... triple consisting of the event type ofthe utterance, the relationword, and the event type ofthe precedingutterance.– add the candidate triple to the BKB, if itfound in the BKB, increase ... automaticallyparsed corpora. While the relation word is usuallypart ofthe utterance that represents the source of the relation, determining the appropriate target (an-tecedent) ofthe relation may be difficult ... where the factual target ofthe rela-tion was non-adjacent) are equally distributed, theyshould be filtered out by the significance tests. The goal of this paper is to evaluate the validity of this...
... among E, R and S, but rather by successively taking account ofthe meanings ofthe nested pres, futr and perf operators in the LF ofthe sentence. As it happens, each of those operators implicitly ... tree nodes. The traver- sal of trees and the addition of new tokens is simply and fully determined by the logical forms ofthe sentences being interpreted. The major advantage of tense trees ... e5], i.e., the breaking ofthe ankle, e6, is before the state John is in at the time ofthe doctor's talking to him, e4. In addition, the recursive rules take correct account of embedding....
... paper, we study the utility ofthe dis-course structure on the user side of a dialogue sys-tem. One related study is that of (Rich and Sidner, 1998). Similar to the NM, they use thediscourse structure ... de-scribe the motion ofthe person and his keys while heis holding them. Then we will look at the motion of the person and his keys after he lets go of them. Let's begin by looking at the ... perception ofthe system. We find that the NM presence significantly improves user’s perception of the system in terms of their ability to concen-trate on the instruction (Q3), in terms of their...
... substituted for another whilepreserving the meaning of a text. Knott (1996)studies the substitutability ofdiscourse connectives,and proposes that substitutability can motivate the- ories ofdiscourse ... q(x) = 0.these results demonstrate a three way correspon-dence between the human ratings ofthe similar-ity of a pair of connectives, their substitutabil-ity relationship, and their distributional ... The task was then to decide automatically which of q andqis the SYNONYM of p. The second task was identical in nature to the first,however here the relationship between p and q waseither SYNONYMY...
... expected ofthe user, the inferential machinery can derive the appropriate intention behind the use of a noun phrase fragment. The theory should account for 48% ofthe 32 DEPENDENCIES OFDISCOURSE ... Frequency of Request types Since most of each dialogue consisted ofthe making of requests, the first analysis examined the frequency ofthe various kinds of requests in the corpus of five ... from those behind the uttering of " ;the smallest ofthe red pieces?", where the hearer is expected to physically identify the piece. According to the theory, the speaker ' s...
... verb, thensubtype := med/situation15. if the head ofthe NP and one ofthe preceding verbs in the same sentence share the same WordNethypernym which is not in synsets that appear one ofthe ... approximations ofthe definitions of the corresponding subtypes, the med rules are morecomplicated than their old counterparts, in partbecause of their reliance on the extraction of so-phisticated ... cap-ture a crucial aspect ofthe ruleset: the ordering of the rules. For instance, Rule i should be appliedonly if the conditions ofthe first i−1 rules are notsatisfied by the NP, but such ordering...
... about 12% of sentences do not contain the discourse marker they are supposed to. Of thediscourse markers used in the experiments,their frequencies in the database ranged from 270for the instant ... level of judgement wastherefore exercised by the author.parser errors, and the fact that the syntactic heuris-tics are not foolproof, the database contains noise.Manual analysis of a sample of ... between occurrences of then in the antecedent(subordinate) and consequent (main) clauses linkedby if.We also recorded the presence of other discourse markers in the two clauses, as these had previously3For...
... retrieved by way of their corresponding node(s) in the syntax; the oper- ations performed on these representations are dictated by the nature ofthe constraints imposed. The two types of inference ... with in the treatment of VP-eUipsis, perhaps at the cost of some degree of the- oretical inelegance. However, this aspect was crucial for handling the gapping data, since the infelicity of gapping ... refused to ] The current approach accounts for these cases. The works of Priist (1992) and Asher (1993) pro- vide analyses of VP-ellipsis 16 in the context of an account ofdiscourse structure...
... parses on the basis of the discourse information If the partial parses are not unified into a single structure in the previous step, they are joined to- gether on the basis ofthediscourse ... parses with the application of our method, the heuristic rules were applied. In such cases the default rule of joining the root node of the second partial parse to the last node ofthe first ... for the extra TAT required as a result of using thediscourse information, provided the size ofthediscourse was kept to between 100 and 300 sentences. In this paper, the term " ;discourse& quot;...
... layouts, there is a minority strategy, used by 4% ofthe speakers (3 out of 72 cases of the data of Linde (1974)) describing the layout in the form of a map. The speaker first describes the outside ... delete, or move nodes of the tree. The sequence of transformations encodes the construction ofthediscourse as it actually proceeds in time. We now turn to a discussion ofthediscourse units which ... thediscourse level. In order =o demonstrate that at leas= some ofthe structure found at thediscourse level is independent of the structure ofthe semantic domain, we may show that there...
... ofthe dependency tree is directly dependent on another word if and only if there is a single line between the node ofthe first word and that ofthe second. For our purpose the strength of ... case the value of our transitive dependency model is deter- mined by the validity ofthe output ofthe coherent discourse generator in terms of its input. If we have uncovered some ofthe mechanisms ... morphemes.) The rules of dependency are as follows: 1. The head ofthe main verb phrase of a sentence or clause is dependent upon the head ofthe subject. 2. The head of a direct object phrase...
... parts: the topic and the controlling idea.- The topic sentence is the subject ofthe paragraph.Eg: The color yellow is the color of mental activity. The topic: the color yellow- The controlling ... structure, the sub-title, and thediscourseofthe news story.From which, I would like to draw some difficulties of Vietnamese readers when they translate the news story.To sum up, the scope ofthe ... write the thesis. This part includes the aims, scopes, methods and design ofthe study.Part B is the main part ofthe study that consists of three chapters below• Chapter I focuses on the theories...
... wake at 6 a.m., but nap for two hours or so in the early afternoon. Thus the influence on one's sleep pattern is worthy of consideration when choosing an occupation....
... men maintain approximately the same number of hours of unpaid work as in childless households, but the number of hours women work in the home rises to 52 per week, much of it, on doubt, due to ... responsibilities. Interestingly, when there are three or more children in the household, men are found to work even fewer hours around the house than before the appearance ofthe third child. Whereas women's ... rise to approximately 56 per week, the corresponding figure for men, 16, actually represents a decrease. The data suggest that the increased presence of women in the paid work force has yet to...