Discourse Parser

Notes:

Shallow discourse parsing is the task of identifying and classifying the discourse relations between different units of text, such as sentences or paragraphs. These relations can include things like cause-effect, contrast, and elaboration, and can help to convey the overall structure and meaning of a text.

In shallow discourse parsing, the goal is to identify and classify the discourse relations between the units of text, but not to build a deeper structure that connects these relations in a tree or graph. This is in contrast to deep discourse parsing, which aims to build a more comprehensive and connected structure that represents the discourse relations in a text.

Shallow discourse parsing is often used in natural language processing and text analysis applications to understand the meaning and structure of a text. It can be useful for tasks such as text summarization, question answering, and information extraction, among others.

A discourse parser is a type of natural language processing (NLP) tool that is designed to analyze the discourse structure of a text. A discourse parser works by identifying and classifying the discourse relations between different units of text, such as sentences or paragraphs. These relations can include things like cause-effect, contrast, and elaboration, and can help to convey the overall structure and meaning of a text.

There are two main types of discourse parsers: shallow discourse parsers and deep discourse parsers. Shallow discourse parsers are focused on identifying and classifying the discourse relations between the units of text, but do not build a deeper structure that connects these relations in a tree or graph. Deep discourse parsers, on the other hand, aim to build a more comprehensive and connected structure that represents the discourse relations in a text.

Discourse parsers can be used in a variety of natural language processing tasks, including text summarization, question answering, and information extraction. They can be trained using supervised learning methods, and can be trained on large datasets of annotated text to improve their performance.

Deep discourse parsing is a natural language processing task that involves building a deeper, more comprehensive structure that represents the discourse relations in a text. This structure is often in the form of a tree or graph, and can include the connections between different units of text, such as sentences or paragraphs, as well as the relationships between these connections.

There are several approaches to deep discourse parsing, but most involve using machine learning algorithms to analyze the text and identify the discourse relations between different units. This can be done using supervised learning techniques, in which the algorithm is trained on a large dataset of annotated text, or unsupervised learning techniques, in which the algorithm learns to identify the discourse relations on its own.

Once the discourse relations have been identified and classified, the algorithm can then build a representation of the overall discourse structure of the text. This representation can be used to better understand the meaning and structure of the text, and can be useful for tasks such as text summarization, question answering, and information extraction.

  • Argument mining is the process of automatically identifying, extracting, and analyzing arguments from natural language text. This can include identifying the premises and conclusions of an argument, as well as the relationships between different arguments within a text.
  • Automatic discourse segmentation is the process of automatically dividing a text into coherent segments, such as paragraphs or sections. This can be useful for tasks such as text summarization or information extraction, as it allows for the text to be more easily understood and processed.
  • Coherence relations are the relationships that exist between different units of text, such as sentences or paragraphs, that help to convey the overall meaning and structure of a text. These relations can include things like cause-effect, contrast, and elaboration.
  • Discourse parsing is the process of analyzing the discourse structure of a text, including the identification and classification of the discourse relations between different units of text. This can be useful for tasks such as text summarization, question answering, and information extraction, as it can help to better understand the meaning and structure of a text.
  • Discourse processing system is a type of software or system that is designed to analyze and process the discourse structure of a text. This can include tasks such as identifying the discourse relations between different units of text and building a representation of the overall discourse structure of a text.
  • Discourse relation classification is the process of identifying and classifying the discourse relations between different units of text. These relations can include things like cause-effect, contrast, and elaboration, and can help to convey the overall meaning and structure of a text.
  • Discourse representation is a representation of the discourse structure of a text, including the discourse relations between different units of text and their overall organization. This can be in the form of a tree or graph structure, and can be used to better understand the meaning and structure of a text.
  • Discourse segmentation is the process of dividing a text into coherent segments, such as paragraphs or sections. This can be useful for tasks such as text summarization or information extraction, as it allows for the text to be more easily understood and processed.
  • Discourse segmenter is a type of natural language processing tool that is designed to automatically divide a text into coherent segments, such as paragraphs or sections.
  • Discourse structures are the overall organization and relationships between different units of text, such as sentences or paragraphs, that help to convey the meaning and structure of a text. These structures can include things like cause-effect relations, contrast, and elaboration.
  • Discourse units are the individual units of text that make up a larger text, such as sentences or paragraphs. In discourse analysis, these units are often analyzed in terms of their relationships to one another and their role in conveying the overall meaning and structure of a text.
  • Shallow discourse parsing is the process of analyzing the discourse structure of a text, including the identification and classification of the discourse relations between different units of text. However, shallow discourse parsing does not build a deeper structure that connects these relations in a tree or graph, as deep discourse parsing does.

