Báo cáo khoa học: "Robust VPE detection using Automatically Parsed Text" pdf

... Robust VPE detection using Automatically Parsed Text Leif Arda Nielsen Department of Computer Science King’s College London nielsen@dcs.kcl.ac.uk Abstract This ... El- lipsis (VPE) detection system, built for robustness, accuracy and domain inde- pendence. The system is corpus-based, and uses machine learning techniques on free text that has been automatically parsed. ... Effec...

Ngày tải lên: 17/03/2014, 06:20

... 13 July 2010. c 2010 Association for Computational Linguistics Automatic Sanskrit Segmentizer Using Finite State Transducers Vipul Mittal Language Technologies Research Center, IIIT-H, Gachibowli, ... associ- ated with each of them. We followed two different approaches to segment a Sanskrit text using sandhi 1 rules extracted from a parallel corpus of manually sandhi split text. While th...

Ngày tải lên: 07/03/2014, 22:20

... Republic, June 2007. c 2007 Association for Computational Linguistics Detecting Erroneous Sentences using Automatically Mined Sequential Patterns Guihua Sun ∗ Xiaohua Liu Gao Cong Ming Zhou Chongqing ... build a machine learning model to automatically classify each sentence into one of the two classes, “erro- neous” and “correct.” To build the learning model, we automatically extract...

Ngày tải lên: 08/03/2014, 02:21

... task. Classification performance using Charniak parses is about 3% absolute worse than when using Tree- Bank parses. On the other hand, argument identifi- cation performance using Charniak parses is about 12.7% ... hypotheses using a trigram lan- guage model of the argument sequence. We analyze the performance on three tasks: • Argument Identification – This is the pro- cess of identifyi...

Ngày tải lên: 08/03/2014, 04:22

... by-product of the Concept Model is a semantic structure for the secondary language. This is automatically constructed using background knowledge of the structure for the primary language and the observed ... for each sense using the conditional probabilities of the words. As in Bengio and Kermorvant (2003), this generative procedure may be captured by factor- ing the joint distribution...

Ngày tải lên: 08/03/2014, 04:22

... One Microsoft Way Redmond, WA 98052 U.S.A. Abstract As a lexical knowledge base constructed automatically from the definitions and example sentences in two machine-readable dictionaries ... simply a modest subset. There have been many other attempts to process dictionary definitions using heuristic pattern matching (e.g., Chodorow et al. 1985), specially constructed definition...

Ngày tải lên: 17/03/2014, 07:20

... architecture using hierarchical task decomposition and an expectation agenda. For mod- eling dialog, the domain-specific dialog control is represented in the Dialog Task Specification layer using a ... possible nodes are generated using the discourse interpretation. Secondly, the multi-level score func- tions are computed for each candidate node c i given a hypothesis h i . Using the gr...

Ngày tải lên: 23/03/2014, 17:20

... ef- fect of training size on performance while using grammars automatically extracted from the Penn- II Treebank (Marcus et al., 1994) for generation. Using an automatically extracted XTAGgrammar, they ... discriminative disambiguation model using a hand-crafted HPSG grammar for generation. Belz (2005) describes a method for building statistical generation mod- els using an autom...

Ngày tải lên: 23/03/2014, 18:20

... on converting parser output for evaluation, e.g. Lin (1998) and Briscoe et al. (2002) proposed using underlying dependencies for evaluation. There has also been work on conver- sion to phrase ... from the CCG bottom- up, creating leaves with lexical schemas, then merg- ing/adding sub-trees using rule schemas at each step. The schemas for Figure 1 are shown in Table 1. These apply to creat...

Ngày tải lên: 19/02/2014, 19:20

... and method. • TRG: The models were trained using only the real-error corpus (baseline). • SRC: Trained using only the pseudo-error corpus. • ALL: Trained using the real-error and pseudo- error corpora ... the difficulty of collecting large error cor- pora. We tackle this problem by using pseudo- error sentences generated automatically. Fur- thermore, we apply domain adaptation, the ps...

Ngày tải lên: 19/02/2014, 19:20