Pub Date : 2019-10-22DOI: 10.26615/978-954-452-056-4_024
P. Costa, Ivandré Paraboni
In Natural Language Generation systems, personalization strategies - i.e, the use of information about a target author to generate text that (more) closely resembles human-produced language - have long been applied to improve results. The present work addresses one such strategy - namely, the use of Big Five personality information about the target author - applied to the case of abstractive text summarization using neural sequence-to-sequence models. Initial results suggest that having access to personality information does lead to more accurate (or human-like) text summaries, and paves the way for more robust systems of this kind.
{"title":"Personality-dependent Neural Text Summarization","authors":"P. Costa, Ivandré Paraboni","doi":"10.26615/978-954-452-056-4_024","DOIUrl":"https://doi.org/10.26615/978-954-452-056-4_024","url":null,"abstract":"In Natural Language Generation systems, personalization strategies - i.e, the use of information about a target author to generate text that (more) closely resembles human-produced language - have long been applied to improve results. The present work addresses one such strategy - namely, the use of Big Five personality information about the target author - applied to the case of abstractive text summarization using neural sequence-to-sequence models. Initial results suggest that having access to personality information does lead to more accurate (or human-like) text summaries, and paves the way for more robust systems of this kind.","PeriodicalId":284493,"journal":{"name":"Recent Advances in Natural Language Processing","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114691344","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 : 2019-10-22DOI: 10.26615/978-954-452-056-4_150
Fei Wang, R. Ross, John D. Kelleher
The current state of the art for First Story Detection (FSD) are nearest neighbour-based models with traditional term vector representations; however, one challenge faced by FSD models is that the document representation is usually defined by the vocabulary and term frequency from a background corpus. Consequently, the ideal background corpus should arguably be both large-scale to ensure adequate term coverage, and similar to the target domain in terms of the language distribution. However, given these two factors cannot always be mutually satisfied, in this paper we examine whether the distributional similarity of common terms is more important than the scale of common terms for FSD. As a basis for our analysis we propose a set of metrics to quantitatively measure the scale of common terms and the distributional similarity between corpora. Using these metrics we rank different background corpora relative to a target corpus. We also apply models based on different background corpora to the FSD task. Our results show that term distributional similarity is more predictive of good FSD performance than the scale of common terms; and, thus we demonstrate that a smaller recent domain-related corpus will be more suitable than a very large-scale general corpus for FSD.
{"title":"Bigger versus Similar: Selecting a Background Corpus for First Story Detection Based on Distributional Similarity","authors":"Fei Wang, R. Ross, John D. Kelleher","doi":"10.26615/978-954-452-056-4_150","DOIUrl":"https://doi.org/10.26615/978-954-452-056-4_150","url":null,"abstract":"The current state of the art for First Story Detection (FSD) are nearest neighbour-based models with traditional term vector representations; however, one challenge faced by FSD models is that the document representation is usually defined by the vocabulary and term frequency from a background corpus. Consequently, the ideal background corpus should arguably be both large-scale to ensure adequate term coverage, and similar to the target domain in terms of the language distribution. However, given these two factors cannot always be mutually satisfied, in this paper we examine whether the distributional similarity of common terms is more important than the scale of common terms for FSD. As a basis for our analysis we propose a set of metrics to quantitatively measure the scale of common terms and the distributional similarity between corpora. Using these metrics we rank different background corpora relative to a target corpus. We also apply models based on different background corpora to the FSD task. Our results show that term distributional similarity is more predictive of good FSD performance than the scale of common terms; and, thus we demonstrate that a smaller recent domain-related corpus will be more suitable than a very large-scale general corpus for FSD.","PeriodicalId":284493,"journal":{"name":"Recent Advances in Natural Language Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127594758","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 : 2019-10-22DOI: 10.26615/978-954-452-056-4_103
Sean Papay, Sebastian Padó
The detection of quotations (i.e., reported speech, thought, and writing) has established itself as an NLP analysis task. However, state-of-the-art models have been developed on the basis of specific corpora and incorpo- rate a high degree of corpus-specific assumptions and knowledge, which leads to fragmentation. In the spirit of task-agnostic modeling, we present a corpus-agnostic neural model for quotation detection and evaluate it on three corpora that vary in language, text genre, and structural assumptions. The model (a) approaches the state-of-the-art on the corpora when using established feature sets and (b) shows reasonable performance even when us- ing solely word forms, which makes it applicable for non-standard (i.e., historical) corpora.
