genre distinctions for discourse
Tài liệu Báo cáo khoa học: "An annotation scheme for discourse-level argumentation in research articles" doc
... work as basis of or support for own work? Figure 2: Decision tree for annotation Our materials consist of 48 computational lin- guistics papers (22 for Study I, 26 for Study II), taken from ... information besides computational lin- guistics knowledge, performed satisfactorily - a fact that seems to confirm the promise of shallow methods. Overall, reproducibility and stability for ... train- ing, including the reading of coding instructions for the two versions of the scheme (6 pages for the basic scheme and 17 pages for the full scheme), four training papers and weekly discussions,...
- 8
- 396
- 0
Báo cáo khoa học: "Choosing Sense Distinctions for WSD: Psycholinguistic Evidence" potx
... pages 249–252,Columbus, Ohio, USA, June 2008.c2008 Association for Computational LinguisticsChoosing Sense Distinctions for WSD: Psycholinguistic Evidence Susan Windisch Brown Department ... accessibility, has become the resource of choice for WSD. However, some have questioned whether WordNet’s fine-grained sense distinctions are ap-propriate for the task (Ide & Wilks, 2007; Palmer ... implications for automatic word sense disam-biguation. 1 Introduction* The problem of creating a successful word sense disambiguation system begins, or should begin, well before methods...
- 4
- 177
- 0
Báo cáo khoa học: "Chinese Comma Disambiguation for Discourse Analysis" pptx
... information totrain and test supervised models. This discourse information is formalized as a classification of theChinese comma, with each class representing theboundary of an elementary discourse ... Association for Computational Linguistics, pages 786–794,Jeju, Republic of Korea, 8-14 July 2012.c2012 Association for Computational LinguisticsChinese Comma Disambiguation for Discourse AnalysisYaqin ... tobe the anchor of discourse relations, in the sense ofthe Penn Discourse Treebank (PDT) (Prasad et al.,2008). Disambiguating the comma is thus necessary for the purpose of discourse segmentation,...
- 9
- 280
- 0
Tài liệu Báo cáo khoa học: "Unsupervised Topic Modelling for Multi-Party Spoken Discourse" ppt
... Association for Computational LinguisticsUnsupervised Topic Modelling for Multi-Party Spoken Discourse Matthew PurverCSLIStanford UniversityStanford, CA 94305, USAmpurver@stanford.eduKonrad ... speech recognition data for theICSI corpus and for their helpful advice; JohnNiekrasz and Alex Gruenstein for help with theNOMOS corpus annotation tool; and Michel Gal-ley for discussion of his ... threshold, increasing performance; ifnot, we must set it at a level which corresponds tothe desired general level of granularity. For eachset of annotations, we therefore performed twosets of segmentations:...
- 8
- 366
- 0
Tài liệu Báo cáo khoa học: "DiMLex: A lexicon of discourse markers for text generation and understanding" docx
... pieces of information on German and English discourse markers from grammars, dic- tionaries, and the linguistics research literature. This information is classified and organized into a discourse ... treat discourse marker selection as a task to be performed as a "side effect" by the gram- mar, much like for other function words such as prepositions. 1240 2 Building a Discourse ... criteria. Therefore, under the generation view, the infor- mation in DiMLex is grouped into the following three classes: Applicability conditions: The necessary conditions for using a discourse...
- 5
- 528
- 0
Báo cáo khoa học: "The utility of parse-derived features for automatic discourse segmentation" doc
... segmentation performance, we also be-lieve that it will prove useful for improving full discourse parsing, both at the sentence level andbeyond. For efficient inter-sentential discourse parsing, ... boundaries in the RST-DT donot correspond to a well-formed subtree in the hu-man annotated discourse parse for that document.Therefore, to perform accurate and efficient pars-ing of the RST-DT ... approach shouldwork well for Discourse GraphBank style parsing.The Penn Discourse Treebank (Miltsakaki et al.,2004), or PDTB, uses a relatively flat annotation of discourse structure, in contrast...
- 8
- 373
- 0
Báo cáo khoa học: "Semantic Discourse Segmentation and Labeling for Route Instructions" potx
... mentions of LEFT/RIGHT,• For each occurrence of LEFT/RIGHT, look for an ordinal number, LAST, or END (= endof the hallway) nearby,• Also, for each LEFT/RIGHT, look for a men-tion of DOOR. ... DECODE PATH(x, n, start, go) for each label y1node[0][y1].cost ← s(y1, 0)node[0][y1].end ← start; for j ← 1 to n − 1 for each label yj+1bestc ← −∞;end ← null; for each label yjcost ... suchmodels will perform better. Also, some form ofco-reference resolution or more sophisticated ac-tion tracking should also be considered.AcknowledgementWe thank Dr. Andrew Haas for introducing...
- 6
- 374
- 0
Báo cáo khoa học: "EMPIRICAL STUDIES OF DISCOURSE REPRESENTATIONS FOR NATURAL LANGUAGE INTERFACES" ppt
... systems. In these cases more than one task can be performed, asking for information and giving an order. This means not only that the discourse representation needs to be more complicated, ... "holes" in the sys- tem performance, i.e. finding subsets for which we can computationally handle complete linguistic and conceptual coverage. This points to the need for theories of the 'sublanguage' ... linguistic representation used. An utterance can obviously only be ill-formed relative to a formal specification of well-formedness. With some hesitation the exclusion of such a specifi- cation...