Resources:

Wikipedia:

References:

See also:

100 Best Discourse Analysis Videos | Computational Discourse | Computational Discourse Analysis | Discourse Analysis & Chatbots | Discourse Unit & Dialog Systems | Rhetorical Parser

Modeling discourse cohesion for discourse parsing via memory network
Y Jia, Y Ye, Y Feng, Y Lai, R Yan, D Zhao – … of the 56th Annual Meeting of …, 2018 – aclweb.org
… Most existing approaches design sophisticated features or exploit various off-the-shelf tools, but achieve little success. In this paper, we propose a new transition-based discourse parser that makes use of memory networks to take discourse cohesion into account …

Detecting logical argumentation in text via communicative discourse tree
B Galitsky, D Ilvovsky, SO Kuznetsov – Journal of Experimental & …, 2018 – Taylor & Francis
… Not many applications rely on DTs, obtained by one or another discourse parser, to solve a document classifica- tion or analysis problems, although DTs provide rather rich high-level information about a document structure …

Signalling of coherence relations in discourse, beyond discourse markers
D Das, M Taboada – Discourse Processes, 2018 – Taylor & Francis
Page 1. Signalling of Coherence Relations in Discourse, Beyond Discourse Markers Debopam Dasa and Maite Taboadab aDepartment of Linguistics, University of Potsdam, Potsdam, Germany; bDepartment of Linguistics, Simon …

Constructing a lexicon of English discourse connectives
D Das, T Scheffler, P Bourgonje, M Stede – Proceedings of the 19th …, 2018 – aclweb.org
… 2010. HILDA: A Discourse Parser Using Support Vector Machine Classification. Dialogue and Discourse, 1(3):1–33 … Ziheng Lin, Hwee Tou Ng, and Min-Yen Kan. 2014. A PDTB-Styled End-to-End Discourse Parser. Natu- ral Language Engineering, 20(2):151184 …

Identifying explicit discourse connectives in German
P Bourgonje, M Stede – Proceedings of the 19th Annual SIGdial Meeting …, 2018 – aclweb.org
… We will adopt it for our goal, viz. developing an end-to-end discourse parser for German. This paper focuses on the first step in the pipeline and introduces a connective identification module for German … 2016. A Constituent Syntactic Parse Tree Based Discourse Parser …

A lexicon of discourse markers for portuguese–ldm-pt
A Mendes, I del Rio, M Stede… – … Conference on Language …, 2018 – repositorio.ul.pt
… Pardo, T. and Nunes, M. (2008). On the development and evaluation of a Brazilian Portuguese discourse parser. Journal of Theoretical and Applied Computing, vol. 15, pp … Ziheng, L., Hwee, TN and Min-Yen, K. (2014). A PDTB-Styled End-to-End Discourse Parser …

Improving Implicit Discourse Relation Classification by Modeling Inter-dependencies of Discourse Units in a Paragraph
Z Dai, R Huang – arXiv preprint arXiv:1804.05918, 2018 – arxiv.org
… Therefore, the multi-way classification set- ting is more appropriate and natural in evaluat- ing a practical end-to-end discourse parser, and we mainly evaluate our proposed models using the four-way multi-class classification setting …

Deep enhanced representation for implicit discourse relation recognition
H Bai, H Zhao – arXiv preprint arXiv:1807.05154, 2018 – arxiv.org
… 2016. A constituent syntactic parse tree based discourse parser. In Proceedings of the Twentieth Conference on Computational Natural Language Learning (CoNLL) – Shared Task, pages 60–64, Berlin, Germany, August. Ziheng Lin, Min-Yen Kan, and Hwee Tou Ng. 2009 …

Employing text matching network to recognise nuclearity in chinese discourse
S Xu, P Li, G Zhou, Q Zhu – … of the 27th International Conference on …, 2018 – aclweb.org
… Kong and Zhou (2017) inte- grated some previous research and proposed a CDT-styled End-to-End discourse parser, which can au- tomatically detect discourse units and perform all three discourse parsing subtasks in sequence …

Tag-enhanced tree-structured neural networks for implicit discourse relation classification
Y Wang, S Li, J Yang, X Sun, H Wang – arXiv preprint arXiv:1803.01165, 2018 – arxiv.org
… According to Rutherford and Xue (2014), the multi-class classification setting is more natu- ral and realistic. Moreover, the multi-class clas- sifier can directly serve as one building block of a complete discourse parser (Qin et al., 2017) …

A Discourse Parser Language Model Based on Improved Neural Network in Machine Translation
C Xue – … Conference on Intelligent Transportation, Big Data & …, 2018 – ieeexplore.ieee.org
The development of statistical machine translation technology is so fast and there are many new models and methods. This obtains great achievement in translation of simple sentence or fixed sentence with certain applications. However, there still exists poor coherence and …

Learning structured text representations
Y Liu, M Lapata – Transactions of the Association for Computational …, 2018 – MIT Press
… mlap@inf.ed.ac.uk Abstract In this paper, we focus on learning structure- aware document representations from data without recourse to a discourse parser or addi- tional annotations. Drawing inspiration from recent efforts to …

Acquiring annotated data with cross-lingual explicitation for implicit discourse relation classification
W Shi, F Yung, V Demberg – arXiv preprint arXiv:1808.10290, 2018 – arxiv.org
… sev- eral languages may yield the same connective be- cause the original English sentence actually was not really unmarked, but rather contained an ex- pression which could not be automatically recog- nized as a discourse relation marker by the auto- matic discourse parser …

