unsupervised learning of narrative schemas and their participants

Unsupervised Learning of Narrative Event Chains docx

Unsupervised Learning of Narrative Event Chains docx

Ngày tải lên : 07/03/2014, 17:20
... coherence judgements of real narrative in- stances extracted from documents. Finally, the space of narrative events and temporal orders is clustered and pruned to create discrete sets of narrative chains. 2 ... single actor in this study, a narrative event is thus a tuple of the event and the typed dependency of the protagonist: (event, depen- dency). A narrative chain is a set of narrative events {e 1 , ... consti- tute narrative chains. Formally, a narrative chain is a partially ordered set of narrative events that share a common actor. A narrative event is a tu- ple of an event (most simply a verb) and...
  • 9
  • 396
  • 0
Tài liệu ALPHABETICAL INDEX OF REPRESENTED ORGANIZATIONS AND THEIR LEGISLATIVE AGENTS BY REGISTRATION NUMBER FOR THE THIRD QUARTER 2002 docx

Tài liệu ALPHABETICAL INDEX OF REPRESENTED ORGANIZATIONS AND THEIR LEGISLATIVE AGENTS BY REGISTRATION NUMBER FOR THE THIRD QUARTER 2002 docx

Ngày tải lên : 16/02/2014, 10:20
... 75 Association of NJ Rifle & Pistol Clubs 1233 Association of Residential CADE Homes of NJ 803 Association of Schools and Agencies/Handicapped 811 Association of Test Borers 868 Association of Trial ... 1244 Center for Non-Profit Corp Inc 682 Central States Indemnity Co of Omaha 26 CentraState Medical Ctr 1247 Page 8 of 51 PART III ALPHABETICAL INDEX OF REPRESENTED ORGANIZATIONS AND THEIR LEGISLATIVE ... 365 Association of Hearing Health Professionals 100 Association of Ind Colleges & Universities in NJ 304 Association of Independent Cemeteries 1247 Association of Municipal Assessers of NJ 75 Association...
  • 51
  • 574
  • 0
Tài liệu Báo cáo khoa học: "Going Beyond AER: An Extensive Analysis of Word Alignments and Their Impact on MT" pdf

Tài liệu Báo cáo khoa học: "Going Beyond AER: An Extensive Analysis of Word Alignments and Their Impact on MT" pdf

Ngày tải lên : 20/02/2014, 11:21
... AER: An Extensive Analysis of Word Alignments and Their Impact on MT Necip Fazil Ayan and Bonnie J. Dorr Institute of Advanced Computer Studies (UMIACS) University of Maryland College Park, MD 20742 {nfa,bonnie}@umiacs.umd.edu Abstract This ... correspond to the phrase pairs with j FL words and i English words. For S U and S G , the majority of the phrases contain only one FL word, and the percentage of the phrases with more than 2 FL words ... set (top row) and the phrases used in decoding the same test set (bottom row) ac- cording to their lengths 50-65% of the total number of phrases used in de- coding). S I , S A and S B use the...
  • 8
  • 508
  • 0
Báo cáo khoa học: "Task-oriented Evaluation of Syntactic Parsers and Their Representations" potx

Báo cáo khoa học: "Task-oriented Evaluation of Syntactic Parsers and Their Representations" potx

Ngày tải lên : 08/03/2014, 01:20
... dependency parsers (Mc- Donald and Pereira, 2006; Nivre and Nilsson, 2005; Sagae and Tsujii, 2007) and deep parsers (Kaplan et al., 2004; Clark and Curran, 2004; Miyao and Tsujii, 2008). However, ... system with several combinations of parser and parse representa- tion, and examine their impact on PPI identi- fication accuracy. Our experiments show that the levels of accuracy obtained with these ... Katrenko and Adriaans 52 Proceedings of ACL-08: HLT, pages 46–54, Columbus, Ohio, USA, June 2008. c 2008 Association for Computational Linguistics Task-oriented Evaluation of Syntactic Parsers and Their...
  • 9
  • 483
  • 0
Báo cáo khoa học: "Unsupervised Learning of Acoustic Sub-word Units" pot

