Filters








205,104 Hits in 2.4 sec

Experiments with Sentence Classification

Yuval Marom, Anthony Khoo, David W. Albrecht
2006 Australasian Language Technology Association Workshop  
We present a set of experiments involving sentence classification, addressing issues of representation and feature selection, and we compare our findings with similar results from work on the more general  ...  Our investigations compare the use of various popular classification algorithms with various popular feature selection methods.  ...  Experiments with representation Before looking at feature selection, we investigate different techniques for extracting features from sentences.  ... 
dblp:conf/acl-alta/MaromKA06 fatcat:qlypz322i5c7hdf3h2sunydahy

Experiments with Clustering-based Features for Sentence Classification in Medical Publications: Macquarie Test's participation in the ALTA 2012 shared task

Diego Mollá
2012 Australasian Language Technology Association Workshop  
In our contribution to the ALTA 2012 shared task we experimented with the use of cluster-based features for sentence classification.  ...  In a first stage we cluster the documents according to the distribution of sentence labels. We then use this information as a feature in standard classifiers.  ...  Results For the initial experiments we used NLTK's Naive Bayes classifiers. We experimented with the following features: p Sentence position in the abstract. np Normalised sentence position.  ... 
dblp:conf/acl-alta/Molla12 fatcat:nxrviz5bbfcc7h4fxre3hegbpq

Classification of Multiple-Sentence Questions [chapter]

Akihiro Tamura, Hiroya Takamura, Manabu Okumura
2005 Lecture Notes in Computer Science  
We use the core sentence and its question focus in question classification.  ...  The result of experiments shows that the proposed method improves F-measure by 8.8% and accuracy by 4.4%. 1 http://trec.nist.gov/tracks.htm 2  ...  and conduct experiments of question classification.  ... 
doi:10.1007/11562214_38 fatcat:ayn763thsjeona5bvcuzbuow7y

Utilizing coarse-grained data in low-data settings for event extraction [article]

Osman Mutlu
2022 arXiv   pre-print
We utilize a multi-task model with two auxiliary tasks, document and sentence binary classification, in addition to the main task of token classification.  ...  We perform a series of experiments with varying data regimes for the aforementioned integration.  ...  Our series of experiments show that training with sentence or document classification tasks help improve the results for token classification task.  ... 
arXiv:2205.05468v1 fatcat:egcdpaagdzgyldr5fp7gy5d2qy

FAGON: Fake News Detection Model Using Grammatical Transformation on Deep Neural Network

2019 KSII Transactions on Internet and Information Systems  
It consists of two modules: sentence generator and classification.  ...  The latter classifies the proposition as true or false by training with vectors generated from each sentence of the article and the multiple sentences obtained from the former model respectively.  ...  We evaluate our model with three experiments: First, we evaluate our model in terms of PSG to figure out whether it is crucial for classification.  ... 
doi:10.3837/tiis.2019.10.008 fatcat:2edm52g3cnf4fclreio4lpni3u

Promoting Understandability in Consumer Health Information Search [chapter]

Hua Yang, Teresa Goncalves
2017 Lecture Notes in Computer Science  
In this paper, we present two different approaches to do the classification. With the first approach, we implement two models to satisfy the task.  ...  With the second approach, we only use machine learning techniques to learn a model and classify the sentences into four  ...  We extract features with TF*IDF scheme. Test data needs to be pre-processed before classification. EXPERIMENTS AND RESULTS In this part, we give the results in our experiments.  ... 
doi:10.1007/978-3-319-56608-5_72 fatcat:yp5z6pzozbb2djghowlcaanqiu

The Effect of Downstream Classification Tasks for Evaluating Sentence Embeddings [article]

Peter Potash
2019 arXiv   pre-print
One simple such task is classification, where the sentence representations are used to train and test models on several classification datasets.  ...  We show how characteristics of this matrix can affect the ability for a low-dimensional factorization to perform as sentence representations in a suite of classification tasks.  ...  Experiments In order to empirically determine the effect of various factorization scenarios with respect to sentence embeddings' performance on downstream classification tasks, we ran several experiments  ... 
arXiv:1904.02228v2 fatcat:3q5b3cqgcnglxj65kn4uvteltq

Sentences and Documents in Native Language Identification [chapter]

Andrea Cimino, Felice Dell'Orletta, Dominique Brunato, Giulia Venturi
2018 Proceedings of the Fifth Italian Conference on Computational Linguistics CLiC-it 2018  
We compare the results obtained in a traditional NLI document classification task and in a newly introduced sentence classification task, investigating the different role played by the considered features  ...  Finally, we study the impact of a set of selected features extracted from the sentence classifier in document classification. Italiano.  ...  This trend holds also in the sentence classification experiment where 17.8% of errors were due to the confusion of Korean with Japanese and vice versa (18.2% of errors).  ... 
doi:10.4000/books.aaccademia.3204 fatcat:i6tzia2xbjcfzn5dfakzzzhgk4