{"title":"Quotation Detection and Classification with a Corpus-Agnostic Model","authors":"Sean Papay, Sebastian Padó","doi":"10.26615/978-954-452-056-4_103","DOIUrl":"https://doi.org/10.26615/978-954-452-056-4_103","url":null,"abstract":"The detection of quotations (i.e., reported speech, thought, and writing) has established itself as an NLP analysis task. However, state-of-the-art models have been developed on the basis of specific corpora and incorpo- rate a high degree of corpus-specific assumptions and knowledge, which leads to fragmentation. In the spirit of task-agnostic modeling, we present a corpus-agnostic neural model for quotation detection and evaluate it on three corpora that vary in language, text genre, and structural assumptions. The model (a) approaches the state-of-the-art on the corpora when using established feature sets and (b) shows reasonable performance even when us- ing solely word forms, which makes it applicable for non-standard (i.e., historical) corpora.","PeriodicalId":284493,"journal":{"name":"Recent Advances in Natural Language Processing","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115837696","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 : 2019-10-22DOI: 10.26615/978-954-452-056-4_009
Uğurcan Arıkan, Onur Güngör, S. Uskudarli
For the spell correction task, vocabulary based methods have been replaced with methods that take morphological and grammar rules into account. However, such tools are fairly immature, and, worse, non-existent for many low resource languages. Checking only if a word is well-formed with respect to the morphological rules of a language may produce false negatives due to the ambiguity resulting from the presence of numerous homophonic words. In this work, we propose an approach to detect and correct the “de/da” clitic errors in Turkish text. Our model is a neural sequence tagger trained with a synthetically constructed dataset consisting of positive and negative samples. The model’s performance with this dataset is presented according to different word embedding configurations. The model achieved an F1 score of 86.67% on a synthetically constructed dataset. We also compared the model’s performance on a manually curated dataset of challenging samples that proved superior to other spelling correctors with 71% accuracy compared to the second-best (Google Docs) with and accuracy of 34%.
{"title":"Detecting Clitics Related Orthographic Errors in Turkish","authors":"Uğurcan Arıkan, Onur Güngör, S. Uskudarli","doi":"10.26615/978-954-452-056-4_009","DOIUrl":"https://doi.org/10.26615/978-954-452-056-4_009","url":null,"abstract":"For the spell correction task, vocabulary based methods have been replaced with methods that take morphological and grammar rules into account. However, such tools are fairly immature, and, worse, non-existent for many low resource languages. Checking only if a word is well-formed with respect to the morphological rules of a language may produce false negatives due to the ambiguity resulting from the presence of numerous homophonic words. In this work, we propose an approach to detect and correct the “de/da” clitic errors in Turkish text. Our model is a neural sequence tagger trained with a synthetically constructed dataset consisting of positive and negative samples. The model’s performance with this dataset is presented according to different word embedding configurations. The model achieved an F1 score of 86.67% on a synthetically constructed dataset. We also compared the model’s performance on a manually curated dataset of challenging samples that proved superior to other spelling correctors with 71% accuracy compared to the second-best (Google Docs) with and accuracy of 34%.","PeriodicalId":284493,"journal":{"name":"Recent Advances in Natural Language Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132526666","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 : 2019-10-22DOI: 10.26615/978-954-452-056-4_144
Martin Vita, Jakub Klímek
Natural language inference (NLI) is a key part of natural language understanding. The NLI task is defined as a decision problem whether a given sentence – hypothesis – can be inferred from a given text. Typically, we deal with a text consisting of just a single premise/single sentence, which is called a single premise entailment (SPE) task. Recently, a derived task of NLI from multiple premises (MPE) was introduced together with the first annotated corpus and corresponding several strong baselines. Nevertheless, the further development in MPE field requires accessibility of huge amounts of annotated data. In this paper we introduce a novel method for rapid deriving of MPE corpora from an existing NLI (SPE) annotated data that does not require any additional annotation work. This proposed approach is based on using an open information extraction system. We demonstrate the application of the method on a well known SNLI corpus. Over the obtained corpus, we provide the first evaluations as well as we state a strong baseline.