Báo cáo khoa học: "Unsupervised Learning of Acoustic Sub-word Units" pot

Ngày tải lên : 08/03/2014, 01:20
... µ s 4 and µ s 2 = µ s +δ = µ s 3 , with δ = λ ∗ v ∗ , where λ ∗ and v ∗ are the principal eigenvalue and eigen- vector of Σ s and 0 <   1 is typically 0.2. 3. Re-estimate all parameters of ... ML-SSS. 4.2 Unsupervised Learning of Sub-word Units We used about 30 minutes of phonetically tran- scribed Japanese speech from one speaker 6 provided by Maekawa (2003) for our unsupervised learning experiments. ... desired, re-estimate all parameters of the new HMM, and go to Step 2. Note that the key computational steps are the for- loop of Step 2 and the re-estimation of Step 3. Modifications to the ML-SSS...
  • 4
  • 295
  • 0
Báo cáo khoa học: "Unsupervised Learning of Arabic Stemming using a Parallel Corpus" pot

Báo cáo khoa học: "Unsupervised Learning of Arabic Stemming using a Parallel Corpus" pot

Ngày tải lên : 08/03/2014, 04:22
... over unstemmed text, and 93-96% of the performance of the state of the art, language specific stemmer above. We can speculate that, because of the statistical nature of the unsupervised stemmer, ... posi- tion of policy of the Government and no of cial en- dorsement should be inferred. References P. Brown, S. Della Pietra, V. Della Pietra, and R. Mer- cer. 1993. The mathematics of machine ... Proceedings of the 40th Annual Meeting of the As- sociation for Computational Linguistics (ACL), pages 255–262, July. John Goldsmith. 2001. Unsupervised learning of the morphology of a natural...
  • 8
  • 424
  • 0
Gipsy Life being an account of our Gipsies and their children docx

Gipsy Life being an account of our Gipsies and their children docx

Ngày tải lên : 08/03/2014, 13:20
... middle of the village, and two women (sometimes more) would fall out of the ranks, hand their bonnets to friends, strip off cloak and gown, and fight in their 'shift' sleeves, using their ... outside their mystery boxes, with their thin, flimsy veil of romance and superstitious turn of their faces, will soon discover their Indian character. Of course their intermixture with Circassians and ... men and women living as husbands and wives are unmarried. Mrs. Simpson, a Gipsy woman and a Christian, says she has six sons and daughters and sixteen grandchildren, and only two can read and...
  • 142
  • 471
  • 0
Daughters of the Revolution and Their Times 1769 - 1776 doc

Daughters of the Revolution and Their Times 1769 - 1776 doc

Ngày tải lên : 08/03/2014, 18:20
... daughter of the secretary of the Province, Miss Dorothy Quincy, Miss Mary Shrimpton, and to Isaac and John Coffin[28], sons of his majesty's receiver-general. Daughters of the Revolution and Their ... resistance to that claim was the agreement of all but six of the merchants of Boston not to import tea from England, and the agreement of their wives and daughters not to drink tea so imported. ... story of oppression on the part of Parliament towards the Colonies, or to picture the greed of the merchants and manufacturers of England, who could not then, and who cannot now, bear to think of...
  • 178
  • 522
  • 0
Báo cáo Y học: Fluorescent analogs of UDP-glucose and their use in characterizing substrate binding by toxin A from Clostridium difficile pdf

Báo cáo Y học: Fluorescent analogs of UDP-glucose and their use in characterizing substrate binding by toxin A from Clostridium difficile pdf

Ngày tải lên : 08/03/2014, 22:20
... 3427 Fluorescent analogs of UDP-glucose and their use in characterizing substrate binding by toxin A from Clostridium difficile Sudeep Bhattacharyya, Amy Kerzmann and Andrew L. Feig Department of Chemistry, ... hydrolysis of UDP-Glc to UDP and free glucose (Scheme 1) [6,11]. The molecular biology and domain structure of these toxins has been studied previously [12,13]. TcdA and TcdB share 43% homology and ... have identified D285 and D287 in TcdA as the aspartate residues of this motif [17]. Glycosyltransferases commonly employ Mg 2+ and/ or Mn 2+ cofactors in their catalytic mechanisms and these toxins...
  • 8
  • 516
  • 0
Báo cáo khoa học: "Hierarchical Sequential Learning for Extracting Opinions and their Attributes" ppt

Báo cáo khoa học: "Hierarchical Sequential Learning for Extracting Opinions and their Attributes" ppt

