Discourse Parser 2015


Notes:

Shallow discourse parsing is the task of parsing a piece of text into a set of discourse relations between two adjacent or non-adjacent discourse units.  It is shallow… because the relations in a text are not connected to one another to form a connected structure in the form of a tree or graph.

  • Automatic discourse segmentation
  • Coherence relations
  • Discourse parsing
  • Discourse relation classification
  • Discourse representation
  • Discourse segmentation
  • Discourse segmenter
  • Discourse structures
  • Discourse units
  • Shallow discourse parsing

Resources:

Wikipedia:

References:

See also:

Discourse Analysis & Dialog Systems 2015Discourse Parser 2013Discourse Parser 2014 | Treebank & Dialog Systems 2014


A refined end-to-end discourse parser J Wang, M Lan – CoNLL 2015, 2015 – aclweb.org Abstract The CoNLL-2015 shared task focuses on shallow discourse parsing, which takes a piece of newswire text as input and returns the discourse relations in a PDTB style. In this paper, we describe our discourse parser that participated in the shared task. We use 9 … Cited by 18 Related articles All 7 versions

Two practical rhetorical structure theory parsers M Surdeanu, T Hicks… – Proceedings of the …, 2015 – anthology.aclweb.org … Tucson, AZ, USA {msurdeanu, hickst, marcov}@ email. arizona. edu Abstract We describe the design, development, and API for two discourse parsers for Rhetori- cal Structure Theory. The two parsers use the same underlying … Cited by 9 Related articles All 12 versions

The dcu discourse parser for connective, argument identification and explicit sense classification L Wang, C Hokamp, T Okita, X Zhang, Q Liu – CoNLL 2015, 2015 – aclweb.org Abstract This paper describes our submission to the CoNLL-2015 shared task on discourse parsing. We factor the pipeline into subcomponents which are then used to form the final sequential architecture. Focusing on achieving good performance when inferring explicit … Cited by 4 Related articles All 7 versions

The conll-2015 shared task on shallow discourse parsing N Xue, HT Ng, S Pradhan, RPOC Bryant… – Proceedings of …, 2015 – aclweb.org … 4.3 Evaluation metrics and scorer A shallow discourse parser is evaluated based on the end-to-end F1 score on a per-discourse relation basis. The input to the system consists of docu- ments with gold-standard word tokens along with their automatic parses. … Cited by 34 Related articles All 8 versions

Spectral semi-supervised discourse relation classification R Fisher, R Simmons – Volume 2: Short Papers, 2015 – anthology.aclweb.org … In addition to requiring a fully supervised train- ing set, most existing discourse parsers use non- spectral optimization that is often slow and inex- act. … Vanessa Wei Feng and Graeme Hirst. 2014. A linear- time bottom-up discourse parser with constraints and post-editing. … Cited by 5 Related articles All 9 versions

Improving a pipeline architecture for shallow discourse parsing Y Song, H Peng, P Kordjamshidi, M Sammons, D Roth – 2015 – repository.ust.hk … Issue Date, 2015. Source, CoNLL shared task, 2015. Summary, We present a system that implements an end-to-end discourse parser. The system uses a pipeline architecture with seven stages: preprocessing, recognizing explicit … Cited by 2

Summarization based on task-oriented discourse parsing X Wang, Y Yoshida, T Hirao, K Sudoh… – … /ACM Transactions on …, 2015 – ieeexplore.ieee.org … Existing studies usually adopt existing discourse parsers directly with no modifica- tions, hence cannot take full advantage of discourse parsing. … In contrast to previous work, we train a discourse parser specially for summarization by using summaries. … Cited by 3 Related articles All 3 versions

Better document-level sentiment analysis from rst discourse parsing P Bhatia, Y Ji, J Eisenstein – Proceedings of the Conference on Empirical …, 2015 – aclweb.org … 2212 Page 2. can be used in combination with an “off the shelf” discourse parser. … Wang et al. (2012) address sentiment analysis in Chinese. Lacking a discourse parser, they focus on explicit connectives, using a strategy that is re- lated to our discourse depth reweighting. … Cited by 10 Related articles All 13 versions

One vector is not enough: Entity-augmented distributed semantics for discourse relations Y Ji, J Eisenstein – Transactions of the Association for …, 2015 – tacl2013.cs.columbia.edu Page 1. One Vector is Not Enough: Entity-Augmented Distributed Semantics for Discourse Relations Yangfeng Ji and Jacob Eisenstein School of Interactive Computing Georgia Institute of Technology {jiyfeng, jacobe}@gatech.edu Abstract … Cited by 19 Related articles All 11 versions

Improving the inference of implicit discourse relations via classifying explicit discourse connectives A Rutherford, N Xue – Proceedings of the NAACL-HLT, 2015 – cs.brandeis.edu … Discourse relation classification is an im- portant component for automatic discourse parsing and natural language understanding. The performance bottleneck of a discourse parser comes from implicit discourse rela- tions, whose discourse connectives are not overtly present. … Cited by 10 Related articles All 7 versions

Comparing word representations for implicit discourse relation classification C Braud, P Denis – Empirical Methods in Natural Language Processing ( …, 2015 – hal.inria.fr … hand-crafted features. 1 Introduction Identifying discourse relations is an important task, either to build a discourse parser or to help other NLP systems such as text summarization or question-answering. This task is relatively … Cited by 13 Related articles All 16 versions

Building a Language-Independent Discourse Parser using Universal Networking Language SC Navaneethakrishnan… – Computational …, 2015 – Wiley Online Library Abstract Discourse parsing has become an inevitable task to process information in the natural language processing arena. Parsing complex discourse structures beyond the sentence level is a significant challenge. This article proposes a discourse parser that … Cited by 2 Related articles All 2 versions

