Software Product Line Engineering (SPLE) supports developing and managing families of similar software products, termed Software Product Lines (SPLs). An essential SPLE activity is variability modeling which aims at r...
详细信息
Software Product Line Engineering (SPLE) supports developing and managing families of similar software products, termed Software Product Lines (SPLs). An essential SPLE activity is variability modeling which aims at repre-senting the differences among the SPL's members. This is commonly done with feature diagrams - graph structures specifying the user visible characteristics of SPL's members and the dependencies among them. Despite the attention that feature diagrams attract, the identification of features and structuring them into feature diagrams remain challenging. In this study, we utilized naturallanguageprocessing (NLP) techniques in order to explore dif-ferent patterns for identifying and structuring features from textual descriptions. Such a catalog of patterns is important for both manually-created and automati-cally-generated feature diagrams.
We present a survey of tagging accuracies - concerning part-of-speech and full morphological tagging - for several taggers based on a corpus for medieval church Latin (see ***). The best tagger in our sample, Lapos, h...
详细信息
language resources are an essential component of any naturallanguageprocessing system and such systems can only be applied to new languages and domains if appropriate resources can be found. Currently the task of fi...
详细信息
How humans acquire language, and in particular two or more different languages with the same neural computing substrate, is still an open issue. To address this issue we suggest to build models that are able to proces...
详细信息
Compositional embedding models build a representation (or embedding) for a linguistic structure based on its component word embeddings. We propose a Feature-rich Compositional Embedding Model (fcm) for relation extrac...
详细信息
作者：
Lo, Chi-KiuDowling, Philipp C.Wu, DekaiNRC-CNRC
Multilingual Text Processing National Research Council Canada 1200 Montreal Road OttawaONK1A 0R6 Canada Tum
Fakultät für Informatik Technische Universität München Boltzmannstraße 3 Garching bei München85748 Germany Hkust
Human Language Technology Center Hk University of Science and Technology Clear Water Bay Kowloon Hong Kong
We show that, consistent with MEANTtuned systems that translate into Chinese, MEANT-tuned MT systems that translate into English also outperforms BLEUtuned systems across commonly used MT evaluation metrics, even in B...
详细信息
This paper concerns a logical approach to naturallanguage parsing based on proof nets (PNs), i.e. de-sequentialized proofs, of linear logic (LL). In particular, it presents a simple and intuitive syntax for PNs of th...
详细信息
ISBN:
(数字)9783662477090
ISBN:
(纸本)9783662477090;9783662477083
This paper concerns a logical approach to naturallanguage parsing based on proof nets (PNs), i.e. de-sequentialized proofs, of linear logic (LL). In particular, it presents a simple and intuitive syntax for PNs of the cyclic multiplicative fragment of linear logic (CyMLL). The proposed correctness criterion for CyMLL PNs can be considered as the non-commutative counterpart of the famous Danos-Regnier (DR) criterion for PNs of the pure multiplicative fragment (MLL) of LL. The main intuition relies on the fact that any DR-switching (i.e. any correction or test graph for a given PN) can be naturally viewed as a seaweed, i.e. a rootless planar tree inducing a cyclic order on the conclusions of the given PN. Dislike the most part of current syntaxes for non-commutative PNs, our syntax allows a sequentialization for the full class of CyMLL PNs, without requiring these latter must be cut-free. Moreover, we give a simple characterization of CyMLL PNs for Lambek Calculus and thus a geometrical (non inductive) way to parse phrases or sentences by means of Lambek PNs.
While parallel corpora are an indispensable resource for data-driven multilingual naturallanguageprocessing tasks such as machine translation, they are limited in quantity, quality and coverage. As a result, learnin...
详细信息
ISBN:
(纸本)9781577357384
While parallel corpora are an indispensable resource for data-driven multilingual naturallanguageprocessing tasks such as machine translation, they are limited in quantity, quality and coverage. As a result, learning translation models from non-parallel corpora has become increasingly important nowadays, especially for low-resource languages. In this work, we propose a joint model for iteratively learning parallel lexicons and phrases from non-parallel corpora. The model is trained using a Viterbi EM algorithm that alternates between constructing parallel phrases using lexicons and updating lexicons based on the constructed parallel phrases. Experiments on Chinese-English datasets show that our approach learns better parallel lexicons and phrases and improves translation performance significantly.
The proceedings contain 8 papers. The topics discussed include: a new parametric estimation method for graph-based clustering;extracting signed social networks from text;using link analysis to discover interesting mes...
ISBN:
(纸本)9781937284374
The proceedings contain 8 papers. The topics discussed include: a new parametric estimation method for graph-based clustering;extracting signed social networks from text;using link analysis to discover interesting messages spread across twitter;graphbased similarity measures for synonym extraction from parsed text;semantic relatedness for biomedical word sense disambiguation;identifying untyped relation mentions in a corpus given an ontology;cause-effect relation learning;and bringing the associative ability to social tag recommendation.
Guinaudeau and Strube (2013) introduce a graphbased model to compute local entity coherence. We propose a computationally efficient normalization method for these graphs and then evaluate it on three tasks: sentence ...
详细信息
暂无评论