Classification of individual trials based on the best independent component of EEG-recorded sentences

Dik Kin Wong, Marcos Perreau Guimaraes, E. Timothy Uy, Patrick Suppes
2004 Neurocomputing  
By tlie use of a multichannel classifier (MCC), classification rates were greatly inlproved for tlie subjects with bipolar settings, while the improvement for subjects with monopolar settings were small  ...  Significant results for individual trials were achieved in recognizing brain waves using singlechannel perceptron-based classifiers (SCC) on electroencephalograpliy (EEG) data generated by visual sentences  ...  In the 24-sentence experiment, there were 7 subjects with monopolar settings, 3 with bipolar settings. There were 10 subjects for the 48-sentence experiment with bipolar settings.  ... 
doi:10.1016/j.neucom.2004.06.004 fatcat:ppqszwywn5c73cofxpn76tez44

Supervised Machine Learning for Extractive Query Based Summarisation of Biomedical Data

Mandeep Kaur, Diego Mollá
2018 Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis  
We tackled the problem of annotating sentences for training classification systems and show that a simple annotation approach outperforms regression-based summarisation.  ...  In particular, we compare classification and regression approaches for query-based extractive summarisation using data provided by the BioASQ Challenge.  ...  Apparently, sentences with score between 0.3 and 0.7 were not used in their experiments.  ... 
doi:10.18653/v1/w18-5604 dblp:conf/acl-louhi/KaurM18 fatcat:k5fzffdhxjgjtjkabhahmbv4ry

Supervised Machine Learning for Extractive Query Based Summarisation of Biomedical Data [article]

Mandeep Kaur, Diego Mollá
2018 arXiv   pre-print
We tackled the problem of annotating sentences for training classification systems and show that a simple annotation approach outperforms regression-based summarisation.  ...  In particular, we compare classification and regression approaches for query-based extractive summarisation using data provided by the BioASQ Challenge.  ...  Apparently, sentences with score between 0.3 and 0.7 were not used in their experiments.  ... 
arXiv:1809.05268v2 fatcat:7qpvthjjjfeohclog3qoeoe3eu

CLASSIFICATION OF SENTENCES
文の分類

GIYOO HATANO, KEIKO KUHARA
1973 Japanese psychological research (Print)  
, EXPERIMENT I SPONTANEOUS CLASSIFICATION Materials A set of 8 sentences in Japanese (SJ) and a parallel set of corresponding sentences in English (SE) were used.  ...  EXPERIMENT II CLASSIFICATION WITH FEEDBACK Materials Here each S was tested as to whether he was able to adopt a prescribed way of classification shown only implicitly, i.e. by feedback.  ... 
doi:10.4992/psycholres1954.15.33 fatcat:kgwn6u2rfzannmauvk57i7sd2q

How Implication Is Understood

P. N. Johnson-Laird, Joanna Tagart
1969 American Journal of Psychology  
Table II shows the six common classifications of these stimuli, and the frequencies with which they occurred for each type of sentence.  ...  None of the remaining classifications occurred more than twice throughout the whole experiment.  ... 
doi:10.2307/1420752 fatcat:s6wlrzc2cna4lkxodofxe4t76q

Adapting Text Simplification Decisions to Different Text Genres and Target Users

Sanja Stajner, Horacio Saggion
2013 Revista de Procesamiento de Lenguaje Natural (SEPLN)  
The experiments were the following: • Experiment I: Classification between deleted ("1-0") and kept ("1-1" and "1n") sentences; • Experiment II: Classification between split and unsplit (same) sentences  ...  These sentences were thus excluded from Corpus B in all classification experiments.  ... 
dblp:journals/pdln/StajnerS13 fatcat:nxp3krnicveifg32ccgakrnkae

One Step Closer to Automatic Evaluation of Text Simplification Systems

Sanja Štajner, Ruslan Mitkov, Horacio Saggion
2014 Proceedings of the 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations (PITR)  
As the results show a significant correlation between them, we go further and try to classify simplified sentences into: (1) those which are acceptable; (2) those which need minimal post-editing; and (  ...  The focus is on six widely used machine translation (MT) evaluation metrics and their correlation with human judgements of grammaticality and meaning preservation in text snippets.  ...  Sentence Classification The results of the four classification experiments (Section 3.6) are given in Table 7 .  ... 
doi:10.3115/v1/w14-1201 dblp:conf/acl-pitr/StajnerMS14 fatcat:hqm6zbegyzgo7pgyn5rvlvf35i
« Previous Showing results 1 — 15 out of 205,104 results