Mapping different rhetorical relation annotations: A proposal F Benamara, M Taboada – … of the 4th Joint Conference on …, 2015 – pdfs.semanticscholar.org … resources have contributed to a number of applications, most notably discourse segmentation into elementary discourse units, iden- tification of explicit and implicit relations for the purpose of discourse parsing, and development of end-to-end discourse parsers (Hernault et al … Cited by 3 Related articles All 4 versions

On the usage of discourse relations across texts with different readability levels E Davoodi – Canadian Conference on Artificial Intelligence, 2015 – Springer … Automatic tools called discourse parsers have been designed in order to iden- tify discourse relations and their arguments automatically. Different discourse parsers use different approaches to segment the text, identify the arguments of a relation and label the relations. … Cited by 1 Related articles

Establishing criteria for RST-based discourse segmentation and annotation for texts in Basque M Iruskieta, A Diaz de Ilarraza… – Corpus Linguistics and …, 2015 – degruyter.com Page 1. DOI 10.1515/cllt-2013-0008 Mikel Iruskieta, Arantza Diaz de Ilarraza and Mikel Lersundi Establishing criteria for RST-based discourse segmentation and annotation for texts in Basque1 Abstract: This article presents … Cited by 6 Related articles All 3 versions

Hybrid approach to PDTB-styled discourse parsing for CoNLL-2015 Y Yoshida, K Hayashi, T Hirao, M Nagata – CoNLL 2015, 2015 – aclweb.org … ntt. co. jp Abstract This paper describes our end-to-end PDTB-styled discourse parser for the CoNLL-2015 shared task. … 6 Conclusion In this paper, we presented our PDTB-styled full discourse parser for CoNLL-2015. We extended the work by (Ziheng et al., 2014). … Cited by 3 Related articles All 7 versions

Spinning straw into gold: Using free text to train monolingual alignment models for non-factoid question answering R Sharp, P Jansen, M Surdeanu, P Clark – … of the Conference of the North …, 2015 – aclweb.org … We show that the RST-based method captures within and across-sentence alignments and performs bet- ter than the sequential model, but the sequential model is an acceptable approximation when a discourse parser is not available. … Cited by 4 Related articles All 11 versions

Exploiting Debate Portals for Semi-Supervised Argumentation Mining in User-Generated Web Discourse I Habernal, I Gurevych – Proceedings of the 2015 Conference on Empirical …, 2015 – Citeseer … Furthermore, we include features result- ing from a PTDB-style discourse parser (Li et al., 2012), such as the type of discourse relation (ex- plicit, implicit), the presence of discourse connec- tives, and attributions. 4.2 Unsupervised features … Cited by 13 Related articles All 10 versions

Semi-supervised never-ending learning in rhetorical relation identification EG Maziero, G Hirst, TAS Pardo – International Conference on …, 2015 – producao.usp.br … English were adapted to this language. Portuguese is a lan- guage with insufficient annotated data to obtain a good discourse parser, but has all the tools to adapt some English discourse parsers. A framework of semi-supervised … Cited by 3 Related articles All 21 versions

Discourse-sensitive Automatic Identification of Generic Expressions A Friedrich, M Pinkal – … of the 53rd Annual Meeting of the …, 2015 – anthology.aclweb.org … We use the discourse parser SPADE (Soricut and Marcu, 2003) to automatically segment the first 70 sentences of each article into clauses. Each clause is manually annotated with the following information (for more details on the annotation scheme, see (Friedrich et al., 2015)): … Cited by 5 Related articles All 7 versions

RST-style discourse parsing and its applications in discourse analysis VW Feng – 2015 – cs.toronto.edu … tection of deception. In particular, I propose to use a set of application-neutral features, which are derived from the discourse relations extracted by my discourse parser, and compare the … 53 5 A Linear-Time Bottom-up Discourse Parser with Constraints and Post-Editing 55 … Cited by 7 Related articles All 17 versions

Disambiguating discourse connectives for statistical machine translation T Meyer, N Hajlaoui… – IEEE/ACM Transactions …, 2015 – ieeexplore.ieee.org … discourse connective labeling task has strong relations with discourse parsing. Therefore, we use the output of the discourse parser by Soricut and Marcu [32] as features for our labeler. (Of course, if such a parser was fully accurate … Cited by 5 Related articles All 6 versions

Using rhetorical structure in sentiment analysis A Hogenboom, F Frasincar, F De Jong… – Communications of the …, 2015 – dl.acm.org … 24–28). ACM Press, New York, 2011, 1061–1070. 9. Hernault, H., Prendinger, H., duVerle, D., and Ishizuka, M. HILDA: A discourse parser using support vector machine classification. Dialogue and Discourse 1, 3 (Dec. 2010), 1–33. 10. … Cited by 10 Related articles All 9 versions

An Approach for Intention Mining of Complex Comparative Opinion Why Type Questions Asked on Product Review Sites A Mishra, SK Jain – International Conference on Intelligent Text Processing …, 2015 – Springer … The algorithm is as follows: 1. The question is parsed through A PDTB-Styled End-to-End Discourse Parser developed by Ziheng Lin et al. [9]. We first analyze inter-sentential discourse structure then intra-sentential discourse structure of the question. … Cited by 1 Related articles

Mapping Different Rhetorical Relation Annotations: A Proposal FB Zitoune, M Taboada – Lexical and Computational …, 2015 – anthology.aclweb.org … resources have contributed to a number of applications, most notably discourse segmentation into elementary discourse units, iden- tification of explicit and implicit relations for the purpose of discourse parsing, and development of end-to-end discourse parsers (Hernault et al … Cited by 1 Related articles All 7 versions

Discourse and documentlevel information for evaluating language output tasks C Scarton – The 2015 Conference of the North American Chapter of …, 2015 – aclweb.org … In fact, topic modelling approaches have al- ready been used to improve MT and also for QE at sentence level. Their advantage is that they are fast, language independent and do not require robust re- sources (such as discourse parsers). … Cited by 2 Related articles All 7 versions