{"title":"Exploiting Open IE for Deriving Multiple Premises Entailment Corpus","authors":"Martin Vita, Jakub Klímek","doi":"10.26615/978-954-452-056-4_144","DOIUrl":"https://doi.org/10.26615/978-954-452-056-4_144","url":null,"abstract":"Natural language inference (NLI) is a key part of natural language understanding. The NLI task is defined as a decision problem whether a given sentence – hypothesis – can be inferred from a given text. Typically, we deal with a text consisting of just a single premise/single sentence, which is called a single premise entailment (SPE) task. Recently, a derived task of NLI from multiple premises (MPE) was introduced together with the first annotated corpus and corresponding several strong baselines. Nevertheless, the further development in MPE field requires accessibility of huge amounts of annotated data. In this paper we introduce a novel method for rapid deriving of MPE corpora from an existing NLI (SPE) annotated data that does not require any additional annotation work. This proposed approach is based on using an open information extraction system. We demonstrate the application of the method on a well known SNLI corpus. Over the obtained corpus, we provide the first evaluations as well as we state a strong baseline.","PeriodicalId":284493,"journal":{"name":"Recent Advances in Natural Language Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130840660","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 : 2019-10-22DOI: 10.26615/978-954-452-056-4_046
Dhouha Ghazouani, L. Lancieri, Habib Ounelli, J. Chaker
Every day, the emotion and opinion of different people across the world are reflected in the form of short messages using microblogging platforms. Despite the existence of enormous potential introduced by this data source, the Twitter community is still ambiguous and is not fully explored yet. While there are a huge number of studies examining the possibilities of inferring gender and age, there exist hardly researches on socioeconomic status (SES) inference of Twitter users. As socioeconomic status is essential to treating diverse questions linked to human behavior in several fields (sociology, demography, public health, etc.), we conducted a comprehensive literature review of SES studies, inference methods, and metrics. With reference to the research on literature’s results, we came to outline the most critical challenges for researchers. To the best of our knowledge, this paper is the first review that introduces the different aspects of SES inference. Indeed, this article provides the benefits for practitioners who aim to process and explore Twitter SES inference.
{"title":"Assessing socioeconomic status of Twitter users: A survey","authors":"Dhouha Ghazouani, L. Lancieri, Habib Ounelli, J. Chaker","doi":"10.26615/978-954-452-056-4_046","DOIUrl":"https://doi.org/10.26615/978-954-452-056-4_046","url":null,"abstract":"Every day, the emotion and opinion of different people across the world are reflected in the form of short messages using microblogging platforms. Despite the existence of enormous potential introduced by this data source, the Twitter community is still ambiguous and is not fully explored yet. While there are a huge number of studies examining the possibilities of inferring gender and age, there exist hardly researches on socioeconomic status (SES) inference of Twitter users. As socioeconomic status is essential to treating diverse questions linked to human behavior in several fields (sociology, demography, public health, etc.), we conducted a comprehensive literature review of SES studies, inference methods, and metrics. With reference to the research on literature’s results, we came to outline the most critical challenges for researchers. To the best of our knowledge, this paper is the first review that introduces the different aspects of SES inference. Indeed, this article provides the benefits for practitioners who aim to process and explore Twitter SES inference.","PeriodicalId":284493,"journal":{"name":"Recent Advances in Natural Language Processing","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131105478","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 : 2019-10-22DOI: 10.26615/978-954-452-056-4_067
Venelin Kovatchev, M. A. Martí, Maria Salamó, Javier Beltrán
In this paper, we present a new approach for the evaluation, error analysis, and interpretation of supervised and unsupervised Paraphrase Identification (PI) systems. Our evaluation framework makes use of a PI corpus annotated with linguistic phenomena to provide a better understanding and interpretation of the performance of various PI systems. Our approach allows for a qualitative evaluation and comparison of the PI models using human interpretable categories. It does not require modification of the training objective of the systems and does not place additional burden on the developers. We replicate several popular supervised and unsupervised PI systems. Using our evaluation framework we show that: 1) Each system performs differently with respect to a set of linguistic phenomena and makes qualitatively different kinds of errors; 2) Some linguistic phenomena are more challenging than others across all systems.
{"title":"A Qualitative Evaluation Framework for Paraphrase Identification","authors":"Venelin Kovatchev, M. A. Martí, Maria Salamó, Javier Beltrán","doi":"10.26615/978-954-452-056-4_067","DOIUrl":"https://doi.org/10.26615/978-954-452-056-4_067","url":null,"abstract":"In this paper, we present a new approach for the evaluation, error analysis, and interpretation of supervised and unsupervised Paraphrase Identification (PI) systems. Our evaluation framework makes use of a PI corpus annotated with linguistic phenomena to provide a better understanding and interpretation of the performance of various PI systems. Our approach allows for a qualitative evaluation and comparison of the PI models using human interpretable categories. It does not require modification of the training objective of the systems and does not place additional burden on the developers. We replicate several popular supervised and unsupervised PI systems. Using our evaluation framework we show that: 1) Each system performs differently with respect to a set of linguistic phenomena and makes qualitatively different kinds of errors; 2) Some linguistic phenomena are more challenging than others across all systems.","PeriodicalId":284493,"journal":{"name":"Recent Advances in Natural Language Processing","volume":"541 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133453693","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 : 2019-10-22DOI: 10.26615/978-954-452-056-4_123
W. Santos, Ivandré Paraboni
We introduce a labelled corpus of stances about moral issues for the Brazilian Portuguese language, and present reference results for both the stance recognition and polarity classification tasks. The corpus is built from Twitter and further expanded with data elicited through crowd sourcing and labelled by their own authors. Put together, the corpus and reference results are expected to be taken as a baseline for further studies in the field of stance recognition and polarity classification from text.