Modeling sentiment association in discourse for humor recognition
L Liu, D Zhang, W Song – Proceedings of the 56th Annual Meeting of the …, 2018 – aclweb.org
… In this paper, we utilize a discourse parser to get comparable text units and measure sentiment association among them. 3.1 Discourse Parsing … We use the discourse parser implemented by Feng and Hirst (2012) to automatically recog- nize RST style discourse relations …

Improved Discourse Parsing with Two-Step Neural Transition-Based Model
Y Jia, Y Feng, Y Ye, C Lv, C Shi, D Zhao – ACM Transactions on Asian …, 2018 – dl.acm.org
… tools. Joty and Moschitti [19] rely on reranking discourse trees generated by an existing probabilistic discourse parser. Feng and Hirst [10] add constraints in the Viterbi decoding and postedit the fully built discourse trees. Although …

Assessing Crosslingual Discourse Relations in Machine Translation
KS Smith, L Specia – arXiv preprint arXiv:1810.03148, 2018 – arxiv.org
… implementation is language-specific. For language pairs where one or both languages have a substantial amount of implicit discourse relations, a discourse parser would be needed instead of cues. 3.1 Datasets We used French …

Developing the Bangla RST Discourse Treebank
D Das, M Stede – Proceedings of the Eleventh International Conference …, 2018 – aclweb.org
… Feng, VW and Hirst, G. (2014). A linear-time bottom- up discourse parser with constraints and post-editing … Hernault, H., Prendinger, H., duVerle, D., and Ishizuka, M. (2010). Hilda: A discourse parser using support vector machine classification …

Discourse lexicon induction for multiple languages and its use for gender profiling
B Verhoeven, W Daelemans – Digital Scholarship in the …, 2018 – academic.oup.com
… corpus. Using gender profiling as an application, we evaluate our approach by comparing it with an approach using features from a knowledge-based lexicon and with an Rhetorical structure theory (RST) discourse parser. Our …

A dependency perspective on rst discourse parsing and evaluation
M Morey, P Muller, N Asher – Computational Linguistics, 2018 – MIT Press
Create a new account. Email. Returning user. Can’t sign in? Forgot your password? Enter your email address below and we will send you the reset instructions. Email. Cancel. If the address matches an existing account you will …

Primary and secondary discourse connectives: definitions and lexicons
L Danlos, K Rysova, M Rysova, M Stede – 2018 – halshs.archives-ouvertes.fr
Page 1. HAL Id: halshs-02002613 https://halshs.archives-ouvertes.fr/halshs-02002613 Submitted on 15 Mar 2019 HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not …

Building dialogue structure from discourse tree of a question
B Galitsky – Workshops at the Thirty-Second AAAI Conference on …, 2018 – aaai.org
… The component, which enforces complement relation, combines Stanford NLP parsing, coreferences, entity extrac- tion, DT construction (discourse parser, Surdeanu et al 2013 and Joty et al 2016), VerbNet and Tree Kernel builder into one system …

Sense classification of shallow discourse relations with focused RNNs
G Weiss, M Bajec – PloS one, 2018 – journals.plos.org
… English datasets. https://doi.org/10.1371/journal.pone.0206057.t001. A couple of sense classifiers have been developed as standalone systems, while others were used as components of a shallow discourse parser. Table 2 …

Claimrank: Detecting check-worthy claims in arabic and english
I Jaradat, P Gencheva, A Barrón-Cedeño… – arXiv preprint arXiv …, 2018 – arxiv.org
… More- over, here we exclude some of the features, namely some debate-specific information (eg, speaker, system messages), in order to be able to process any free text, and also discourse parse features, as we do not have a discourse parser for Arabic …

A discourse-aware neural network-based text model for document-level text classification
K Lee, S Han, SH Myaeng – Journal of Information Science, 2018 – journals.sagepub.com
Capturing semantics scattered across entire text is one of the important issues for Natural Language Processing (NLP) tasks. It would be particularly critical w…

Discourse coherence: Concurrent explicit and implicit relations
H Rohde, A Johnson, N Schneider… – Proceedings of the 56th …, 2018 – aclweb.org
Page 1. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Long Papers), pages 2257–2267 Melbourne, Australia, July 15 – 20, 2018. c 2018 Association for Computational Linguistics 2257 …

A joint model of conversational discourse and latent topics on microblogs
J Li, Y Song, Z Wei, KF Wong – Computational Linguistics, 2018 – MIT Press
Create a new account. Email. Returning user. Can’t sign in? Forgot your password? Enter your email address below and we will send you the reset instructions. Email. Cancel. If the address matches an existing account you will …

Rhetorical structure and Alzheimer’s disease
M Abdalla, F Rudzicz, G Hirst – Aphasiology, 2018 – Taylor & Francis
… The HILDA discourse parser is a commonly used greedy tree-building strategy (Duverle & Prendinger, 2009; Hernault, Bollegala, & Ishizuka, 2010) … Methodology We use a fast, linear-time bottom-up discourse parser to extract RST relations, as described later …

