relations. We use a neural approach that integrates contextualized word embeddings and predicts whether a connective candidate is part of a discourse relation or not. We study the influence of those context-specific embeddings. Further, we show the benefit of training the tasks of connective disambiguation and sense classification together at the same time. The success of our approach is supported by state-of-the-art results.","PeriodicalId":332037,"journal":{"name":"Proceedings of the First Workshop on Computational Approaches to Discourse","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117171465","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}
Pub Date : 2020-11-01DOI: 10.18653/v1/2020.codi-1.12
F. Same, Kees van Deemter
First, we discuss the most common linguistic perspectives on the concept of recency and propose a taxonomy of recency metrics employed in Machine Learning studies for choosing the form of referring expressions in discourse context. We then report on a Multi-Layer Perceptron study and a Sequential Forward Search experiment, followed by Bayes Factor analysis of the outcomes. The results suggest that recency metrics counting paragraphs and sentences contribute to referential choice prediction more than other recency-related metrics. Based on the results of our analysis, we argue that, sensitivity to discourse structure is important for recency metrics used in determining referring expression forms.
{"title":"Computational Interpretation of Recency for the Choice of Referring Expressions in Discourse","authors":"F. Same, Kees van Deemter","doi":"10.18653/v1/2020.codi-1.12","DOIUrl":"https://doi.org/10.18653/v1/2020.codi-1.12","url":null,"abstract":"First, we discuss the most common linguistic perspectives on the concept of recency and propose a taxonomy of recency metrics employed in Machine Learning studies for choosing the form of referring expressions in discourse context. We then report on a Multi-Layer Perceptron study and a Sequential Forward Search experiment, followed by Bayes Factor analysis of the outcomes. The results suggest that recency metrics counting paragraphs and sentences contribute to referential choice prediction more than other recency-related metrics. Based on the results of our analysis, we argue that, sensitivity to discourse structure is important for recency metrics used in determining referring expression forms.","PeriodicalId":332037,"journal":{"name":"Proceedings of the First Workshop on Computational Approaches to Discourse","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125728381","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}
Pub Date : 2020-11-01DOI: 10.18653/v1/2020.codi-1.10
Yunmo Chen, Tongfei Chen, Benjamin Van Durme
We recognize the task of event argument linking in documents as similar to that of intent slot resolution in dialogue, providing a Transformer-based model that extends from a recently proposed solution to resolve references to slots. The approach allows for joint consideration of argument candidates given a detected event, which we illustrate leads to state-of-the-art performance in multi-sentence argument linking.
{"title":"Joint Modeling of Arguments for Event Understanding","authors":"Yunmo Chen, Tongfei Chen, Benjamin Van Durme","doi":"10.18653/v1/2020.codi-1.10","DOIUrl":"https://doi.org/10.18653/v1/2020.codi-1.10","url":null,"abstract":"We recognize the task of event argument linking in documents as similar to that of intent slot resolution in dialogue, providing a Transformer-based model that extends from a recently proposed solution to resolve references to slots. The approach allows for joint consideration of argument candidates given a detected event, which we illustrate leads to state-of-the-art performance in multi-sentence argument linking.","PeriodicalId":332037,"journal":{"name":"Proceedings of the First Workshop on Computational Approaches to Discourse","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125464973","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}
Pub Date : 2020-11-01DOI: 10.18653/v1/2020.codi-1.6
Ekaterina Lapshinova-Koltunski, K. Kunz
The present paper focuses on variation phenomena in coreference chains. We address the hypothesis that the degree of structural variation between chain elements depends on language-specific constraints and preferences and, even more, on the communicative situation of language production. We define coreference features that also include reference to abstract entities and events. These features are inspired through several sources – cognitive parameters, pragmatic factors and typological status. We pay attention to the distributions of these features in a dataset containing English and German texts of spoken and written discourse mode, which can be classified into seven different registers. We apply text classification and feature selection to find out how these variational dimensions (language, mode and register) impact on coreference features. Knowledge on the variation under analysis is valuable for contrastive linguistics, translation studies and multilingual natural language processing (NLP), e.g. machine translation or cross-lingual coreference resolution.
{"title":"Exploring Coreference Features in Heterogeneous Data with Text Classification","authors":"Ekaterina Lapshinova-Koltunski, K. Kunz","doi":"10.18653/v1/2020.codi-1.6","DOIUrl":"https://doi.org/10.18653/v1/2020.codi-1.6","url":null,"abstract":"The present paper focuses on variation phenomena in coreference chains. We address the hypothesis that the degree of structural variation between chain elements depends on language-specific constraints and preferences and, even more, on the communicative situation of language production. We define coreference features that also include reference to abstract entities and events. These features are inspired through several sources – cognitive parameters, pragmatic factors and typological status. We pay attention to the distributions of these features in a dataset containing English and German texts of spoken and written discourse mode, which can be classified into seven different registers. We apply text classification and feature selection to find out how these variational dimensions (language, mode and register) impact on coreference features. Knowledge on the variation under analysis is valuable for contrastive linguistics, translation studies and multilingual natural language processing (NLP), e.g. machine translation or cross-lingual coreference resolution.","PeriodicalId":332037,"journal":{"name":"Proceedings of the First Workshop on Computational Approaches to Discourse","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125943792","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}
Pub Date : 1900-01-01DOI: 10.18653/v1/2020.codi-1.2
M. Maitreyee
This work proposes a framework to predict sequences in dialogues, using turn based syntactic features and dialogue control functions. Syntactic features were extracted using dependency parsing, while dialogue control functions were manually labelled. These features were transformed using tf-idf and word embedding; feature selection was done using Principal Component Analysis (PCA). We ran experiments on six combinations of features to predict sequences with Hierarchical Agglomerative Clustering. An analysis of the clustering results indicate that using word-embeddings and syntactic features, significantly improved the results.
{"title":"Beyond Adjacency Pairs: Hierarchical Clustering of Long Sequences for Human-Machine Dialogues","authors":"M. Maitreyee","doi":"10.18653/v1/2020.codi-1.2","DOIUrl":"https://doi.org/10.18653/v1/2020.codi-1.2","url":null,"abstract":"This work proposes a framework to predict sequences in dialogues, using turn based syntactic features and dialogue control functions. Syntactic features were extracted using dependency parsing, while dialogue control functions were manually labelled. These features were transformed using tf-idf and word embedding; feature selection was done using Principal Component Analysis (PCA). We ran experiments on six combinations of features to predict sequences with Hierarchical Agglomerative Clustering. An analysis of the clustering results indicate that using word-embeddings and syntactic features, significantly improved the results.","PeriodicalId":332037,"journal":{"name":"Proceedings of the First Workshop on Computational Approaches to Discourse","volume":"82 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":"116941709","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：