Báo cáo khoa học: "Improving the Interpretation of Noun Phrases with Cross-linguistic Information" doc

... of the prepo-sitions (especially of/ de) to the semantic classes addsto the complexity of the interpretation task. Thus,for the interpretation of these constructions a systemmust rely on the ... 85% of the cases (again, with the exception of Romanian – 50%). It is interesting to note here thatsome of the English NPs are translated into both noun noun and noun adjective compounds in the target ... seman-tic relations. For example, the departure of the girl.d. Inherently passive nouns such as the cap-ture of the soldier. These nouns, like the verbs theyare derived from, assume a default...

Báo cáo khoa học: "Improving Parsing and PP attachment Performance with Sense Information" doc

... pizza with anchovies, the PP with anchovies could attacheither to the verb (c.f. ate with anchovies) or to the noun (c.f. pizza with anchovies), of which the noun is the correct attachment site. With ... interpretation of this result is that the approach of annotating all occurrences of the same word with the same sense allows the model to avoid the datasparseness associated with the gold-standard distinc-tions, ... have shown that the Bikel parser performs aswell as the state -of -the- art in PP attachment, whichsuggests our method improves over the current state- of -the- art. The fact that the improvement...

Tài liệu Báo cáo khoa học: "Improving the Scalability of Semi-Markov Conditional Random Fields for Named Entity Recognition" pdf

... compared the result of the recog-nizers with and without ﬁltering using only 2000sentences as the training data. Table 5 shows the result of the total system with different ﬁlteringthresholds. The ... 10). The results of McNemar’s test suggestthat the system with chunk features is signiﬁcantlybetter than the system without it (the p-value isless than 1.0 < 10−4). The result of the precedingentity ... type of non-local information, i.e. the label of the preceding entity, the model can be solvedwithout approximation.4 Reduction of Training/Inference Cost The straightforward implementation of...

Báo cáo khoa học: "Improving the Use of Pseudo-Words for Evaluating Selectional Preferences" docx

... a noun- noun similarity score,Seen(vd) is the set of seen head words ﬁlling the slot vdduring training, and C(vd, n) is the num-ber of times the noun n was seen ﬁlling the slot vd The ... co-occurrence count with the verb is cho-sen. As with the other models, if the two nounshave the same counts, it randomly guesses. The smoothing model is named Erk in the re-sults with both Jaccard ... which of two verbswas the correct predicate for a given noun object.One verb v was the original from the source doc- ument, and the other vwas randomly generated.This was the ﬁrst use of such...

Báo cáo khoa học: "Improving the Accuracy of Subcategorizations Acquired from Corpora" pdf

... lexicon of the tar-get grammar,4and make use of the existing sets of 4When the lexicon is less accurate, I can determine the number of clusters using other algorithms (Hamerly, 2003).SCFs for the ... cm. I then initialize the num-ber of clusters k to the number of cm.I ﬁnally update the acquired SCFs using the ob-tained clusters and the conﬁdence values of SCFsin this order. I call the ... how often words derivablefrom the word stem appeared with the SCF type in the training corpus. The obtained SCFs comprise the total 163 SCF types which are originally basedon the SCFs in the...

Báo cáo khoa học: "Signalling the Interpretation of Indirect Speech Acts" pptx

... force(s) of an utterance. The goal of such a theory is to formalize the set of possible plans underlying the use of particular speech acts Co achieve a given set of goals. In light of the independent ... pass the salt. The remainder of this paper attempts to illustrate the kinds of predictlons made by the theory,.and the use of anaphora to support one such prediction." Consider the following ... independent of the use of language, but is the source of much conversational coherence. A plan based theory of speech acts specifies that plan recognition is the basis for inferring the illocuCionary...

Báo cáo khoa học: "Improving the Performance of the Random Walk Model for Answering Complex Questions" pptx

... cases where the query is composed of two or more sentences, wecompute the similarity between the document sen-tence (s) and each of the query-sentences (qi) thenwe take the average of the scores.3 ... between The hero killed the villain” and The villain killed the hero”. The task like answering complex questionsthat requires the use of more complex syntactic andsemantics, the approaches with ... represents the occurrencefrequency (TF*IDF) of a word. However, the majorlimitation of the TF*IDF approach is that it only re-tains the frequency of the words and does not takeinto account the sequence,...

Báo cáo khoa học: "Comparing the Accuracy of CCG and Penn Treebank Parsers" docx

... number of sentencesin the sample, and the % column gives the samplesize as a percentage of the whole section.We compare the CCG parser to the Berkeleyparser using the accurate mode of the Berke-ley ... underestimated, when the evaluation frame-work is such that incremental improvements of afew tenths of a percent are routinely presented asimproving the state -of -the- art, as is the case with the Parseval ... parser, together with the model supplied with the publicly available version. Table 3 gives the results for Section 23, comparing the CCG andBerkeley parsers. The projected columns give the projected...

Báo cáo khoa học: "ON THE INDEPENDENCE OF DISCOURSE STRUCTURE AND SEMANTIC DOMAIN" docx

... layouts, there is a minority strategy, used by 4% of the 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 ... breadth first traversal with the root being the outside shape, the internal divisions the next layer of nodes, and the names of these divisions the terminal nodes. Because there are so few example, ... tour of the apartment, building up the description of the layout by successive mention of each room and its position. This tour forms a tree composed of the entry to the apartment as root with...

Báo cáo khoa học: "Assessing the Effect of Inconsistent Assessors on Summarization Evaluation" doc

... too.2Therefore, it would be better to look at whether as-sessors tend to ﬁnd the same SCUs (information“nuggets”) in different summaries on the same topic,and whether they annotate them consistently. ... manually-annotatedsummaries from the same topic, and then we com-pared the resulting “autoPyramid” score with the score from the original manual annotation for thatsummary. Ideally, the autoPyramid score ... If the autoPyramid score is higher than the manual Pyramid score, it means that either (1) the assessor missed relevant strings in this summary,but found them in other summaries; or (2) the...

Xem thêm