Transition-based neural rst parsing with implicit syntax features
N Yu, M Zhang, G Fu – Proceedings of the 27th International Conference …, 2018 – aclweb.org
Page 1. Proceedings of the 27th International Conference on Computational Linguistics, pages 559–570 Santa Fe, New Mexico, USA, August 20-26, 2018. 559 Transition-based Neural RST Parsing with Implicit Syntax Features …

Exploring coherence in visual explanations
M Alikhani, M Stone – 2018 IEEE Conference on Multimedia …, 2018 – ieeexplore.ieee.org
… Discourse markers, such as “however” and “meanwhile” are used as shallow cues and a discourse parser exploits deeper less obvious relations. 5 Conclusion … [10] VW Feng and G. Hirst. A linear-time bottom-up discourse parser with constraints and post-editing …

Quantitative aspects of PDTB-style discourse relations across languages
K Sun, L Zhang – Journal of Quantitative Linguistics, 2018 – Taylor & Francis
Page 1. https://doi.org/10.1080/09296174.2017.1390934 © 2017 informa uK limited, trading as taylor & francis group Quantitative Aspects of PDTB-Style Discourse Relations across Languages Kun Suna,b and Lili Zhanga,c …

RST Discourse Parsing with Tree-Structured Neural Networks
L Zhang, C Sun, X Tan, F Kong – China Workshop on Machine Translation, 2018 – Springer
… While neural network models have been successfully implemented in many tasks, little neural network based RST-style discourse parser has been proposed up to now [13, 14, 15] … Recently, some studies have focused on building neural network based discourse parser …

Automatic Query-Focused Summary Generation System for Tourism Discourse Using Rhetorical Structure Theory: Cognitive and Multimodal Approach to Tourism …
CN Subalalitha, J Balaji – Innovative Perspectives on Tourism …, 2018 – igi-global.com
… The UNL and the RST based works discussed in this section have many shortfalls such as, they can find only coherent clauses or sentences, whereas the UNL-RST discourse parser is capable of identify- ing the coherent text units at many levels namely, clause, sentence …

Using a discourse bank and a lexicon for the automatic identification of discourse connectives
A Mendes, I del Río – … Conference on Computational Processing of the …, 2018 – Springer
… Longman, Harlow (1976)Google Scholar. 11. Lin, Z., Ng, HT, Kan, MY: A PDTB-styled end-to-end discourse parser. Nat. Lang. Eng … MIT Press, Cambridge (2000)zbMATHGoogle Scholar. 14. Maziero, E., Pardo, TA: CSTPARSER – a multi-document discourse parser …

RST-based Discourse Coherence Quality Analysis Model for Students’ English Essays
G Huang, M Tan, Z Sun, Y Zhou – MATEC Web of …, 2018 – matec-conferences.org
… Escarcega. Two Practical Rhetorical Structure Theory Parsers, (2015) 10. H. Hernault, H. Prendinger, DA Duverle. HILDA: A Discourse Parser Using Support Vector Machine Classification, 1(3), (2010) 11. VW Feng, G. Hirst. Text …

Discourse Modeling of Non-Native Spontaneous Speech Using the Rhetorical Structure Theory Framework
X Wang, B Gyawali, JV Bruno… – 2018 IEEE Spoken …, 2018 – ieeexplore.ieee.org
… 2009, pp. 81–84. [21] Hugo Hernault, Helmut Prendinger, David A. duVerle, and Mitsuru Ishizuka, “HILDA: A discourse parser us- ing support vector machine classification,” Dialogue & Discourse, vol. 1, no. 3, pp. 1–33, 2010. [22 …

Infrequent discourse relation identification using data programming
X Zeng – 2018 – open.library.ubc.ca
Search.

Constructing a Lexicon of Dutch Discourse Connectives
P Bourgonje, J Hoek, J Evers-Vermeul… – … Linguistics in the …, 2018 – clinjournal.org
… Thailand, pp. 79–86. http://mt-archive.info/MTS-2005-Koehn.pdf. Lin, Ziheng, Hwee Tou Ng, and Min-Yen Kan (2014), A PDTB-styled end-to-end discourse parser, Natural Language Engineering 20, pp. 151–184. Mann, William …

Joint Modeling of Structure Identification and Nuclearity Recognition in Macro Chinese Discourse Treebank
X Chu, F Jiang, Y Zhou, G Zhou, Q Zhu – Proceedings of the 27th …, 2018 – aclweb.org
… The HILDA discourse parser (Hernault et al., 2010) is the first attempt at document-level discourse parsing on RST-DT … Vanessa Wei Feng and Graeme Hirst. 2014. A linear-time bottom-up discourse parser with constraints and post- editing. In ACL (1), pages 511–521 …

Discourse in Multimedia: A Case Study in Information Extraction
M Sachan, KA Dubey, EH Hovy, TM Mitchell… – arXiv preprint arXiv …, 2018 – arxiv.org
Page 1. Discourse in Multimedia: A Case Study in Information Extraction Mrinmaya Sachan Machine Learning Department School of Computer Science Carnegie Mellon University Kumar Avinava Dubey Machine Learning Department …