Ngày tải lên : 17/03/2014, 00:20
... a number of related tasks, such as identifying expressions of opinion (e.g. Kim and Hovy (2005), Popescu and Etzioni (2005), Breck et al. (2007)), determining their polarity (e.g. Hu and Liu (2004), ... Hierarchical Sequential Learning We define the problem of joint extraction of opin- ion expressions and their attributes as a sequence tagging task as follows. Given a sequence of to- kens, x = x 1 ... Riloff and T. Wilson. 2002. Summer Workshop on Multiple- Perspective Question Answering: Final Report. In NRRC. J. Wiebe and T. Wilson and C. Cardie 2005. Annotat- ing Expressions of Opinions and...
  • 6
  • 299
  • 0
Báo cáo khoa học: "Unsupervised Learning of Dependency Structure for Language Modeling" potx

Báo cáo khoa học: "Unsupervised Learning of Dependency Structure for Language Modeling" potx

Ngày tải lên : 17/03/2014, 06:20
... the elements of the DLM that assign probability to each possible W and its most probable D, P(W, D). Fi- nally, we present an EM-like iterative method for unsupervised learning of dependency ... probability of Equation (11) backs off to the estimate of P(w j |R), which is computed as: N RwC RwP j j ),( )|( = , (14) where N is the total number of dependencies in training data, and C(w j , ... compounds. Unsupervised Learning of Dependency Structure for Language Modeling Jianfeng Gao Microsoft Research, Asia 49 Zhichun Road, Haidian District Beijing 100080 China jfgao@microsoft.com...
  • 8
  • 380
  • 0
Elderly Victims of Sexual Abuse and Their Offenders doc

Elderly Victims of Sexual Abuse and Their Offenders doc

Ngày tải lên : 22/03/2014, 13:20
... Date, time, and day of the week; location, type and sequence of sexual acts; number of offenders; single or multiple crimes; Victims response to the offender (resistance and offenders reaction); ... and prosecution of elder sexual abuse. Institutional Review Board (IRB) IRB approval was granted by Boston College for record reviews of elder victims of sexual abuse and their offenders and ... seeks to expand the understanding of the impact of elder sexual abuse on highly vulnerable victims, thereby improving the protocols for evaluating and treating these victims and their offenders....
  • 157
  • 332
  • 0
ALPHABETICAL INDEX OF REPRESENTED ORGANIZATIONS AND THEIR GOVERNMENTAL AFFAIRS AGENTS BY REGISTRATION NUMBER FOR THE SECOND QUARTER 2005 potx

ALPHABETICAL INDEX OF REPRESENTED ORGANIZATIONS AND THEIR GOVERNMENTAL AFFAIRS AGENTS BY REGISTRATION NUMBER FOR THE SECOND QUARTER 2005 potx

Ngày tải lên : 22/03/2014, 21:20
... Society of New Jersey 1427 Medical Society of NJ 174 Medical Society of NJ 721 Medical Transportation Assn of NJ 703 Page 37 of 75 PART III ALPHABETICAL INDEX OF REPRESENTED ORGANIZATIONS AND THEIR ... ORGANIZATION NAME AGENT REGISTRATION NUMBER County of Hunterdon 1439 County of Morris 849 County of Morris 1234 County of Warren 1439 County Officers Assn of NJ 365 Covanta Energy Corp 721 Craftmatic ... Solutions 721 Metro Newark Chamber of Commerce 703 Meyner & Landis LLP 1256 Page 38 of 75 PART III ALPHABETICAL INDEX OF REPRESENTED ORGANIZATIONS AND THEIR GOVERNMENTAL AFFAIRS AGENTS BY...
  • 75
  • 400
  • 0
Báo cáo khoa học: "Unsupervised Learning of Semantic Relation Composition" ppt

Báo cáo khoa học: "Unsupervised Learning of Semantic Relation Composition" ppt

Ngày tải lên : 23/03/2014, 16:20
... Huhns and Stephens (1989). Their relations are not linguistically motivated and ten of them map to some sort of PART-WHOLE (e.g. PIECE- OF, SUBREGION -OF) . Unlike (Cohen and Losielle, 1988; Huhns and ... deep characteristics of relations. They are independently determinable for each relation and specify a property between an el- ement of the domain and an element of the range of the relation being ... Cohen and Losielle (1988) combines a set of nine fairly specific relations (e.g., FOCUS -OF, PRODUCT -OF, SETTING -OF) . The key to determine plausibility is the transitivity charac- teristic of the...
  • 10
  • 293
  • 0