Báo cáo khoa học: "Using Linguistic Knowledge in Automatic Abstracting" potx

Tài liệu Báo cáo khoa học: "Identifying Linguistic Structure in a Quantitative Analysis of Dialect Pronunciation" docx

... of linguistic structure in the aggregate analysis is based on the analysis ofthe pronunciation of the vowels found in the data set. In work presented in this paper the identiﬁcationof linguistic ... Proceedings of the ACL 2007 Student Research Workshop, pages 61–66,Prague, June 2007.c2007 Association for Computational LinguisticsIdentifying Linguistic Structure in a QuantitativeAnalysis ... the divisions ob-tained by the aggregate analysis.1 IntroductionComputational dialectometry is a multidisciplinaryﬁeld that uses quantitative methods in order to mea-sure linguistic differences...

Tài liệu Báo cáo khoa học: "Using linguistic principles to recover empty categories" ppt

... nodes in the string, taking a POS-tagged string as input, and outputting a POS-tagged string with labeled empty nodes inserted. The PCFG parser is then trained, using the enhanced strings as input, ... illustrated in Figure 2, where the final line inserts NP* with the function tag SBJ in the case where it is the subject of an infinitive clause. The rule that inserts WH-trace (called in line 12 in ... try to insert *U* in X 7 try to insert a VP ellipsis site in X 8 try to insert S*T* or SBAR in X 9 try to insert trace of topicalized XP in X 10 try to insert trace of extraposition in X 11...

Tài liệu Báo cáo khoa học: "User Participation Prediction in Online Forums" potx

... mutual information between users afterdoing an average-link clustering on their pairwisemutual information. In a clean clustering, intra-cluster mutual information should be high, whileinter-cluster ... andJanusz Wnek. 1997. Learning and revising user pro-ﬁles: The identiﬁcation of interesting web sites. In Machine Learning, pages 313–331.Elaine Rich. 1979. User modeling via stereotypes.Cognitive ... thewords inside latent topics in the LDA model in- ferred from online forums, we show in Table 2 thetop words in 3 out of 20 latent topics inferred from“Ubuntu” forum according to its multinomial...

Tài liệu Báo cáo khoa học: "Using adaptor grammars to identify synergies in the unsupervised acquisition of linguistic structure" docx

... these independently. Thissuggests that there might be a synergistic interaction in learning several aspects of linguistic structure si-multaneously, as compared to learning each kind of linguistic ... shown in Figure 1. In this grammar and the grammars below, under-lining indicates an adapted nonterminal. Phonemeis a nonterminal that expands to each of the 50 dis-tinct phonemes present in ... grammar, in which the subtrees are speciﬁed in advance, in an adaptor grammar the subtrees, aswell as their probabilities, are learnt from the train-ing data. In order to make parsing and inferencetractable...

Tài liệu Báo cáo khoa học: "Using Smaller Constituents Rather Than Sentences in Active Learning for Japanese Dependency Parsing" docx

... sampling in this paper.Minimum Margin Selection (Min) Thismethod is to select sentences that contain bun-setsu pairs which have smaller margin valuesof outputs of the classiﬁer used in parsing. ... out in parsing. The differ-ence between AVG and MIN is that for AVG weuse∑|f(xk)|/l where l is the number of callingDep() in Figure 3 for the sentence siinstead ofmin |f (xk)| for MIN.5.2 ... selection for parsing. Weuse Japanese dependency parsing as a target task in this study since a simple and efﬁcient algorithmof parsing is proposed and, to our knowledge, ac-tive learning for Japanese...

Tài liệu Báo cáo khoa học: "Using Automatically Transcribed Dialogs to Learn User Models in a Spoken Dialog System" doc

... distributions in our model are multinomials. Hence θ is a vec-tor that parameterizes the user model according toPr(At= a | St= s, Ut= u; θ) = θasu.The problem we are interested in is estimating ... model was esti-mated by transcribing 50 randomly chosen dialogsfrom the training set in Section 4.2 and calculat-ing the frequency with which the ASR engine rec-ognized˜Atsuch that˜At= ... this way, we were able tocreate synthetic training sets of varying sizes, as wellas a test set of 1000 dialogs. Each generated dialogd in each training/test set consisted of a sequence ofvalues...

Tài liệu Báo cáo khoa học: "Mining metalinguistic activity in corpora to create lexical resources using Information Extraction techniques: the MOP system" doc

... Mining metalinguistic activity in corpora to create lexical resources using Information Extraction techniques: the MOP system Carlos Rodríguez Penagos Language Engineering Group, Engineering ... filtering. Our filtering strategies in effect distinguish between useful results such as (3) from non-metalinguistic instances like (4): (3) Since the shame that was elicited by the co-ding ... heterogeneous information, rather that a complete definition, are much more common. B) Introduction of metalinguistic information in discourse is highly regular, regardless of the spe-cific domain....

Tài liệu Báo cáo khoa học: "Discovering Global Patterns in Linguistic Networks through Spectral Analysis: A Case Study of the Consonant Inventories" pdf

... for discovering theglobal patterns in linguistic networks. These pat-terns, in turn, are then interpreted in the light of ex-isting linguistic theories to gather deeper insightsinto the nature ... This indicates that though3Binning is the process of dividing the entire range of avariable into smaller intervals and counting the number ofobservations within each bin or interval. In ﬁxed ... important linguistic typologies.The results obtained from the analysis of thethird eigenvectors of B and Bindicate that im-plicational universals also play a crucial role in determining linguistic...

Báo cáo khoa học: "Resolving Personal Names in Email Using Context Expansion" pot

... resolution. In structured data (e.g., databases),approaches have included minimizing the numberof “matching” and “merging” operations (Benjel-loun et al., 2006), using global relational informa-tion(Malin, ... impor-tant in resolving personal names (Reuther, 2006),and take into account global relational informa-tion. Similarly, approaches in unstructured data(e.g., text) have involved using clustering ... the Web to acquire information aboutindividuals mentioned in headers of an email col-lection. Our work is focused on resolving personalname references in the full email including the mes-sage...

Báo cáo khoa học: "Using Syntax to Disambiguate Explicit Discourse Connectives in Text" pot

... high baseline, with an f-score of75.33% and an accuracy of 85.86%. Interest-ingly, using only the syntactic features, ignoringthe identity of the connective, is even better, re-sulting in an ... improvement over those ob-tained by Marcu (2000) in his corpus-based ap-proach which achieves an f-score of 84.9%3foridentifying discourse connectives in text. Whilebearing in mind that the evaluations ... noleft sibling implies that the connective is the ﬁrstsubstring inside its Parent Category. In example(1a), this feature would be “NONE”, while in ex-ample (1b), the left sibling of and is...

Xem thêm