On the role of syntactic dependencies and discourse relations for author and gender identification
J Soler-Company, L Wanner – Pattern Recognition Letters, 2018 – Elsevier
… To obtain dependency trees from which the syntactic features are then extracted, Bohnet and Nivre’s [4] statistical dependency parser is used. The discourse features are extracted from discourse structure trees obtained using Surdeanu et al.’s [37] discourse parser …

Recognizing Macro Chinese Discourse Structure on Label Degeneracy Combination Model
F Jiang, P Li, X Chu, Q Zhu, G Zhou – CCF International Conference on …, 2018 – Springer
… structures. PTL J. Descr. Poet. Theory Lit. 1, 547–568 (1976)Google Scholar. 3. Hernault, H., Prendinger, H., duVerle, DA, Ishizuka, M.: HILDA: a discourse parser using support vector machine classification. Dialogue Discourse …

Discovering anD assessing HeateD arguments at tHe Discourse LeveL
R Taylor – dialog-21.ru
… We combined Stanford NLP parsing, coreferences, entity extraction, DT con- struction (discourse parser, [Surdeanu et al., 2016] and [Joty et al., 2013]), VerbNet and Tree Kernel builder into one system available at https://github.com/bgalitsky/ relevance-based-on-parse-trees …

Attention for Implicit Discourse Relation Recognition
A Cianflone, L Kosseim – … of the Eleventh International Conference on …, 2018 – aclweb.org
… Rutherford, A. and Xue, N. (2016). Robust non-explicit neural discourse parser in english and chinese. In Pro- ceedings of the Twentieth Conference on Computational Natural Language Learning: Shared Task (CoNLL), pages 55–59, Berlin, Germany …

MCDTB: A Macro-level Chinese Discourse TreeBank
F Jiang, S Xu, X Chu, P Li, Q Zhu, G Zhou – Proceedings of the 27th …, 2018 – aclweb.org
… Vanessa Wei Feng and Graeme Hirst. 2014. A linear-time bottom-up discourse parser with constraints and post- editing. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (ACL 2014). Pages 511-521, Baltimore, USA, June …

Discourse and Lexicons: Lexemes, MWEs, Grammatical Constructions and Compositional Word Combinations to Signal Discourse Relations
L Danlos – 2018 – hal.archives-ouvertes.fr
… Ziheng Lin, Hwee Tou Ng, and Min-Yen Kan. 2014. A PDTB-styled end-to-end discourse parser. Natural Language Engineering, 20:151–184. Gyri Smrdal Losnegaard, Federico Sangati, Carla Parra Escartn, Agata Savary, Sascha Bargmann, and Johanna Monti. 2016 …

Introduction to the special issue on language in social media: Exploiting discourse and other contextual information
F Benamara, D Inkpen, M Taboada – Computational Linguistics, 2018 – MIT Press
Create a new account. Email. Returning user. Can’t sign in? Forgot your password? Enter your email address below and we will send you the reset instructions. Email. Cancel. If the address matches an existing account you will …

A Knowledge-Augmented Neural Network Model for Implicit Discourse Relation Classification
Y Kishimoto, Y Murawaki, S Kurohashi – Proceedings of the 27th …, 2018 – aclweb.org
… the recurrent neural network, it can easily be combined with other neural network models that are built on top of LSTMs. Another popular choice of network is convolutional neural networks (CNN). Wang and Lan (2016) proposed an end-to-end shallow discourse parser …

The Leeds Arabic Discourse Treebank: Guidelines for Annotating Discourse Connectives and Relations
A Alsaif, K Markert – Arabic Corpus Linguistics, 2018 – books.google.com
Page 82. 5 The Leeds Arabic Discourse Treebank: Guidelines for Annotating Discourse Connectives and Relations Amal Alsaif and Katja Markert 1. Introduction In the last two decades, advanced discourse studies have tended …

Causal Explanation Analysis on Social Media
Y Son, N Bayas, HA Schwartz – arXiv preprint arXiv:1809.01202, 2018 – arxiv.org
Page 1. Causal Explanation Analysis on Social Media Youngseo Son, Nipun Bayas, and H. Andrew Schwartz Stony Brook University Stony Brook, NY 1yson,nbayas,hasl@ cs.stonybrook.edu Abstract Understanding causal explanations …

NLP for Conversations: Sentiment, Summarization, and Group Dynamics
G Murray, G Carenini, S Joty – … of the 27th International Conference on …, 2018 – aclweb.org
… His work has primarily focused on developing discourse analysis tools (eg, discourse parser, coherence model, topic model, dialogue act recognizer), and exploiting these tools effectively in downstream NLP applications like machine translation, summarization, and sentiment …

Detecting the Central Units of Brazilian Portuguese argumentative answer texts
K Bengoetxea Kortazar, M Iruskieta Quintian… – 2018 – rua.ua.es
… automatic translation, paraphrasing and even evaluat- ing texts. To do such tasks, we need anno- tated corpora to develop and test an auto- matic discourse parser. Regarding Brazilian Portuguese, CST News Corpus (Aleixo …

