Báo cáo khoa học: "A Generic Sentence Trimmer with CRFs" pot
... for sentence compres- 299 sion in Japanese. We will look at how the present approach compares with that of DPM in Section 6. 2 A Sentence Trimmer with CRFs Our idea on how to make CRFs comply with ... Linguistics A Generic Sentence Trimmer with CRFs Tadashi Nomoto National Institute of Japanese Literature 10-3, Midori Tachikawa Tokyo, 190-0014, Japan nomoto@acm.org Abstrac...
Ngày tải lên: 31/03/2014, 00:20
... inaccu- rate in these cases. We therefore eliminated such sentences from the test suite. From the remaining sentences we made a selection of 500 sentences of various lengths. The results are shown ... Note that super linear speedup is achieved with up to 12 processors, repeat- edly for the same set of sentences. Super lin- 5 Because the system was shared with other users, only 6 processor...
Ngày tải lên: 31/03/2014, 04:20
... it instead in conjunction with extra-sentential discourse processing. A possible problem for this approach can be seen in sentences where the anaphor is combined with another am- biguous ... while the subject NP in (14) need not be disjoint in reference with the underlined pronoun. Compare (13) with (10b) and (14) with (1 lb). (12) He likes Bill's pictures of John. They...
Ngày tải lên: 21/02/2014, 20:20
Báo cáo khoa học: "A Deductive Approach to Dependency Parsing∗" potx
... that an input sentence can be represented as a set of trees which are used as initial items (hypotheses) for the de- duction system. Thus, a sentence w 1 . . . w n produces a set of hypotheses {{w 1 (w 1 )}, ... each node is labelled with an element of Σ∪(Σ×N), and the following conditions hold: • All nodes labelled with marked terminals w i ∈ (Σ × N) are leaves, • Nodes labelled wit...
Ngày tải lên: 08/03/2014, 01:20
Báo cáo khoa học: "A Discriminative Language Model with Pseudo-Negative Samples" pptx
... perfor- mance with very few features. We then examined the effect of PKI. Table 3 shows the results of the classifier with rd order polynomial kernel both with and without PKI. In this experiment, only sentences ... correct and incorrect sentences and can therefore classify these sentences correctly. 2 Previous work Probabilistic language models (PLMs) estimate the probability of word st...
Ngày tải lên: 08/03/2014, 02:21
Báo cáo khoa học: "A Common Framework for Syntactic Annotation" pot
... themselves. Thus, in a document containing an actual annotation, several objects with the type argument may be instantiated, each with a different value. The RDF schema ensures that each instantiation ... can be used within a given annotation scheme, again using RDF schema. The DCS defines constraints on each category, including restrictions on the values they can take (e.g., "text...
Ngày tải lên: 08/03/2014, 05:20
Báo cáo khoa học: "A MODULAR APPROACH TO STORY GENERATION" potx
... rewarded, or where he is otherwise presented with the object, without having to carry out any directed action to acquire it. Elsewhere, it is potential redundancy which allows the safe deletion ... (Subject) on the city of Saragossa (Object, with Object category city), currently ruled by Thibaut (Source), in which he is helped by Charles (Auxiliary), with opposition from Clario...
Ngày tải lên: 09/03/2014, 01:20
Báo cáo khoa học: "A Sentiment Analyzer for Micro-blogs" potx
... because the system cannot find out which sentence/ parts of sentence is ex- pressing opinion about the target entity. 4.2.4 Coverage of Resources Tweet: I’m done with this bullshit. You’re the psycho not ... (Prelo- vac, 2010). A micro-blog allows users to exchange small elements of content such as short sentences, individual pages, or video links (Kaplan and Haen- lein, 2010). More about...
Ngày tải lên: 17/03/2014, 00:20
Báo cáo khoa học: "A SNoW based Supertagger with Application to NP Chunking" ppt
... word in a sentence is associated with an el- ementary tree, or a supertag (Joshi and Srinivas, 1994). Supertagging is the process of assigning the correct supertag to each word of an input sentence. The ... in the dataset. With POS tags we achieve an F-score of , but with supertags we only achieve an F-score of . This is not sur- prising becuase Srinivas’ supertag was only trained...
Ngày tải lên: 17/03/2014, 06:20
Báo cáo khoa học: "A LOGICAL VERSION OF FUNCTIONAL GRAMMAR" potx
... such that the labeling 93 symbols agree with the symbols labeling the positions of w, then w is compatible with A. This is our new way of dealing with free word order. Suppose that no precedence ... that subsurnption is a partial order on isomorphism classes of automata (without orderings), and that for any formula 4} without recursion or ordering, that there are a finite number...
Ngày tải lên: 17/03/2014, 20:20