... First, zero- anaphora resolution is studied in the con-text of anaphora resolution (AR), in which zero- anaphora is regarded as a subclass of anaphora. In AR, the research trend has been shifting ... analyzing japaneseanaphora integrating zero pronoun detection and resolution. In Proceedings of the19th COLING, pages 911–917.W. M. Soon, H. T. Ng, and D. C. Y. Lim. 2001. A ma-chine learning approach ... of learn-ing non-anaphoric zero- pronouns (181 instances)as negative training instances in intra-sententialanaphoricity determination, which enables it to re-ject non-anaphoric zero- pronouns...
... < 1.3 mg/dL into those with normal and pseudo-normal renal function, resulting in the corresponding serum concentrations of digoxin. Key words: Cystatin C, Creatinine, Digoxin, Serum concentration, ... range, necessitating the routine monitoring of its serum concentration to maximize the therapeutic effects and minimize toxicities [16-19]. Since digoxin is mainly eliminated via the kidneys, ... digoxin inJapanese patients. The serum levels of Cys-C and Cr in the patients were higher than those in the healthy elderly subjects, but the increase of Cys-C was more predominant in the...
... (1987) "Economy inJapanese scientific terminology." Terminology and Knowledge Engineering '87. p. 123-136. [12] Japanese Ministry of Education (1986) Japanese Scientific ... phemes in terminology on the basis of a small sample. 1 Introduction In computational linguistics, the interest in ter- minological applications such as automatic term extraction is growing, ... morphemes show interesting characteristics in each domain. Firstly, in computer science, at the relatively early stage of terminological growth (i.e. N -~ 3500), the borrowed morphemes begin to take...
... descrlptlonal anaphora (both definite and indefinite, in Eeneric as well as in non-Eenerlc sentences) we have To pack more information into discourse referents than in standard DRT. In addition, ... and plurality, in: Studies in Modeltheoretlc Semantics, tem Meulen, A.G.B., ed., PP. 85-i06, Foris, Dordrecht/Cinnaminson, 1983 Evans 1980: Evans, G., Pmonouns, in: Linsuistic Inquiry, 11, ... Hirst, G., Anaphorain Natural LanEuaEe UnderstandinE, Lecture Notes in Computer Science 119, SprinEer-VerlaE, Berlin/HeidelberE/New York, 1981 Johnson 1985: Johnson, M and Klein, E., A...
... lead-ing to a renewed interest inzeroanaphora resolu-tion, particularly at the light of the mediocre resultsobtained on zero anaphors by most systems partici-pating in SEMEVAL. Resolving zero ... joint inference1As shown in Table 1, 64.3% of anaphors in the NAIST TextCorpus of Anaphora are zeros.804inter-sentential cases, induced from the remainingtraining instances.To estimate the ... (2009), useful features in intra-sentential zero- anaphora are different from ones in inter-sentential zero- anaphora because in the former problem syn-tactic information between a zero pronoun and...
... impor-tant inresolving personal names (Reuther, 2006),and take into account global relational informa-tion. Similarly, approaches in unstructured data(e.g., text) have involved using clustering ... 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, ... 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...
... only in the first word. Bothcontain a particle to, which is one of the most fre-quent coordination markers inJapanese but onlythe first sentence contains a coordinate structure.Pattern matching ... points improvement over theoriginal SH in terms of F1 measure in coordinationscope detection. Adding bypasses to alignmentgraphs further improved the performance, makinga total of +4.7 points ... listedabove are concerned mainly with scope disam-biguation, reflecting the fact that detecting thepresence of coordinations in a sentence (Task 1)is straightforward in English. Indeed, nearly 100%precision...
... turing the semantic distinctions involved in interper- sonal meanings is allowing us to apply to interper- sonal knowledge the technique that was adopted for ideational meanings of determining ... really to determine whether the inquiry framework is going to provide the took necessary for capturing the kind of meaning this in- volves. If the inquiry framework can be used in thk area also, ... constructing an inquiry proceeds first by means of suc- cees|ve approximations in informal terms, glossed in English, followed by an encoding of the understanding achieved of the semantic distinction...
... fourth line in Table 6 shows the accuracyobtained when a chunking model without transfor-mation rules was used.The accuracy obtained by using the chunkingmodel was one point higher in F-measure ... POStagging was 94 points in F-measure (Uchimoto etal., 2002). That is much lower than the accuracy ob-tained by manual tagging. Several problems led tothis inaccuracy. In the following, we ... accuracy.Considering the results obtained in this sectionand in Section 4.2.1, we are now detecting short andlong word segments and their POS categories in thewhole corpus by using the following steps:1....
... common in Spanish, as can be seen in this figure (49%).This fact represents one of the main difficultiesfound inresolvinganaphorain Spanish: thestructure of a sentence is more flexible than in English. ... resolved in the followingmodule of anaphora resolution. Person andnumber information is obtained from the clauseverb. Sometimes in Spanish, gender informationof the pronoun can be obtained ... syntactic information. In Ferrández et al. (1998), a partial parsing strategythat provides all the necessary information for resolving anaphora is presented. That studyshows that only the following...
... "On Inversion in Spanish and Some of Its Effects", I, inguistic Inquiry 15, 103-130. WAHL, 1987: :I Aoun; N Hornstein; D Lightfoot; A Wein- berg: "Two types of locality" Linguistic ... languages in which S is a bounding node, such as English, and for languages which have S-bar as bounding node. The difference in boundedness will be expressed in the lexicon and the bindings will ... level anaphora. In MiMo, anaphoric rela- tions are defined by a separate type of rule. This enables linguists to define anaphoric relations in a declarative and modular way. It appeared that linguistic...