Báo cáo khoa học: "Finding Salient Dates for Building Thematic Timelines" pot
... only this information to detect salient dates for the construction of event timelines. Other types of content are used for initial thematic document retrieval. Output is a list of dates, ranked from ... 730–739, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Finding Salient Dates for Building Thematic Timelines R ´ emy Kessler...
Ngày tải lên: 23/03/2014, 14:20
... describing target entities for IE, as their arguments. Thus verbs which take top- ical nouns can be candidates for anchor verbs. Our method collects anchor verb candidates by choosing PASs whose ... discovering enormous amount of new facts, and thus there is an increasing need for information extraction (IE) technology to support database building and to find novel knowledge in online...
Ngày tải lên: 31/03/2014, 03:20
... that the LinguaStream platform promotes the combination of purely declarative formalisms (when GATE is mostly based on the JAPE language and NOOJ focuses on a unique formalism), and allows processing ... analy- sis models and methodological concerns. Finally, when other platforms usually enforce the use of a dedicated document format, LinguaStream is able to process any XML document. On the o...
Ngày tải lên: 22/02/2014, 02:20
Tài liệu Báo cáo khoa học: "A rich environment for experimentation unification grammars" potx
... into discussion of the under- lying complexity, for which we unfortunately do not have space here, we give an exter- nal form of a lexical entry for some of the senses of the German verb traeumen. ... PATR-style languages is their lack of facilities for defining new abstractions and expressing linguistic generalisations not foreseen (or even foreseeable) by the language desi...
Ngày tải lên: 22/02/2014, 10:20
Tài liệu Báo cáo khoa học: "A COMMON FRAMEWORK FOR ANALYSIS AND GENERATION" potx
... compo- nent describing their functional structure. For the rule for S, for instance, we add an ele- ment describing what the SUBJECT and PRED are for. We could say that the SUBJECT is the theme ... complete formal paraphrase of (1) must include at least as much information as we have given above. In particular, the logical structure of our para- phrases contains essential inform...
Ngày tải lên: 22/02/2014, 10:20
Báo cáo khoa học: "Advanced Online Learning for Natural Language Processing" pot
Ngày tải lên: 08/03/2014, 01:20
Báo cáo khoa học: "Learning Expressive Models for Word Sense Disambiguation" pot
... customized for this monolingual task, the ILP approach signif- icantly outperforms the majority sense baseline and performs as well as the state-of-the-art system re- porting results for the same ... context. For example, among the possible senses of the verb “run” are “to move fast by using one's feet” and “to direct or control”. WSD can be useful for many applications, incl...
Ngày tải lên: 08/03/2014, 02:21
Báo cáo khoa học: "A STOCHASTIC PROCESS FOR WORD FREQUENCY DISTRIBUTIONS" pot
... (1975), have been put forward, all of which have Zipf's law as some special or limiting form. Unrelated to Zipf's law is the lognormal hypothesis, advanced for word fre- quency ... matrix 7 ) defines a uniform distribu- tion (all pi# equal), we immediately have that the expected neighborhood density for length rnl is identical for all targets Yt, while for length m~...
Ngày tải lên: 08/03/2014, 07:20
Báo cáo khoa học: "Using Derivation Trees for Treebank Error Detection" potx
... and points on either side). See Dickinson and Meur- ers (2003b) for details. This work forms the basis for the DECCA system. 1 2.2 Motivation for Our Approach (2) a. NP qmp summit NP $rm Sharm NP Al$yx the ... Sheikh NP #a3 qmp summit #b1 S:1.2 NP NP^ $rm Sharm #b2 NP Al$yx The Sheikh For (2a) For (2b) For (2c) A:1.1,left #b3 NP Al$yx The Sheikh A:1.1,left #c3 $rm Sharm Figure 1...
Ngày tải lên: 17/03/2014, 00:20
Báo cáo khoa học: "Incremental HMM Alignment for MT System Combination" pot
... the order of hypotheses. If hypothesis 2 is aligned before hypothesis 1, the final CN will not be good. Therefore, the obser- vation in Rosti et al. (2008) that different order of hypotheses does ... align- ment of any of the hypotheses, no matter how good the alignments of other hypotheses are. For ex- ample, suppose we have the backbone “he buys a computer” and two hypotheses “he bought a...
Ngày tải lên: 17/03/2014, 01:20