72074 T¨ubingen, Germany kouchnir@sfs.uni-tuebingen.de Abstract This paper presents a novel ensemble learning approach to resolving German pronouns. Boosting, the method in question, combines the moderately ac- curate hypotheses of several classifiers to form a highly accurate one. Expe[r]
2.2 Translingual projection We implement a novel cross-language approach for Arabic coreference resolution by expanding the space of exact match comparisons to approxi- mate matches of English translations of the Arabic strings. The intuition for this approach is that o[r]
Richardson, TX 75083-0688 { altaf,vince } @hlt.utdallas.edu Abstract While world knowledge has been shown to improve learning-based coreference resolvers, the improvements were typically obtained by incorporating world knowledge into a fairly weak baseline resolver. Hence, it is[r]
resolved (called active mention henceforth) is linked to an appropriate entity chain (if any), based on clas- sification results. One problem that arises with the entity-mention model is how to represent the knowledge related to an entity. In a document, an entity may have more than one mention.[r]
4 Conclusion In this paper we have investigated the effects of using semantic role information within a ma- chine learning based coreference resolution sys- tem. Empirical results show that coreference res- olution can benefit from SRL. The analysis of the relevance of[r]
Asthma and allergies prevalence increased in recent decades, being a serious global health problem. They are complex diseases with strong contextual influence, so that the use of advanced machine learning tools such as genetic programming could be important for the understanding the causal mechanism[r]
applies discriminative learning methods to pairs of mentions, using features which encode properties such as distance, syntactic environment, and so on (Soon et al., 2001; Ng and Cardie, 2002). Although such approaches have been successful, they have several liabilities. First, rich features[r]
Despite the existence of several noun phrase coref- erence resolution data sets as well as several for- mal evaluations on the task, it remains frustratingly difficult to compare results across different corefer- ence resolution systems. This is due to the high cost of implement[r]
Considering this, we encoded all source video sequences (SRC) with a fixed quantization parameter QP using the H.264/AVC video codec, x264 implementation. Prior to encoding, we applied some modifications involving resolution change and crop in order to obtain diverse aspect ratios between car p[r]
6 Conclusion We have presented an approach to detecting non- referential pronouns in text based on the distribu- tion of the pronoun’s context. The approach is sim- ple to implement, attains state-of-the-art results, and should be easily ported to other languages. Our tech- nique demonstrates how[r]
Single-particle analysis of electron cryo-microscopy (cryo-EM) is a key technology for elucidation of macromolecular structures. Recent technical advances in hardware and software developments significantly enhanced the resolution of cryo-EM density maps and broadened the applicability and the circl[r]
Table 4: Results for the coreference resolution Compared with the gains in pronoun resolution, the improvement in non-pronoun resolution is slight. As shown in Table 3, our approach resolves non-pronominal anaphors with the recall of 51.3 (39.7) and the prec[r]
Maximum Metric Score Training In Chapter 1 and Chapter 2, we have shown that most prior work on coreference resolution recasts the task as a two-class classification problem and applies machine learning-based classifiers to determine whether a candidate anaphor and a[r]
Tan, Coreference resolution using competition learning approach, in: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1, ACL ’03, Association [r]
Selection rules are applied to the exist- ing MRs to find out whether the current RE may or may not refer to the object represented by the MR. As our implementation deals with unrestricted texts, only very basic selection rules are used; there are two agre[r]