Euseduseg: A dependency-based edu segmentation for basque M Iruskieta, B Zapirain – Procesamiento del Lenguaje Natural, 2015 – journal.sepln.org … 1 Introduction An obligatory first step in the annotation of any discourse parser is to identify the dis- course units. … c) DiZer format (Pardo, Nunes, and Rino, 2004) to use in an automatic discourse parser. System architecture is presented in Fig- ure 4. 4.3 Evaluation measures … Cited by 3 Related articles All 6 versions

Annotation and classification of argumentative writing revisions F Zhang, D Litman – … of the Tenth Workshop on Innovative …, 2015 – pdfs.semanticscholar.org … clauses after. A potential benefit is that clauses are often the ba- sic units of discourse structures, so extracting clause revisions will allow the direct use of discourse parser outputs (Feng and Hirst, 2014; Lin et al., 2014). However … Cited by 4 Related articles All 11 versions

A minimalist approach to shallow discourse parsing and implicit relation recognition C Chiarcos, N Schenk – CoNLL 2015, 2015 – aclweb.org … Reason—one out of roughly 20 three-level senses marking the relation sense between any given argument pair in the PDTB. We participate in the CoNLL 2015 Shared Task (Xue et al., 2015) with a minimalist end-to-end shallow discourse parser developed from scratch. … Cited by 1 Related articles All 7 versions

A Model for the Recognition of Discourse Relations M Balint, S Trausan-Matu – 2015 20th International Conference …, 2015 – ieeexplore.ieee.org … significant results. In 2003, Soricut and Marcu publish the details of SPADE [17], a discourse parser limited to sentence level analysis. SPADE … document level. In 2010, the Hilda [6] discourse parser is made publicly available. Hilda … Cited by 1 Related articles

Pdtb discourse parsing as a tagging task: The two taggers approach O Biran, K McKeown – 16th Annual Meeting of the Special Interest Group …, 2015 – aclweb.org … David A. duVerle and Helmut Prendinger. 2009. A novel discourse parser based on support vector ma- chine classification. … The MIT Press. Vanessa Wei Feng and Graeme Hirst. 2014. A Linear- Time Bottom-Up Discourse Parser with Constraints and Post-Editing. … Cited by 2 Related articles All 10 versions

Discourse analysis of arabic documents and application to automatic summarization I Keskes – 2015 – thesesups.ups-tlse.fr … general. The usefulness of discourse in NLP applications mainly depends on the availability of powerful discourse parsers. … Page 5. Abstract II • An automatic discourse parser where we investigate both automatic segmentation of Arabic … Cited by 2 Related articles All 2 versions

Summarizing a document by trimming the discourse tree T Hirao, M Nishino, Y Yoshida, J Suzuki… – … On Audio, Speech, …, 2015 – ieeexplore.ieee.org Page 1. 2329-9290 (c) 2015 IEEE. Personal use is permitted, but republication/ redistribution requires IEEE permission. See http://www.ieee.org/ publications_standards/publications/rights/index.html for more information. This … Cited by 1 Related articles All 2 versions

Discourse Segmentation of German Texts U Sidarenka, A Peldszus, M Stede – Document-level school lesson quality …, 2015 – jlcl.org … For RST and SDRT (and similar approaches), any discourse parser relies on a segmentation of the text into EDUs, which in all present frameworks amounts to a sequence of non-overlapping units that completely covers the text. … Cited by 1 Related articles All 2 versions

Scientific Article Summarization Using Citation-Context and Article’s Discourse Structure A Cohan, N Goharian – … in Natural Language Processing (EMNLP ’15), 2015 – aclweb.org … Summarization based on rhetorical structure is better suited for shorter documents and is highly dependent on the quality of the discourse parser that is used. Training the discourse parser requires large amount of training data in the RST framework. … Cited by 2 Related articles All 10 versions

Truth and deception at the rhetorical structure level VL Rubin, T Lukoianova – Journal of the Association for …, 2015 – Wiley Online Library … Recent efforts in developing a fully automated RST-based discourse parser confirm that it is feasible to extend traditional sentence-level discourse parsing to text-level parsing. The first fully implemented text-level discourse … Cited by 5 Related articles All 6 versions

Discourse element identification in student essays based on global and local cohesion W Song, R Fu, L Liu, T Liu – Proceedings of the 2015 Conference on …, 2015 – aclweb.org … In addition, its ease of implementation is also attrac- tive. Other options for representing text structure such as full-text discourse parsers (Marcu, 2000) may be not available or don’t have satisfied per- formance, especially for non-English languages. … Cited by 1 Related articles All 9 versions

The Chinese Discourse Parser J JI, M ZHANG, B QIN, T LIU – Journal of Jiangxi Normal University ( …, 2015 – en.cnki.com.cn Discourse relation analysis usually focuses on identifying elementary discourse units (EDUs) and recognizing the discourse relation between EDUs. Previous work on this topic primarily focused on English. To the best of our knowledge, there is no publicly available … Related articles

The CLaC Discourse Parser at CoNLL-2015 M Laali, E Davoodi, L Kosseim – CoNLL 2015, 2015 – aclweb.org Abstract This paper describes our submission (kosseim15) to the CoNLL-2015 shared task on shallow discourse parsing. We used the UIMA framework to develop our parser and used ClearTK to add machine learning functionality to the UIMA framework. Overall, our parser … Cited by 1 Related articles All 7 versions

Building a High Performance End-to-End Explicit Discourse Parser for Practical Application J Wang, M Lan – … Conference on Knowledge Science, Engineering and …, 2015 – Springer Abstract To build practical end-to-end discourse parser, labeling arguments to discourse is the bottleneck to improve performance of whole parser. In consideration of the difference between syntactic and discourse arguments of connectives and the difference between … Related articles All 2 versions

