Báo cáo khoa học: "Bootstrapping Coreference Resolution Using Word Associations" potx

... Manning. 2008. Enforcing transitivity in coreference resolution. In HLT ’08, pages 45–48. Aria Haghighi and Dan Klein. 2007. Unsupervised coreference resolution in a nonparametric bayesian model. ... Roukos. 2004. A Mention-Synchronous Coreference Resolution Algo- rithm Based on the Bell Tree. In ACL ’04, pages 135– 142. Xiaoqiang Luo. 2005. On coreference resolution perfor- ma...

Ngày tải lên: 07/03/2014, 22:20

... presented an unsupervised approach to coreference resolution, which mined the co-referring NP pairs with similar predicate- arguments from a large corpus using a bootstrapping method. However, ... apparent improvement for the overall pronoun resolution. Indeed, existing learning-based approaches to anaphor resolution have performed reasonably well using limited and shallow knowledge...

Ngày tải lên: 20/02/2014, 15:20

... commonly used to evalu- ate coreference systems on a within-document basis. Since our system relies on sampling, all results are averaged over five random runs. 3 Coreference Resolution Models In this ... approach to coreference reso- lution which models both global entity iden- tity across a corpus as well as the sequen- tial anaphoric structure within each docu- ment. While most exis...

Ngày tải lên: 08/03/2014, 02:21

... Spoken Dialogue Management Using Probabilistic Reasoning Nicholas Roy and Joelle Pineau and Sebastian Thrun Robotics Institute Carnegie ... Institute Carnegie Mellon University Pittsburgh, PA 15213 Abstract Spoken dialogue managers have benefited from using stochastic planners such as Markov Decision Processes (MDPs). How- ever, so far, MDPs do not ... rewards with rewards conditioned on o...

Ngày tải lên: 08/03/2014, 05:20

... Algorithm JTAG selects the correct sequence of words using connective-cost, the number of co- occurrences, the priority of words, and the length of words. The precise description of the algolithm ... added unregistered words to the dictionaries, changed the costs of registered words, and supplied the information of the co-occurrence of words. The changes in the costs of words caused...

Ngày tải lên: 08/03/2014, 05:21

... also introduce many word alignment errors. The example in Figure 1 shows the word align- ment of the given Chinese and English sentence pair, where the English words following each Chi- nese word is its ... learned based on word alignment. In this paper we introduce a confidence mea- sure for word alignment, which is robust to extra or missing words in the bilingual sentence pairs, a...

Ngày tải lên: 17/03/2014, 01:20

... number of words in the prediction window. We focus on 5 -word prediction windows. Many com- mercial devices provide optimized input for the most common words (called core vocabulary) and offer word ... word contributes to the relevance of the word. If a word was used somewhat recently, we would expect to see the word again. We follow Bellegarda (2000) in using an exponentially dec...

Ngày tải lên: 31/03/2014, 00:20

... learned decisions of the resolution classifier. Without path coreference knowledge, a resolution process would resolve the pronouns in (1) and (2) the same way. Indeed, coreference resolution research has ... Related Work Coreference resolution is generally conducted as a pairwise classification task, using various con- straints and preferences to determine whether two 33 expres...

Ngày tải lên: 20/02/2014, 11:21

... CRF models are trained using the alignment results as supervised data. 2.2 Insertion / Deletion Since an insertion can be regarded as replacing an empty word with an actual word, and deletion is ... output words (similar to the trans- lation models of PBSMT). The latter measure the fluency of the output word sequence (similar to lan- guage models). The mapping features are all binary. T...

Ngày tải lên: 19/02/2014, 19:20

... W is a set of word / part-of-speech pairs for all the words in WordNet. E is the set of edges connecting each pair of synonymous words. Nodes represent word/ pos pairs rather than words because ... WordNet with a 5- long sequence “good, sound, heavy, big, bad”. A given word w may be more connected to one set of words (e.g., positive words), yet have a shorter path connecting it to one w...

Ngày tải lên: 20/02/2014, 04:20