{"title":"Moral Stance Recognition and Polarity Classification from Twitter and Elicited Text","authors":"W. Santos, Ivandré Paraboni","doi":"10.26615/978-954-452-056-4_123","DOIUrl":"https://doi.org/10.26615/978-954-452-056-4_123","url":null,"abstract":"We introduce a labelled corpus of stances about moral issues for the Brazilian Portuguese language, and present reference results for both the stance recognition and polarity classification tasks. The corpus is built from Twitter and further expanded with data elicited through crowd sourcing and labelled by their own authors. Put together, the corpus and reference results are expected to be taken as a baseline for further studies in the field of stance recognition and polarity classification from text.","PeriodicalId":284493,"journal":{"name":"Recent Advances in Natural Language Processing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133677459","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 : 2019-10-22DOI: 10.26615/978-954-452-056-4_146
Tatiana Vodolazova, Elena Lloret
In this paper we describe how an abstractive text summarization method improved the informativeness of automatic summaries by integrating syntactic text simplification, subject-verb-object concept frequency scoring and a set of rules that transform text into its semantic representation. We analyzed the impact of each component of our approach on the quality of generated summaries and tested it on DUC 2002 dataset. Our experiments showed that our approach outperformed other state-of-the-art abstractive methods while maintaining acceptable linguistic quality and redundancy rate.
{"title":"The Impact of Rule-Based Text Generation on the Quality of Abstractive Summaries","authors":"Tatiana Vodolazova, Elena Lloret","doi":"10.26615/978-954-452-056-4_146","DOIUrl":"https://doi.org/10.26615/978-954-452-056-4_146","url":null,"abstract":"In this paper we describe how an abstractive text summarization method improved the informativeness of automatic summaries by integrating syntactic text simplification, subject-verb-object concept frequency scoring and a set of rules that transform text into its semantic representation. We analyzed the impact of each component of our approach on the quality of generated summaries and tested it on DUC 2002 dataset. Our experiments showed that our approach outperformed other state-of-the-art abstractive methods while maintaining acceptable linguistic quality and redundancy rate.","PeriodicalId":284493,"journal":{"name":"Recent Advances in Natural Language Processing","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115724041","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 : 2019-10-22DOI: 10.26615/978-954-452-056-4_015
Michele Bevilacqua, Roberto Navigli
While contextualized embeddings have produced performance breakthroughs in many Natural Language Processing (NLP) tasks, Word Sense Disambiguation (WSD) has not benefited from them yet. In this paper, we introduce QBERT, a Transformer-based architecture for contextualized embeddings which makes use of a co-attentive layer to produce more deeply bidirectional representations, better-fitting for the WSD task. As a result, we are able to train a WSD system that beats the state of the art on the concatenation of all evaluation datasets by over 3 points, also outperforming a comparable model using ELMo.
{"title":"Quasi Bidirectional Encoder Representations from Transformers for Word Sense Disambiguation","authors":"Michele Bevilacqua, Roberto Navigli","doi":"10.26615/978-954-452-056-4_015","DOIUrl":"https://doi.org/10.26615/978-954-452-056-4_015","url":null,"abstract":"While contextualized embeddings have produced performance breakthroughs in many Natural Language Processing (NLP) tasks, Word Sense Disambiguation (WSD) has not benefited from them yet. In this paper, we introduce QBERT, a Transformer-based architecture for contextualized embeddings which makes use of a co-attentive layer to produce more deeply bidirectional representations, better-fitting for the WSD task. As a result, we are able to train a WSD system that beats the state of the art on the concatenation of all evaluation datasets by over 3 points, also outperforming a comparable model using ELMo.","PeriodicalId":284493,"journal":{"name":"Recent Advances in Natural Language Processing","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124152302","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：