The UniTN Discourse Parser in CoNLL 2015 Shared Task: Token-level Sequence Labeling with Argument-specific Models EASGR Ali, O Bayer – CoNLL 2015, 2015 – aclweb.org Abstract Penn Discourse Treebank style discourse parsing is a composite task of identifying discourse relations (explicit or nonexplicit), their connective and argument spans, and assigning a sense to these relations from the hierarchy of senses. In this paper we … Cited by 1 Related articles All 10 versions

Semtrex a framework for building Semantic structures CN Subalalitha – 2015 – ir.inflibnet.ac.in … 75 3.4 SUMMARY 79 4 LANGUAGE INDEPENDENT UNL-RST DISCOURSE PARSER 80 4.1 LANGUAGE INDEPENDENT UNL- RST … 85 4.1.2 Evaluation of the UNL-RST clause/sentence Discourse Parser 88 4.2 UNL-RSTparagraphe/document DISCOURSE PARSER 91 … All 2 versions

Recognizing nuclearity between Chinese Discourse units X Chu, Z Wang, Q Zhu, G Zhou – … International Conference on …, 2015 – ieeexplore.ieee.org … RELATED WORK Since Marcu flrst developed a rule-based discourse parser [I], several algorithms for discourse parsing have been proposed, both statistical and rule-based, especially since the release of English discourse corpus such as Penn Discourse Treebank (PDTB) [2 … Related articles

A Shallow Discourse Parsing System Based On Maximum Entropy Model J Sun, P Li, W Xu, Y Yan – CoNLL 2015, 2015 – aclweb.org … Lin (Lin et al., 2014) de- signed an end-to-end discourse parser with the PDTB including the explicit, implicit sense and the argument spans identification. … 2009. A novel discourse parser based on support vector ma- chine classification. … Related articles All 7 versions

The SoNLP-DP System in the CoNLL-2015 shared Task FKSLG Zhou – CoNLL 2015, 2015 – anthology.aclweb.org … Our System classifies discourse re- lations into explicit and non-explicit re- lations and uses a pipeline platform to conduct every subtask to form an end-to- end shallow discourse parser in the Penn Discourse Treebank (PDTB). … Cited by 3 Related articles All 8 versions

Improving a Pipeline Architecture for Shallow Discourse Parsing YSHPP Kordjamshidi, MSD Roth – CoNLL 2015, 2015 – aclweb.org … Illinois at Urbana-Champaign {yqsong, hpeng7, kordjam, mssammon, danr}@ illinois. edu Abstract We present a system that implements an end-to-end discourse parser. The system uses a pipeline architecture with seven stages … Related articles All 10 versions

On the Influence of Text Complexity on Discourse-Level Choices E DAVOODI, L KOSSEIM – IJCLA, 2015 – gelbukh.com … bahripublications. com Page 26. called Discourse Markers (DM). According to [21], DMs constitute strong clues to detect explicit relations, hence discourse parsers have used them as valuable features in order to identify DRs automatically (eg [13, 26, 10, 16]). …

Sentiment Polarity Classification with Low-level Discourse-based Features EA Stepanov, G Riccardi – CLiC it, 2015 – iris.unito.it … Trento, TN, Italy 1evgeny. stepanov, giuseppe. riccardil@ unitn. it Abstract English. The poor state-of-the-art perfor- mances of discourse parsers prevent their application to downstream tasks. How- ever, discourse parsing sub … Related articles All 2 versions

Shallow Discourse Parsing with Syntactic and (a Few) Semantic Features S Mukherjee, A Tiwari, M Gupta, AK Singh – CoNLL 2015, 2015 – aclweb.org … of which is considerably harder. Previously, an end-to-end model by Lin et al.(2014) was developed which used only syn- tactic features from parse trees and improved the discourse parser performance. In our paper, we have … Related articles All 7 versions

Learning representations for text-level discourse parsing G Weiss – ACL-IJCNLP 2015, 2015 – aclweb.org … Ji and Eisenstein (Ji and Eisen- stein, 2014) implement a shift-reduce discourse parser on top of given RST-style discourse units to simultaneously learn parsing and a discourse- driven projection of features using support vector machines with gradient-based updates. Li et al. … Related articles All 8 versions

A Discourse Search Engine based on Rhetorical Structure Theory P Kuyten, D Bollegala, B Hollerit, H Prendinger… – … on Information Retrieval, 2015 – Springer … can be ambiguous with respect to the discourse relations they express [7]. It is inadequate to classify dis- course relations purely based on discourse markers, and discourse parsers that use more advanced NLP methods are required [5,6,9,10,12,19,22]. … Related articles All 7 versions

Chinese Discourse Segmentation Based on Punctuation Marks Y Li, H Feng, W Feng – International Journal of Signal Processing, Image …, 2015 – sersc.org … We bold the connective words for emphasis. The discourse parser tree of example (1) is shown in Figure 1: 1 2 … In our discourse parser trees, connectives can not only represent the discourse relation, but also represent the discourse hierarchical structure in the tree. … Related articles All 2 versions

Deceptive Opinion Spam Detection Using Deep Level Linguistic Features C Chen, H Zhao, Y Yang – National CCF Conference on Natural Language …, 2015 – Springer … The first type of features are derived from a shallow discourse parser trained on Penn Discourse Treebank (PDTB), which can capture inter-sentence information. The second type is based on the relationship between sentiment analysis and spam detection. … Related articles All 4 versions

Adaptation of discourse parsing models for the portuguese language EG Maziero, G Hirst, TAS Pardo – 2015 Brazilian Conference …, 2015 – ieeexplore.ieee.org … The first is that the task was only approached with the use of lexical patterns, and the second is that the available discourse parser was obtained through the analysis of a corpus of academic texts [6], being domain-specific. To treat a new text genre, new lexical Fig. … Related articles All 10 versions

