unsupervised preposition sense disambiguation

... supervised preposition sense disambiguation approach which explores different settings; Tratz and Hovy (2009), Hovy et al. (2010) make explicit use of the arguments for preposition sense disambiguation, ... include both preposition and argument senses. In this paper, we present our unsupervised framework and show results for preposition disam- biguation. We hope to present results for the joint disambiguation ... cru- cially depend on unsupervised techniques as the ones described here for textual enrichment. Our contributions are: • we present the first unsupervised preposition sense disambiguation (PSD)...

Ngày tải lên: 20/02/2014, 05:20

Ngày tải lên: 31/03/2014, 06:20

... the Concept Model are constructing the Spanish senses and then clustering the English and Spanish senses to build the concepts. Unsupervised Sense Disambiguation Using Bilingual Probabilistic Models Indrajit ... of find- ing sense- labeled training data, researchers have be- gun investigating unsupervised approaches to word- sense disambiguation. For example, the use of par- allel corpora for sense tagging ... France, July. David Yarowsky. 1993. One sense per collocation. In Proceedings, ARPA Human Language Tech- nology Workshop, Princeton. David Yarowsky. 1995. Unsupervised word sense disambiguation rivaling supervised...

Ngày tải lên: 08/03/2014, 04:22

Ngày tải lên: 23/03/2014, 14:20

... Machine- Learning of Word Sense Disambiguation. Natural Language Engineering, Special Issue on Word Sense Disambiguation Systems, 8:311–325. N. Ide, T. Erjavec, and D. Tufis¸. 2002. Sense discrimi- nation ... Evaluation To evaluate our five classifiers, we used the sense in- ventory and test set of the SemEval “Cross-Lingual Word Sense Disambiguation task. The sense inven- tory was built up on the basis of ... a word sense transla- tion table, in which look-ups are performed during the testing phase. This system also differs from the Uvt-WSD and ParaSense systems in the sense that the word senses are...

Ngày tải lên: 20/02/2014, 05:20

... words for every sense of the word in construction of the EP, rich semantic information can be acquired in the training step and is an advantage for sense disambiguation. 2) Senseval-3 has ... Word Sense Disambiguation Within a Multilingual Framework. PhD thesis, University of Maryland College Park. Mona Diab. 2004a. Relieving the Data Acquisition Bottleneck in Word Sense Disambiguation. ... has the same number of EPs as of senses. Each EP's sense maps to a sense of ambiguous word. The semantic equivalence demands further equivalence at each sense level. Every corre- 458 Proceedings...

Ngày tải lên: 20/02/2014, 12:20

... cre- ated, one each for the 10%, 50% and 100% Reuters subset. Lattice-Based Disambiguation. Our disambiguation method is Lattice-Based Disambiguation (LBD, (Atterer and Sch¨utze, 2006)). We form alize ... other dependencies also improve the accuracy of disambiguation (Atterer and Sch¨utze, 2006). For example, light verbs like make and have only provide disambiguation information when their objects ... the most likely attachment is chosen per preposition: 72.2% according to (Collins and Brooks, 1995). With the exception of (Hindle and Rooth, 1993), most unsupervised work on PP attach- ment is...

Ngày tải lên: 20/02/2014, 12:20

... describes SENSELEARNER – a minimally supervised word sense disam- biguation system that attempts to disam- biguate all content words in a text using WordNet senses. We evaluate the accu- racy of SENSELEARNER ... stan- dard sense- annotated data sets, and show that it compares favorably with the best re- sults reported during the recent SENSEVAL evaluations. 1 Introduction The task of word sense disambiguation ... of the SENSEVAL-2 and SENSEVAL-3 data sets), while the performance did not exceed the one obtained with the more general semantic models. The average disambiguation precision obtained with SENSELEARNER...

Ngày tải lên: 20/02/2014, 15:20

... with sense class 1 : training example with sense class 2 : test example with unknown sense class : test example with predicted sense first principal “ quasi-axis” class 2 (correct sense ... and Jessica Stevens. Supervised sense tagging using support vector machines. In Proceedings of Senseval-2, Sec- ond International Workshop on Evaluating Word Sense Disambiguation Systems, pages ... Richard Wicentowski. The Johns Hopkins SENSEVAL2 system descrip- tions. In Proceedings of Senseval-2, Sec- ond International Workshop on Evaluating Word Sense Disambiguation Systems, pages 163–166, Toulouse,...

Ngày tải lên: 20/02/2014, 16:20

... various methods for the 4 datasets. sense priors. To gauge how well the sense pri- ors are estimated, we measure the KL divergence between the true sense priors and the sense pri- ors estimated by using ... and Hwee Tou Ng. 2005a. Scaling up word sense disambiguation via parallel texts. In Proc. of AAAI05. Yee Seng Chan and Hwee Tou Ng. 2005b. Word sense disambiguation with distribution estimation. In ... from different domains may have different sense priors (the proportions of the different senses of a word). This in turn affects the accuracy of word sense disambiguation (WSD) sys- tems trained...