Detecting the Central Units of Brazilian Portuguese argumentative answer texts
K Bengoetxea, M Iruskieta… – … del Lenguaje Natural, 2018 – journal.sepln.org
… automatic translation, paraphrasing and even evaluat- ing texts. To do such tasks, we need anno- tated corpora to develop and test an auto- matic discourse parser. Regarding Brazilian Portuguese, CST News Corpus (Aleixo …

Automatically labeled data generation for classification of reputation defence strategies
N Naderi, G Hirst – … of the Eleventh International Conference on …, 2018 – lrec-conf.org
… We extracted the sentiments using OpinionFinder (Wilson et al., 2005) and discourse relations using End-to-End PDTB- Styled Discourse Parser (Lin et al., 2014) … Lin, Z., Ng, HT, and Kan, M.-Y.(2014). A PDTB-styled end-to-end discourse parser …

Syntax and Semantics of Italian Poetry in the First Half of the 20th Century
R Delmonte – arXiv preprint arXiv:1802.03712, 2018 – arxiv.org
Page 1. Syntax and Semantics of Italian Poetry in the First Half of the 20th Century Rodolfo Delmonte delmont@unive.it Dipartimento Studi Linguistici e Culturali Comparati, Università Ca Foscari, 30121 Venezia Keywords: Italian …

ChangeMyView Through Concessions: Do Concessions Increase Persuasion?
E Musi, D Ghosh, S Muresan – arXiv preprint arXiv:1806.03223, 2018 – arxiv.org
… Page 10. MUSI, GHOSH AND MURESAN with an off-the-shelf state-of-the art discourse parser trained on Penn Discourse Treebank that aims to classify the type of discourse connectives, not their class (Biran and McKeown, 2015). 6.1 Feature Description …

Message Validation Pipeline for Agents of the Internet of Everything
B Galitsky – 2018 AAAI Spring Symposium Series, 2018 – aaai.org
… We combined Stanford NLP parsing, coreferences, entity extraction, DT construction (discourse parser, Surdeanu et al., 2016 and Joty et al., 2016), VerbNet and Tree Kernel builder into one system available at https://github.com/bgalitsky/relevance-based-on-parse-trees …

On the Patent Claim Eligibility Prediction Using Text Mining Techniques
CY Lai, SY Hwang, CP Wei – 2018 – aisel.aisnet.org
… Based on Feng et al. [37], this research provides detailed RST-style discourse parser written in python on their website. We can implement this software after setting up all requirements. However, we still need to modify it to fit our environment …

Annotating Attribution Relations in Arabic
A Alsaif, T Alyahya, M Alotaibi, H Almuzaini… – Proceedings of the …, 2018 – aclweb.org
… CDT takes advantage of both RST and PDTB, and well adapts to the special characteristics of Chinese discourse relation including attribution. Later in (Kong and Zhou 2017), a CDT-styled end-to-end Chinese discourse parser was developed …

Topic–Focus Articulation: A Third Pillar of Automatic Evaluation of Text Coherence
M Novák, J Mírovský, K Rysová, M Rysová – … International Conference on …, 2018 – Springer
… focus on. Lin et al. [10] use a discourse parser that automatically annotates a text with discourse relations in the PDTB style, ie a framework similar to our approach that captures local coherence of the text. Their system further …

Sentic Patterns: Sentiment Data Flow Analysis by Means of Dynamic Linguistic Patterns
S Poria, A Hussain, E Cambria – Multimodal Sentiment Analysis, 2018 – Springer
In this chapter, we introduce a novel paradigm to concept-level sentiment analysis that merges linguistics, common-sense computing, and machine learning for improving the accuracy of tasks such as…

RST Signalling Corpus: A corpus of signals of coherence relations
D Das, M Taboada – Language Resources and Evaluation, 2018 – Springer
We present the RST Signalling Corpus (Das et al. in RST signalling corpus, LDC2015T10. https://catalog.ldc.upenn.edu/LDC2015T10, 2015), a corpus annotated for signals of coherence relations. The…

Opinion Spam Detection: A Review of the Literature
N Bensouda, S El Fkihi, R Faizi – Proceedings of the International …, 2018 – dl.acm.org
… Compared to the truthful ones, liars showed lower cognitive complexity, used fewer self references and more negative emotion words. Changge et al. [9] used two kinds of linguistic features: the first is based on a shallow discourse parser that is used to indicate discourse explicit …

Argumentative Link Prediction using Residual Networks and Multi-Objective Learning
A Galassi, M Lippi, P Torroni – Proceedings of the 5th Workshop on …, 2018 – aclweb.org
Page 1. Proceedings of the 5th Workshop on Argument Mining, pages 1–10 Brussels, Belgium, November 1, 2018. c 2018 Association for Computational Linguistics 1 Argumentative Link Prediction using Residual Networks and Multi-Objective Learning …

Multiple instance learning networks for fine-grained sentiment analysis
S Angelidis, M Lapata – Transactions of the Association for Computational …, 2018 – MIT Press
… Although definitions for EDUs vary in the literature, we follow standard practice and take the elementary units of discourse to be clauses (Carlson et al., 2003). We employ a state-of-the-art discourse parser (Feng and Hirst, 2012) to identify them …