Fast rhetorical structure theory discourse parsing M Heilman, K Sagae – arXiv preprint arXiv:1505.02425, 2015 – arxiv.org … 4 Discourse Parser Description In this section, we describe our RST parser. It borrows extensively from previous work, especially Sagae (2009).1 … Vanessa Wei Feng and Graeme Hirst. 2014. A linear- time bottom-up discourse parser with constraints and post-editing. … Related articles All 3 versions

A Quantitative Analysis of Discourse Phenomena in Machine Translation C Scarton, L Specia – Discours. Revue de linguistique, …, 2015 – discours.revues.org … them. 35EDU breaks were marked using the Discourse Segmenter module of the Discourse Parser developed by Joty et al. (2013). This … units. 36RST relations were extracted with the same discourse parser (Joty et al., 2013). This … Related articles All 3 versions

Differences over discourse structure differences: a reply to Urquhart and Urquhart JA Abrahamson, VL Rubin – Journal of Documentation, 2015 – emeraldinsight.com … Taboada, 2004; Bateman and Delin, 2006). There have been recent efforts to fully automate RST analysis based on marked linguistic features. The HILDA discourse parser was proposed by Hernault et al. (2010) as the first fully implemented text-level discourse parser. … Cited by 1 Related articles

EusEduSeg: A Dependency-Based EDU Segmentation for Basque M Iruskieta Quintian, B Zapirain – 2015 – rua.ua.es … 1 Introduction An obligatory first step in the annotation of any discourse parser is to identify the dis- course units. … c) DiZer format (Pardo, Nunes, and Rino, 2004) to use in an automatic discourse parser. System architecture is presented in Fig- ure 4. 4.3 Evaluation measures … Related articles

Discourse Planning with an N-gram Model of Relations O Biran, K McKeown – cs.columbia.edu … probabilities. The results are shown in Table 1. In the second experiment, we used a PDTB shallow discourse parser we developed (Biran and McKeown, 2015) to create a discourse-annotated version of the English Wikipedia. We … Related articles All 9 versions

Discourse parsing for multi-party chat dialogues SAEKN Asher, J Perret – Citeseer … Such approaches do not apply to our data, as most of the structure in our dialogues lies beyond the sentence level. As for document-level discourse parsers, Subba and Di Eugenio (2009) use a transition-based ap- proach, following the paradigm of Sagae (2009). … Cited by 1 Related articles All 9 versions

Sequential Annotation and Chunking of Chinese Discourse Structure F Yung, K Duh, Y Matsumoto – ACL-IJCNLP 2015, 2015 – aclweb.org … Ziheng Lin, Hwee Tou Ng,, and Min Yen Kan. 2010. A pdtb-styled end-to-end discourse parser. Techni- cal report, National University of Singapore. Ziheng Lin, Hwee Tou Ng, and Minyen Kan. 2011. Automatic evaluating text coherence using discourse relations. … Related articles All 11 versions

Crosslingual Annotation and Analysis of Implicit Discourse Connectives for Machine Translation F Yung, K Duh, Y Matsumoto – DISCOURSE IN MACHINE …, 2015 – cs.cmu.edu … in translation. We investigate how implicit (omitted) DCs in the source text impacts various machine translation (MT) systems, and whether a discourse parser is needed as a preprocessor to explicitate implicit DCs. Based on … Cited by 1 Related articles All 11 versions

Identification and Disambiguation of Lexical Cues of Rhetorical Relations across Different Text Genres T Khazaei, L Xiao, RE Mercer – Workshop on Linking Models of Lexical, …, 2015 – aclweb.org … score of 96.22%. Within a broader context of building an end-to- end discourse parser for PDTB, Lin et al.(Lin et al., 2014) built a cue classifier to identify whether a lexical item functions as a discourse cue or not. In addition to … Related articles All 10 versions

Exploring machine learning design options in discourse parsing W Liao – 2015 – open.library.ubc.ca Learning, knowledge, research, insight: welcome to the world of UBC Library, the second-largest academic research library in Canada. Related articles All 2 versions

USHEF and USAAR-USHEF Participation in the WMT15 Quality Estimation Shared Task C Scarton, L Tan, L Specia – EMNLP 2015, 2015 – aclweb.org … RP tags). Discourse con- nectives are automatically extracted by the parser of Pitler and Nenkova (2009). RST trees and EDUs are extracted by the discourse parser and discourse segmenter of Joty et al.(2013). 3 Experiments … Related articles All 12 versions

Weakly Supervised Learning of Dialogue Structure in MOOC Forum Threads R Fisher, R Simmons… – 2015 IEEE 14th …, 2015 – ieeexplore.ieee.org … platforms such as Coursera. Coupling these structured responses with a semi- supervised training framework allows us to train a discourse parser that does not require manually supplied training data. As with any discourse … Related articles

Labeling the Semantic Roles of Commas N Arivazhagan, C Christodoulopoulos, D Roth – 2015 – christos-c.com … Jarvie, G. 1995. Chambers Good Punctuation Guide. Cham- bers. Lin, Z.; Ng, HT; and Kan, M.-Y. 2012. A PDTB-styled end-to-end discourse parser. Natural Language Engineering 20(02):151–184. Marcus, MP; Santorini, B.; and Marcinkiewicz, M. 1993. … Cited by 1 Related articles All 7 versions

Interactive Visual Data Exploration: A Multi-Focus Approach J Zhao – 2015 – Citeseer Page 1. INTERACTIVE VISUAL DATA EXPLORATION: AMULTI-FOCUS APPROACH by Jian Zhao A thesis submitted in conformity with the requirements for the degree of Doctor of Philosophy Graduate Department of Computer Science University of Toronto … Related articles All 2 versions

Bridging Sentential and Discourse-level Semantics through Clausal Adjuncts R Prasad, B Webber, A Lee, S Pradhan… – Workshop on Linking …, 2015 – aclweb.org … 915. 68 Page 81. Lin, Z., Ng, HT, and Kan, M.-Y. 2012. A PDTB- styled end-to-end discourse parser. Natural Lan- guage Engineering, 20 (02), pages 151–184. Marcus, M., Santorini, B., and Marcinkiewicz, MA 1993. Building … Related articles All 9 versions

