Báo cáo khoa học: "Discriminative Sentence Compression with Soft Syntactic Evidence" doc

... Discriminative Sentence Compression with Soft Syntactic Evidence Ryan McDonald Department of Computer and Information Science University ... possible compressions. Though this model is highly likely to return grammatical com- pressions, it required the training data be human annotated with syntactic trees. 3 Discriminative Sentence Compression For ... learning approach to s...

Ngày tải lên: 24/03/2014, 03:20

... aligned sentences and 484 word- aligned sentences. This data set was used for the 2003 NAACL shared task (Mihalcea and Ped- ersen, 2003), where the word-aligned sentences were split into a 37 sentence ... word alignments over a sentence- aligned bilingual cor- pus, and the second phase uses statistics over these predicted word alignments to decode (translate) novel sentences. This paper de...

Ngày tải lên: 20/02/2014, 11:21

... features – for example, syntactic features, as ex- plored in, e.g., Khudanpur and Wu (2000). We intend to explore methods with new features in the future. Ex- perimental results with n-gram models ... A. Stolcke and Weintraub (1998) experimented with various discriminative approaches including MMIE with mixed results. This work was followed up with some success by Stolcke et al. (...

Ngày tải lên: 23/03/2014, 19:20

... Perl. 23 ate He He:1:2-ate:2:0 ate meat ate:1:0-meat:2:1 ate with ate:1:0 -with: 2:1 meat the the:1:2-meat:2:0 with fork with: 1:0-fork:2:1 fork a a:1:2-fork:2:0 Figure 4: Examples of bigram-subtrees ate meat with ate:1:0-meat:2:1 -with: 3:1 ate with ... (Carreras, 2007). We call the parser with the monolingual features monolingual parser. 3.2 Parsing with bilingual features In...

Ngày tải lên: 16/03/2014, 23:20

... shows a well-formed dependency graph for an English sentence, where each word of the sentence is tagged with its part-of-speech and each arc labeled with a dependency type. 2.2 Parsing Algorithm We ... c 0 = (ǫ, (1, . . . , n), h 0 , d 0 ) with an empty stack, with all the token nodes in the input sequence, and with all token nodes attached to the special root node 0 with a spe...

Ngày tải lên: 23/03/2014, 18:20

... Word n-grams Entropy minimization Entropy minimization with clustering Entropy minimization with filtering Entropy minimization with filtering and clustering # 0 936 16271 1053 1029 ... of dialogues with dialogue 1150 acts, the rules are applied, in turn, to every ut- terance in the corpus, and each utterance that satisfies the conditions of a rule is relabeled with...

Ngày tải lên: 23/03/2014, 19:20

... the value of feature F; as usual in Prolog, symbols starting with a lower-case letter are con- stants, while symbols starting with an upper-case letter are variables. Focus and mention vectors ... problem of updating mention ratios by unification, without resorting to statements like Df is Di + 1. This can be done by replacing numbers with lists of the appropriate length, so that...

Ngày tải lên: 24/03/2014, 03:20

... binary classification simply deals with the is/is-not relationship and will have difficulty when two responses with similar feature values are clas- sified differently. With preference ranking, viola- tions ... appropriate candidates. 4 Experiments To compare with the prior approach of Pinchak and Lin (2006), we use a set of what and which questions with question focus (questions with...

Ngày tải lên: 08/03/2014, 21:20

... on the syntactic informa- tion of a single sentence. Similar phenomena also happen in English noun predicates, in which ar- guments of noun predicates sometimes do not ex- ist in the sentence ... The input to the analyzer is an article (multiple sentences) because our target is to identify arguments spread across sentences. 1. First, each sentence is individually analyzed and segmented...

Ngày tải lên: 23/03/2014, 17:20

... word-aligned to sentence- aligned data 500 sentence pairs 2000 sentence pairs 8000 sentence pairs 16000 sentence pairs Figure 4: The effect on Bleu of varying the ratio of word-aligned to sentence- aligned ... sentence- aligned data 500 sentence pairs 2000 sentence pairs 8000 sentence pairs 16000 sentence pairs Figure 3: The effect on AER of varying the ratio of word-aligne...

Ngày tải lên: 31/03/2014, 03:20