Reading Comprehension with Graph-based Temporal-Casual Reasoning
Y Sun, G Cheng, Y Qu – … of the 27th International Conference on …, 2018 – aclweb.org
… Ziheng Lin, Hwee Tou Ng, and Min-Yen Kan. 2014. A pdtb-styled end-to-end discourse parser. Natural Language Engineering, 20(2):151–184. Christopher Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven Bethard, and David McClosky. 2014 …

Abstractive summarization: an overview of the state of the art
S Gupta, SK Gupta – Expert Systems with Applications, 2018 – Elsevier
Skip to main content …

Cross-Scenario Inference Based Event-Event Relation Detection
Y Hong, J Zhang, R Song, J Yao – CCF International Conference on …, 2018 – Springer
… relations. J. Artif. Intell. Res. (JAIR) 27, 85–117 (2006)CrossRefGoogle Scholar. 13. Lin, Z., Ng, HT, Kan, MY: A PDTB-styled end-to-end discourse parser. Nat. Lang. Eng. 20(02), 151–184 (2014)CrossRefGoogle Scholar. 14 …

Aspect Sentiment Classification with both Word-level and Clause-level Attention Networks.
J Wang, J Li, S Li, Y Kang, M Zhang, L Si, G Zhou – IJCAI, 2018 – ijcai.org
… the precision/recall scores of all categories. 2The word embedding resource is released at https://github.com/jjwangnlp/PTE2ASC 3http://alt.qcri.org/tools/discourse-parser/ Model Restaurant (Macro-F1) Laptop (Macro-F1) Majority …

A Broad Range, Purposeful, Textual Inference
D Roth – 2018 – apps.dtic.mil
… NAACL’15, Samdani et al. ICML’14; Chang et al. EMNLP’13]. b. We have developed a state-of-the-art discourse parser that identifies and classifies implicit and explicit discourse markers, within and across sentences. [Peng et al. CoNLL’17, Peng & Roth ACL’16, Song et al …

Characterization of temporal complementarity: fundamentals for multi-document summarization
JW da Cruz Souza, A Di Felippo – Alfa: Revista de Linguistica, 2018 – search.proquest.com
… Maziero (2012) and Maziero, Jorge and Pardo (2014) developed the multi-document discourse parser called CSTParser, which applies the most popular set of similarity features to detect a CST relation between two sentences: (i) difference in number of words between the …

Big data and causality
H Hassani, X Huang, M Ghodsi – Annals of Data Science, 2018 – Springer
Causality analysis continues to remain one of the fundamental research questions and the ultimate objective for a tremendous amount of scientific studies. In line with the rapid progress of science…

Two authors walk into a bar: studies in author profiling
B Verhoeven – 2018 – repository.uantwerpen.be
… translation techniques. Using gender profiling as an application, we evaluate our approach by comparing it with an approach using features from a knowledge-based lexicon and with an RST discourse parser. Our experiments …

Textual Analogy Parsing: What’s Shared and What’s Compared among Analogous Facts
M Lamm, AT Chaganty, CD Manning… – arXiv preprint arXiv …, 2018 – arxiv.org
… Given (E1) above, a shallow discourse parser would classify the relation of con- trast between C1 and C2—indicating that some salient differences exist in the meanings of the jux- taposed phrases—but without identifying the na- arXiv:1809.02700v1 [cs.CL] 7 Sep 2018 Page 2 …

Coherence in Machine Translation
KM Sim Smith – 2018 – etheses.whiterose.ac.uk
Page 1. Coherence in Machine Translation Karin Sim Smith Department of Computer Science University of Sheffield A thesis submitted for the degree of Doctor of Philosophy August 2017 Page 2. Acknowledgements Firstly, I …

Causality patterns for detecting adverse drug reactions from social media: text mining approach
D Bollegala, S Maskell, R Sloane… – JMIR public health …, 2018 – publichealth.jmir.org
A multidisciplinary journal that focuses on public health and technology, public health informatics, mass media campaigns, surveillance, and innovation in public health practice and research. Also dedicated to rapid open data sharing during epidemics.

Multilayer Corpus Studies
A Zeldes – 2018 – content.taylorfrancis.com
Page 1. Page 2. Multilayer Corpus Studies This volume explores the opportunities afforded by the construction and evaluation of multilayer corpora, an emerging methodology within corpus linguistics that brings together multiple …

Plant discrimination by Support Vector Machine classifier based on spectral reflectance
S Akbarzadeh, A Paap, S Ahderom, B Apopei… – … and electronics in …, 2018 – Elsevier
Skip to main content …

Detecting dementia from written and spoken language
V Masrani – 2018 – open.library.ubc.ca
Learning, knowledge, research, insight: welcome to the world of UBC Library, the second-largest academic research library in Canada.