Defining the Right Frontier in Multi-Party Dialogue J Hunter, N Asher, E Kow, J Perret, S Afantenos – SEMDIAL 2015 goDIAL, 2015 – illc.uva.nl … We call the RFC defined with individual speaker Lasts RFC+MLAST. RFC+MLAST allows the discourse parser to attach turns 235, 236 and 238 in Figure 1 to turn 239 without violations, be- cause for every edge with 239 as its endpoint, its initial point is Last for some speaker. … Related articles All 5 versions

Document-level NLP Support for Improving Information Access A Louis – sigai.acm.org … tures give the best performance overall. To aid this type of work, I have also built discourse parsers [Pitler et al. 2009; Louis et al. 2010b] which can automatically as- sign discourse structure to texts. I have also developed task … Related articles

DAICA-Digital Assistant Investigating Cultural Assets L Hotz, D Cristea, J Pietrzak, M Povazay, B Rauter… – pdfs.semanticscholar.org … It involves a long processing chain (including a tokeniser, a part-of-speech tagger, a noun phrase chunking module, a name entity recogniser, an anaphora resolution module, a clause splitter and a discourse parser). The improvements … Related articles All 5 versions

Sentiment Classification of Arabic Documents: Experiments with multi-type features and ensemble algorithms A Bayoudhi, LH Belguith, H Ghorbel – 2015 – Citeseer Page 1. Sentiment Classification of Arabic Documents: Experiments with multi-type features and ensemble algorithms Amine Bayoudhi Lamia Hadrich Belguith Hatem Ghorbel ANLP Group, MIRACL ANLP Group, MIRACL ISIC Lab, HE-Arc … Related articles All 9 versions

Towards News Verification: Deception Detection Methods for News Discourse VL Rubin, NJ Conroy, Y Chen – 2015 – works.bepress.com Page 1. Western University From the SelectedWorks of Victoria Rubin Winter January 5, 2015 Towards News Verification: Deception Detection Methods for News Discourse Victoria L. Rubin Niall J. Conroy Yimin Chen Available at: http://works.bepress.com/victoriarubin/6/ … Cited by 4 Related articles All 3 versions

Annotating genericity: a survey, a scheme, and a corpus A Friedrich, A Palmer, MP Sørensen… – The 9th Linguistic …, 2015 – aclweb.org … specific instance of the game. We use the discourse parser SPADE (Soricut and Marcu, 2003) to segment the first 70 sentences of each Wikipedia article into clauses, which are the basis for annotation. Subjects are not pre-marked … Cited by 3 Related articles All 10 versions

Automatic Generation and Insertion of Assessment Items in Online Video Courses A Krishna, P Bhowmick, K Ghosh, A Sahu… – Proceedings of the 20th …, 2015 – dl.acm.org … RST style discourse parser5 is used to mark discourse rela- tions between different non-overlapping text spans in W?. The generated discourse parse tree is then traversed to ex- tract discourse relations and the corresponding text spans. … Related articles All 2 versions

Putting Text-Level Linguistics into Statistical Machine Translation A Popescu-Belis – 2015 – failid.whylinguistics.ut.ee … TimeML features • discourse relation features – discourse relations from a discourse parser • polarity features – using a polarity lexicon, count positive and negative words, account for negation • translational features – baseline … Related articles All 5 versions

Applying the SEXTANT Low-Level Parser to the G Grefenstette – researchgate.net … Tokenization divides the input string into tokens and sentences. After this point, all other treatment is confined to individual sentences. There are no inter-sentential relations created by this parser, such as would be found in an anaphor-resolving system or discourse parser. … Related articles

Deep learning for sentiment analysis: successful approaches and future challenges D Tang, B Qin, T Liu – Wiley Interdisciplinary Reviews: Data …, 2015 – Wiley Online Library … Tang et al.[78] compose sentence representations to document representation in a sequential way, without using external discourse parser. Bhatia et al.,[79] however, use RST discourse parser and integrate the parsed results with RNN for document level sentiment analysis. … Cited by 3 Related articles All 4 versions

Statistical Script Learning with Recurrent Neural Nets K Pichotta – 2015 – cs.utexas.edu … Second, we propose integrating more lexical and linguistic information into events. Third, we propose incorporating discourse relations between spans of text into event co-occurrence models, either as output by an off-the-shelf discourse parser or learned automat- ically. … Related articles All 3 versions

CODRA: A novel discriminative framework for rhetorical analysis S Joty, G Carenini, RT Ng – Computational Linguistics, 2015 – MIT Press … CODRA comprises a discourse segmenter and a discourse parser. First, the discourse segmenter, which is based on a binary classifier, identifies the elementary discourse units in a given text. Then the discourse parser builds … Cited by 14 Related articles All 13 versions

A hierarchical neural autoencoder for paragraphs and documents J Li, MT Luong, D Jurafsky – arXiv preprint arXiv:1506.01057, 2015 – arxiv.org Page 1. A Hierarchical Neural Autoencoder for Paragraphs and Documents Jiwei Li, Minh-Thang Luong and Dan Jurafsky Computer Science Department, Stanford University, Stanford, CA 94305, USA jiweil, lmthang, jurafsky@stanford.edu Abstract … Cited by 40 Related articles All 15 versions

This Table is Different: A WordNet-Based Approach to Identifying References to Document Entities S Wilson, AW Black, J Oberlander – Citeseer Page 1. This Table is Different: A WordNet-Based Approach to Identifying References to Document Entities Shomir Wilson Carnegie Mellon University shomir@cs.cmu.edu Alan W Black Carnegie Mellon University awb@cs.cmu.edu … Related articles All 6 versions