Ngày tải lên: 08/03/2014, 02:21

... lexical sample of SENSEVAL-2 1 shows that lexical cohe- sion based on edge-counting techniques is a good way of unsupervisedly disam- biguating senses. 1 Introduction Word Sense Disambiguation ... to Perform Word Sense Disambiguation. Sinopalnikova, A. (2004). Word Association Thesau- rus as a Resource for Building Wordnet. In GWC 2004. Sussna, M. (1993). Word Sense Disambiguation for ... Issue on Senseval: Evaluating Word Sense Disambiguation Programs. Computers and the Humanities 34(1-2): 1-13. Kilgarriff, A. and J. Rosenzweig (2000). Framework and Results for English Senseval....

Ngày tải lên: 08/03/2014, 02:21

... using English transla- tions as word senses would be ideal, they instead predicted the HowNet sense of a word and then used the English gloss of the HowNet sense as the WSD model’s predicted translation. ... gram- mar rule as its translation. Hence, unlike traditional WSD where the sense classes are tied to a specific sense inventory, our “senses” here consist of the En- glish phrases extracted as translations ... is that in resolving sense ambiguity, a WSD system will be able to help an MT system to determine the correct translation for an ambiguous word. To determine the correct sense of a word, WSD...

Ngày tải lên: 08/03/2014, 02:21

... simple, containing only the sentence identifier and the sense of the verb in that sentence, i.e. sense( snt, sense) : sense( snt 1 ,voltar). sense( snt 2 ,ir). … Based on the examples, background ... scenario, we use the sense tagged corpus and sense repositories provided for verbs in Senseval-3. There are 32 verbs with be- tween 40 and 398 examples each. The number of senses varies between ... monolingual task (Senseval-3 verbs with fine-grained sense distinctions and using the evaluation system provided by Senseval). It also shows the average accuracy of the most frequent sense and accuracies...

Ngày tải lên: 08/03/2014, 02:21

... of active learn- ing for word sense disambiguation. In Proc. of HLT/NAACL06. H. T. Dang. 2004. Investigations into the Role of Lex- ical Semantics in Word Sense Disambiguation. PhD dissertation, ... “oracle” which determines the predominant sense, or most frequent sense (MFS), of each noun in our WSJ test data perfectly, and we assign this most frequent sense to each noun in the test data, we ... we explore the issue of different sense priors across different domains. Using the sense priors estimated by expectation-maximization (EM), the predominant sense in the new domain is pre- dicted....

Ngày tải lên: 08/03/2014, 02:21

... Measure Context Target Sense Preprocessing Format Filter Sense Inventory Context Selection Postprocessing Pick Sense Figure 1: A generalized framework for Word Sense Disambiguation. modules ... a method of word sense disambiguation that com- putes the intended sense of a target word, using WordNet-based measures of seman- tic relatedness (Patwardhan et al., 2003). SenseRelate::TargetWord ... Arbor, June 2005. c 2005 Association for Computational Linguistics SenseRelate::TargetWord – A Generalized Framework for Word Sense Disambiguation Siddharth Patwardhan School of Computing University...

Ngày tải lên: 08/03/2014, 04:22

... ap- proach is unsupervised, we also report the results of other unsupervised systems on this test set. Accord- ingly, the last seven row entries in Table 1 present state-of-the-art SENSEVAL2 unsupervised ... Stevens. 2002. Supervised Sense Tagging using Support Vector Machines. Proceedings of the Second International Workshop on Evaluating Word Sense Disambiguation Systems (SENSEVAL-2). Toulouse, France. Scott ... and Martha Palmer, ed. 2001. SENSEVAL-2: Second International Workshop on Evaluating Word Sense Disambiguation Systems. ACL SIGLEX, Toulouse, France. Mona Diab. 2004. An Unsupervised Approach for...

Ngày tải lên: 08/03/2014, 04:22

... church could be the physical building sense (教 堂), or the institution sense ( 教会). In manual sense tagging done in SENSEVAL-2, it is possible to assign two sense tags to church in this case, but ... sample task of SENSEVAL-2. We rely on two sources to decide on the sense classes of w: (i) The sense definitions in WordNet 1.7, which lists seven senses for the noun channel. Two senses are ... of senses before and after sense lump- ing is 5.07 and 3.52 respectively. After sense lumping, we trained a WSD classi- fier for each noun w, by using the lumped senses in the manually sense- tagged...

Ngày tải lên: 08/03/2014, 04:22

Ngày tải lên: 08/03/2014, 04:22

Ngày tải lên: 08/03/2014, 06:20

Ngày tải lên: 08/03/2014, 07:20