- 8
- 302
- 0
Báo cáo khoa học: "Disambiguating Temporal–Contrastive Discourse Connectives for Machine Translation" docx
... signaledby a connective. For French, the ANNODIS project for anno-tation of discourse (Pery-Woodley et al., 2009)will provide an original, discourse- annotated cor-pus. Resources for Czech are also ... 2010). For German, a lexi-con of discourse connectives exists since the 1990s,namely DiMLex for lexicon of discourse markers(Stede and Umbach, 1998). An equivalent, more re-cent database for ... 2010) or the tagging of pro-nouns for grammatical gender agreement (Le Na-gard and Koehn, 2010). On the other hand, inte-grating discourse information, such as discourse re-lations holding between...
- 6
- 181
- 0
Báo cáo khoa học: "Implementing a Characterization of Genre for Automatic Genre Identification of Web Pages" pot
... only paper genres (both literary and practical genres), but also digital genres, and more specifically web genres. Web genres or cybergenres (Shepherd and Watters 1998) are those genres created ... applied for determining genres. In particular, for each of the seven web genre included in this implementation, few hand-crafted rules combine the two predominant text types per web genre with ... BBC genres represent traditional genres adapted to the functionalities of the web, while the seven genres are novel web genres, either unprecedented or showing a loose kinship with paper genres....
- 8
- 318
- 0
Báo cáo khoa học: "Discourse Cues for Broadcast News Segmentation" potx
... Figure 1) or MS-NBC. For example, the structure for the Jim Lehrer News Hour provides not only segmentation information but also content information for each segment. Thus, the order of stories ... regularity of these discourse cues from broadcast to broadcast provides an effective foundation for discourse- based segmentation routines. We have similarly discovered regular discourse cues in ... Table 1. Segmentation Performance Table 1 presents average precision and recall results for multiple programs after applying generalized cue patterns developed first for ABC as described in...
- 4
- 366
- 0
Báo cáo khoa học: "AN ALGORITHM FOR PLAN RECOGNITION COLLABORATIVE DISCOURSE*" pot
... modelling this information and have provided an algorithm for constructing and reasoning with it. The steps of the construction algorithm parallel the reasoning that an agent performs in determining ... in a fixed order. 34 AN ALGORITHM FOR PLAN RECOGNITION IN COLLABORATIVE DISCOURSE* Karen E. Lochbaum Aiken Computation Lab Harvard University 33 Oxford Street Cambridge, MA 02138 kel~harvard.harvard.edu ... assumptions made by his formal model, we directly compare our algorithm to his. ACTION P~EPRESENTATION We use the action representation formally defined by Balkanski (1990) for modelling collaborative...
- 6
- 293
- 0
Báo cáo khoa học: "Discourse Structures for Text Generation" doc
... the Request schema for inducing actions, the Evidence schema for making claims credible, the/nform schema for causing the reader to know particular information, and so forth. Our knowledge ... particular kinds of purposes which they serve: questions for obtaining information, marked syntactic constructions for creating emphasis, and so forth. At the schema level as well, it is easy to associate ... is often easy to locate formal correlates for the notions of evidence, elaboration, condition, and so forth, that are expressed in rhetorical structure; the problem of formalization is not necessarily...
- 9
- 305
- 0
ETSI WIDEBAND CDMA STANDARD FOR THE UTRA FDD AIR INTERFACE.pdf
... high-speed data for multimedia services has been the driving forces for developments in third generation, or 3G, infrastructures. Perhaps a more subtle reason for the need for 3G is the growing ... be different for different users within the cell and between cells. It is used for transmitting the forward access channel (FACH) for access grant and the paging channel (PCH) for paging, both ... diversity, the BER performance improved as the chip rate increased. For a chip rate of 0.96 Mcps, the BER performance was close to the computer simulated BER performance with L=1. The performance with...
- 28
- 929
- 0
Tìm thêm: xác định các mục tiêu của chương trình xác định các nguyên tắc biên soạn khảo sát các chuẩn giảng dạy tiếng nhật từ góc độ lí thuyết và thực tiễn khảo sát chương trình đào tạo của các đơn vị đào tạo tại nhật bản xác định thời lượng học về mặt lí thuyết và thực tế tiến hành xây dựng chương trình đào tạo dành cho đối tượng không chuyên ngữ tại việt nam điều tra đối với đối tượng giảng viên và đối tượng quản lí điều tra với đối tượng sinh viên học tiếng nhật không chuyên ngữ1 khảo sát các chương trình đào tạo theo những bộ giáo trình tiêu biểu nội dung cụ thể cho từng kĩ năng ở từng cấp độ xác định mức độ đáp ứng về văn hoá và chuyên môn trong ct các đặc tính của động cơ điện không đồng bộ hệ số công suất cosp fi p2 đặc tuyến mômen quay m fi p2 đặc tuyến dòng điện stato i1 fi p2 động cơ điện không đồng bộ một pha sự cần thiết phải đầu tư xây dựng nhà máy phần 3 giới thiệu nguyên liệu từ bảng 3 1 ta thấy ngoài hai thành phần chủ yếu và chiếm tỷ lệ cao nhất là tinh bột và cacbonhydrat trong hạt gạo tẻ còn chứa đường cellulose hemicellulose chỉ tiêu chất lượng 9 tr 25