Context-aware Argument Mining and Its Applications in Education
H Nguyen – 2018 – d-scholarship.pitt.edu
Page 1. CONTEXT-AWARE ARGUMENT MINING AND ITS APPLICATIONS IN EDUCATION by Huy V. Nguyen Bachelor of Engineering Hanoi University of Sciences and Technologies, Vietnam 2007 Submitted to the Graduate Faculty of …

Facilitating Document Reading by Linking Text and Tables
DH Kim, E Hoque, J Kim, M Agrawala – The 31st Annual ACM …, 2018 – dl.acm.org
Page 1. Facilitating Document Reading by Linking Text and Tables Dae Hyun Kim1, Enamul Hoque1, Juho Kim2, and Maneesh Agrawala1 Stanford University Stanford, CA, USA {dhkim16, enamul, maneesh}@cs.stanford.edu …

Semantics-Driven Aspect-Based Sentiment Analysis
KKIM Schouten – 2018 – repub.eur.nl
Page 1. Semantics-Driven Aspect-Based Sentiment Analysis Page 2. Page 3. Semantics-Driven Aspect-Based Sentiment Analysis Semantiek-gedreven Aspect-gebaseerde Sentiment Analyse Thesis to obtain the degree of Doctor …

Multimodal Sentiment Analysis
S Poria, A Hussain, E Cambria – 2018 – Springer
Page 1. Socio-Affective Computing 8 Soujanya Poria · Amir Hussain Erik Cambria Multimodal Sentiment Analysis Page 2. Socio-Affective Computing Volume 8 Series Editors Amir Hussain, University of Stirling, Stirling, UK Erik …

Learning to represent, categorise and rank in community question answering
D Bogdanova – 2018 – doras.dcu.ie
Page 1. Learning to Represent, Categorise and Rank in Community Question Answering Daria Bogdanova Diploma in Applied Mathematics and Computer Science A dissertation submitted in fulfilment of the requirements for the award of Doctor of Philosophy (Ph.D.) to the …

Turing tests in Natural Language Processing and Information Retrieval
E SANJUAN – dev.termwatch.es
Page 1. ERIC SANJUAN Turing tests in Natural Language Processing and Information Retrieval Contributions to the theory, development and evaluation of textual information processing systems for decision support HDR présentée …

Algorithmic Generation and Mobile Distribution of Phonetic, Orthographic, and Inference-Based Literacy Exercises for Adult Learners
JR Hill – 2018 – letr.seas.gwu.edu
Page 1. Algorithmic Generation and Mobile Distribution of Phonetic, Orthographic, and Inference-Based Literacy Exercises for Adult Learners by Jennifer Rose Hill BS in Computer Science, May 2012, Hood College A Dissertation submitted to …

Automatic recognition of argumentation structure in short monological texts
A Peldszus – 2018 – publishup.uni-potsdam.de
Page 1. Automatic recognition of argumentation structure in short monological texts Andreas Peldszus Doctoral Thesis submitted to the Faculty of Human Sciences, Department Linguistics at the University of Potsdam in partial …

Anaphora with non-nominal antecedents in computational linguistics: A survey
V Kolhatkar, A Roussel, S Dipper… – Computational …, 2018 – MIT Press
Create a new account. Email. Returning user. Can’t sign in? Forgot your password? Enter your email address below and we will send you the reset instructions. Email. Cancel. If the address matches an existing account you will …

Understanding stories via event sequence modeling
H Peng – 2018 – ideals.illinois.edu
Page 1. c 2018 Haoruo Peng Page 2. UNDERSTANDING STORIES VIA EVENT SEQUENCE MODELING BY HAORUO PENG DISSERTATION Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy …

Knowledge-intensive, high-performance relation extraction
S Krause – 2018 – depositonce.tu-berlin.de
Page 1. Knowledge-Intensive, High-Performance Relation Extraction vorgelegt von Dipl.-Inf. Sebastian Krause geb. in Halle (Saale) von der Fakultät IV – Elektrotechnik und Informatik der Technischen Universität Berlin zur Erlangung des akademischen Grades …

Literature Survey and Datasets
S Poria, A Hussain, E Cambria – Multimodal Sentiment Analysis, 2018 – Springer
… sentiments in tweets. In [280], a discourse parser combined information of sentential syntax, semantics and lexical information to build a tree that served as a representation of the discourse structure. Wolf et al. [395] presented …

Summarization of scientific paper through reinforcement ranking on Semantic Link Network
X Sun, H Zhuge – IEEE Access, 2018 – ieeexplore.ieee.org
Page 1. 2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/ redistribution requires IEEE permission. See http://www.ieee.org …

Question classification based on MAC-LSTM
B Yu, Q Xu, P Zhang – … on Data Science in Cyberspace (DSC), 2018 – ieeexplore.ieee.org
Page 1. Question Classification Based on MAC-LSTM Bengong Yu School of Management Hefei University of Technology Hefei, Anhui, China; Email: 188267797@qq.com Qingtang Xu School of Management Hefei University …

Deep interactive text prediction and quality estimation in translation interfaces
CM Hokamp – 2018 – doras.dcu.ie
Page 1. Deep Interactive Text Prediction and Quality Estimation in Translation Interfaces Christopher M. Hokamp BA, MA A dissertation submitted in fulfilment of the requirements for the award of Doctor of Philosophy (Ph.D.) to the Dublin City University School of Computing …