SENSEI Coordinator M Kabadjov, EA Stepanov, F Celli, SA Chowdhury… – sensei-conversation.eu … In Period 3 of the project overlaps will be additionally applied as low-level features for behavioral summarization of spoken conversations. In Section 2.3 we present the discourse parser trained on Penn Discourse Treebank [39] (Eng- lish). … Related articles

Unsupervised extraction of semantic relations using discourse information J Conrath – 2015 – thesesups.ups-tlse.fr Page 1. THÈSE En vue de l’obtention du DOCTORAT DE L’UNIVERSITÉ DE TOULOUSE Présentée et soutenue le 14/12/2015 par : Juliette Conrath Unsupervised extraction of semantic relations using discourse information Directeurs de Thèse : … Related articles

Data-Driven Content Analysis of Social Media A Systematic Overview of Automated Methods HA Schwartz, LH Ungar – The ANNALS of the American Academy …, 2015 – ann.sagepub.com … For example, a popular definition of optimism considers how one explains the cause of situations (Peterson and Seligman 1984). Capturing causal explanations is not easily done simply with words—one may need syntactic or even discourse parsers. … Cited by 8 Related articles All 2 versions

An Information theoretic approach to production and comprehension of discourse markers F Torabi Asr – 2015 – scidok.sulb.uni-saarland.de Page 1. An Information Theoretic Approach to Production and Comprehension of Discourse Markers Thesis for obtaining the title of Doctor of Engineering Science of the Faculty of Natural Science and Technology I of Saarland University by Fatemeh Torabi Asr Saarbruecken … Related articles All 2 versions

Learning answerentailing structures for machine comprehension M Sachan, A Dubey, EP Xing… – Proceedings of ACL, 2015 – msr-waypoint.net Page 1. Learning Answer-Entailing Structures for Machine Comprehension Mrinmaya Sachan1? Avinava Dubey1? Eric P. Xing1 Matthew Richardson2 1Carnegie Mellon University 2Microsoft Research 1{mrinmays, akdubey, epxing}@cs.cmu.edu 2mattri@microsoft.com … Cited by 10 Related articles All 7 versions

Searching for Context: a Study on Document-Level Labels for Translation Quality Estimation C Scarton, M Zampieri, M Vela… – The 18th Annual …, 2015 – academia.edu … HTER scores. Guzmán et al. (2014) explore RST trees (Mann and Thompson, 1987) for automatic evaluation of MT into English, with a discourse parser to anno- tate RST trees at sentence level in English. They compare the … Cited by 9 Related articles All 10 versions

When are tree structures necessary for deep learning of representations? J Li, MT Luong, D Jurafsky, E Hovy – arXiv preprint arXiv:1503.00185, 2015 – arxiv.org Page 1. When Are Tree Structures Necessary for Deep Learning of Representations? Jiwei Li1, Minh-Thang Luong1, Dan Jurafsky1 and Eduard Hovy2 1Computer Science Department, Stanford University, Stanford, CA 94305 … Cited by 26 Related articles All 15 versions

SENSEI Coordinator G Riccardi – sensei-conversation.eu Page 1. D6.2 – Report on the summarization views of the SENSEI prototype Document Number D6.2 Document Title Report on the summarization views of the SENSEI prototype Version 1.6 Status Final Workpackage WP6 Deliverable Type Report … Related articles

Mocking ads through mobile web services L Gatti, M Guerini, O Stock… – Computational …, 2015 – Wiley Online Library … 988–996. Hernault, H., H. Prendinger, D. A. duVerle, and M. Ishizuka. 2010. HILDA: A discourse parser using support vector machine classification. Dialogue & Discourse 1(3): 1–33. CrossRef. Lee, H., A. Chang, Y. Peirsman, N. Chambers, M. Surdeanu, and D. Jurafsky. 2013. … Cited by 1 Related articles All 2 versions

AutoODC: Automated generation of orthogonal defect classifications LG Huang, V Ng, I Persing, M Chen, Z Li… – Automated Software …, 2015 – Springer … contrast relation. Returning to the question of how we can identify the aforementioned conditions and context, we employ the PDTB-styled end-to-end discourse parser (Lin et al. 2014) to perform shallow discourse analysis. More … Cited by 30 Related articles All 16 versions

Soft Computing Applications VE Balas, LC Jain, B Kova?evi? – Springer … 515 Maria Laura Sebu and Horia Ciocârlie x Contents Page 12. Evaluating the Performance of Discourse Parser Systems….. 525 Elena Mitocariu Considerations Regarding an Algebraic Model for Inference and Decision on Heterogeneous Sensory Input….. … All 3 versions

The Discourse Structure Of Turkish ISIND SAHIN – 2015 – etd.lib.metu.edu.tr Page 1. THE DISCOURSE STRUCTURE OF TURKISH A THESIS SUBMITTED TO THE GRADUATE SCHOOL OF INFORMATICS OF MIDDLE EAST TECHNICAL UNIVERSITY I SIN DEMIR SAHIN IN PARTIAL FULFILLMENT … Related articles All 2 versions

Automatically identifying transitions between locutions in dialogue K Budzynska, M Janier, J Kang… – 1st European …, 2015 – hal.archives-ouvertes.fr … 987-996). ACL. Hernault, H., Prendinger, H., duVerle, DA, & Ishizuka, M. (2010). HILDA: a discourse parser using support vector machine classification. Dialogue and Discourse, 1(3), 1-33. Janier M., Aakhus, M., Budzynska, K. & Reed, C (this issue). … Cited by 3 Related articles All 8 versions

An Integrated Approach to Functional Corpus Construction HB Yan, J Webster – Taiwan Journal of Linguistics, 2015 – airitilibrary.com Page 1. Taiwan Journal of Linguistics Vol. 13.1, 53-77, 2015 doi:10.6519/TJL.2015.13( 1).3 53 AN INTEGRATED APPROACH TO FUNCTIONAL CORPUS CONSTRUCTION Hengbin Yan1 and Jonathan Webster2 1Faculty of … Related articles All 3 versions

