Báo cáo khoa học: "Learning PP attachment for filtering prosodic phrasing" potx

... isolated learn- ing of PP attachment in Dutch, and on using predicted PP attachment information for filtering out incorrect placements of prosodic boundaries. First, PP attachment was learned ... (40%) with a verb-attached PP and 606 phrases (60%) with a noun-attached PP. Additionally, as held-out corpus for testing the efficacy of PP attachment information for...

Ngày tải lên: 24/03/2014, 03:20

... Y. Ng, and Christopher Potts Stanford University Stanford, CA 94305 [amaas, rdaly, ptpham, yuze, ang, cgpotts]@stanford.edu Abstract Unsupervised vector-based approaches to se- mantics can model ... per- formance to other approaches, and performed best when concatenated with bag of words representa- tion. Again the variant of our model which utilized extra unlabeled data during training perfo...

Ngày tải lên: 20/02/2014, 04:20

... To assess the performance of the approach the model produced for each verb was tested on the corresponding set of test cases by applying the rules in a decision-list like approach, i.e., retaining ... context. For example, among the possible senses of the verb “run” are “to move fast by using one's feet” and “to direct or control”. WSD can be useful for many applications, in...

Ngày tải lên: 08/03/2014, 02:21

... words. The baseline performance achieved by always guessing the majority class is 67.09% for break index, 54.10% for pitch accent, 66.23% for phrase accent and 79.37% for boundary tone based ... parameters. Applying RIPPER to the simple model yielded rules that signifi- cantly improved performance over the baseline models. For example, the accuracy of the rules learned for b...

Ngày tải lên: 08/03/2014, 05:21

... a new for- mulation of the PP attachment problem. We treat PP attachment as a 4-way classification of PPs into noun argument PPs, noun adjunct PPs, verb argu- ment PPs, and verb adjunct PPs. We ... contains data encoding information for attachment of single PPs in the form of four head words (verb, object noun, preposition and PP- internal noun) for each instance of PP atta...

Ngày tải lên: 08/03/2014, 21:20

... 1(a). smallest the is what state by area QUERY → answer(x 1 ,FORM) FORM → smallest(x 2 ,(FORM,FORM)) FORM → state(x 1 ) FORM → area(x 1 ,x 2 ) Figure 4: Word alignment for the sentence pair in Figure 1(a). extracted for the smallest predicate ... that appear in β ′ and outside the current MR sub-parse. For example, see the rule 962 FORM → state , λx 1 .state(x 1 ) FORM → by area , λx...

Ngày tải lên: 17/03/2014, 04:20

... counterpart. For example, compare affect and effect: [ subj Auto prices] [ arg−ext greatly] [ pred affect] [ obj the PPI]. [ subj Auto prices] have a [ arg−ext big] [ pred effect] [ obj on the PPI]. The ... (Ando and Zhang, 2005a) that by performing one round of minimiza- tion, an approximate solution of Θ can be obtained from (4) by the following algorithm: 1. For each of the m auxiliary...

Ngày tải lên: 23/03/2014, 18:20

... can be transformed to fine grained word senses using simple heuristics, and applying the technique for recent SENSEVAL data sets shows that our approach can yield state of the art perfor- mance. 1 ... learning needs train- ing data created for each and every polysemous word; Ng (1997) estimates an effort of 16 person- years for acquiring training data for 3,200 significant words in Engl...

Ngày tải lên: 31/03/2014, 03:20

... linguists), should not only supply a set of primitives which are appropriate for the application domain but should also contain within themselves sufficient apparatus to enable the user to ... all the infor- mation necessary for mapping - 186- instances of verbs with vp or pp complements to a situation schema (Fenstad, Halvorsen, Langholm and van Benthem, 1987). Here, for...

Ngày tải lên: 22/02/2014, 10:20

... consid- erable debate about the best way of representing this information. 2 GENERATION Suppose we have the formula given above as a for- mal paraphrase of (1), and we want to generate an English ... of some application program is for it to of- fer suggestions about how it is going to build the text, along with explanations of why it is going to build it that way. We therefore su...

Ngày tải lên: 22/02/2014, 10:20