Situation Entity Types A Friedrich, A Palmer – 2015 – coli.uni-saarland.de … In order to provide a common basis for annota- tors, we segment the texts into clauses using a freely available discourse parser, SPADE (Soricut and Marcu, 2003), and apply customized post-processing steps (described in Section 3.2). … Related articles

Finding Ways to Assess Machine Translated Documents for Document-level Quality Prediction C Scarton – Hernani Costa, Anna Zaretskaya, Gloria Corpas Pastor – expert-itn.eu … scores. 70 Page 77. Guzmán et al.(2014) explore RST trees (Mann and Thompson, 1987) for automatic evaluation of MT into English, with a discourse parser to annotate RST trees at sentence level in English. They compare … Related articles All 6 versions

Combining Statistical and Semantic Knowledge for Sarcasm Detection in Online Dialogues JM Alcaide, R Justo, MI Torres – Iberian Conference on Pattern …, 2015 – Springer … Schölkopf, B., Smola, AJ, Williamson, RC, Bartlett, PL: New support vector algorithms. Neural Comput. 12(5), 1207–1245 (2000). 15. Subba, R., Di Eugenio, B.: An effective discourse parser that uses rich linguistic information. In: Proceedings of NAACL HLT 2009, pp. 566–574. … Related articles

Sentic Patterns E Cambria, A Hussain – Sentic Computing, 2015 – Springer … In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 733–734. ACM (2007). 194. Lin, Z., Ng, HT, Kan, MY: A PDTB-styled end-to-end discourse parser. Nat. Lang. Eng. … Related articles

Framework for quality estimation C Scarton, L Specia, J van Genabith, M Zampieri – 2015 – expert-itn.eu Page 1. Project reference: 317471 Project full title: EXPloiting Empirical appRoaches to Translation D5.1: Framework for quality estimation Authors: Carolina Scarton (USFD) Contributors: Lucia Specia (USFD), Josef van Genabith (USAAR), Marcos Zampieri (USAAR) … Related articles

Sentiment Analysis of Data from Online Forums on the Newborn Genome Sequencing H Poursepanj – 2015 – ruor.uottawa.ca Page 1. Sentiment Analysis of Data from Online Forums on the Newborn Genome Sequencing By Hamid Poursepanj Thesis submitted to the Faculty of Graduate and Postdoctoral Studies In partial fulfillment of the requirements For Master of Computer Science (MCS) … All 4 versions

The SENSEI Project: Making Sense of Human Conversations G Riccardi, F Bechet, M Danieli, B Favre… – … Workshop on Future …, 2015 – Springer Related articles All 2 versions

Resolving shell nouns V Kolhatkar – 2015 – cs.toronto.edu Page 1. RESOLVING SHELL NOUNS by Varada Kolhatkar A thesis submitted in conformity with the requirements for the degree of Doctor of Philosophy Graduate Department of Computer Science University of Toronto c Copyright 2015 by Varada Kolhatkar Page 2. Abstract … Cited by 2 Related articles All 36 versions

What Automated Analyses Of Corpora Can Tell Us About Students’ Writing Skills P De – jowr.org … These include spellchecking, methods that detect characteristic word sequences (also known as n-grams) that indicate the presence of grammatical errors, and the application of a discourse parser to recognize key structural elements of an essay. … Related articles

Pipeline Robustness H Wachsmuth – Text Analysis Pipelines, 2015 – Springer

A survey on question answering systems with classification A Mishra, SK Jain – Journal of King Saud University-Computer and …, 2015 – Elsevier Question answering systems (QASs) generate answers of questions asked in natural languages. Early QASs were developed for restricted domains and have limited ca. Cited by 1 Related articles

Mining the Biomedical Literature C Mihaila, R Batista-Navarro, N Alnazzawi… – Healthcare Data …, 2015 – books.google.com Page 280. Chapter 8 Mining the Biomedical Literature Claudiu Mihaila National Centre for Text Mining University of Manchester Manchester, UK claudiu. mihaila@ manchester. ac. uk Riza Batista-Navarro National Centre for … Related articles

[BOOK] Knowledge Science, Engineering and Management: 8th International Conference, KSEM 2015, Chongqing, China, October 28-30, 2015, Proceedings S Zhang, M Wirsing, Z Zhang – 2015 – books.google.com … Representation….. Kai Ye, Liangqiang Li, Mengzhuo Guo, Yu Qian, and Hua Yuan Building a High Performance End-to-End Explicit Discourse Parser for Practical Application….. Jianxiang …

Joint graphical models for date selection in timeline summarization G Tran, E Herder, K Markert – … of the 53rd Annual Meeting of …, 2015 – eprints.whiterose.ac.uk Page 1. This is an author produced version of Joint Graphical Models for Date Selection in Timeline Summarization. White Rose Research Online URL for this paper: http://eprints.whiterose.ac.uk/91931/ Proceedings Paper: Tran … Cited by 1 Related articles All 10 versions

SenticNet E Cambria, A Hussain – Sentic Computing, 2015 – Springer … In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 733–734. ACM (2007). 194. Lin, Z., Ng, HT, Kan, MY: A PDTB-styled end-to-end discourse parser. Nat. Lang. Eng. … Cited by 2 Related articles

Sentic Applications E Cambria, A Hussain – Sentic Computing, 2015 – Springer … In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 733–734. ACM (2007). 194. Lin, Z., Ng, HT, Kan, MY: A PDTB-styled end-to-end discourse parser. Nat. Lang. Eng. … Related articles

Attribution: a computational approach S Pareti – 2015 – era.lib.ed.ac.uk Page 1. This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (eg PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use: This work … Cited by 2 Related articles All 2 versions

Analytics Meta Learning Z Yang – 2015 – cs.cmu.edu Page 1. February 1, 2016 DRAFT Analytics Meta Learning Zi Yang June 2015 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Thesis Committee: Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy. … Related articles All 3 versions