113 Hits in 5.0 sec

Brighter than Gold: Figurative Language in User Generated Comparisons

Vlad Niculae, Cristian Danescu-Niculescu-Mizil
2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)  
We operationalize these insights and apply them to a new task with high relevance to text understanding: distinguishing between figurative and literal comparisons.  ...  Our starting point is a new large dataset of comparisons extracted from product reviews and annotated for figurativeness.  ...  Acknowledgements We would like to thank Yulia Tsvetkov for constructive discussion about figurative language and about her and her co-authors' work.  ... 
doi:10.3115/v1/d14-1215 dblp:conf/emnlp/NiculaeD14 fatcat:vbu6vx7fzvcvzbjhiohd2jt3fy

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
Experimental results show that our joint learning system outperforms independent learning systems.  ...  To inject knowledge, we use a state-of-the-art system which cross-links (or "grounds") expressions in free text to Wikipedia.  ...  Tsukada, and M. Nagata . . . . . . . . p. 123 Detecting Semantic Equiva- lence and Information Dis- parity in Cross-lingual Doc- uments Y. Mehdad, M. Negri, and M.  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

Idiomatic Expression Identification using Semantic Compatibility [article]

Ziheng Zeng, Suma Bhat
2021 arXiv   pre-print
To address this challenge, we study the task of detecting whether a sentence has an idiomatic expression and localizing it.  ...  A salient feature of the model is its ability to identify idioms unseen during training with gains from 1.4% to 30.8% over competitive baselines on the largest dataset.  ...  It uses RoBERTa and a set of linguistic features to perform token level metaphor tagging. Experimental setup.  ... 
arXiv:2110.10064v1 fatcat:4fiudgxrojdj3knvd4igxprzzm


2016 Journal of Engineering Science and Technology  
The results are compared with the baseline approach and performance is evaluated based on standard PAN measures.  ...  Many works are already available in verbatim plagiarism detection which is a type of simple copy and paste plagiarism but when it comes to intelligent plagiarism the scenario becomes more complex.  ...  Copy & paste plagiarism, style plagiarism, idea plagiarism, word switch plagiarism, metaphor plagiarism and cross-lingual plagiarisms are some of the main categories [2] .  ... 
doaj:966443565f4f49cf967fbcbf19dc0ccb fatcat:jgdw6p5dwfhmtlv6kvx6c777ci

Re-Representing Metaphor: Modeling Metaphor Perception Using Dynamically Contextual Distributional Semantics

Stephen McGregor, Kat Agres, Karolina Rataj, Matthew Purver, Geraint Wiggins
2019 Frontiers in Psychology  
In this paper, we present a novel context-dependent approach to modeling word meaning, and apply it to the modeling of metaphor.  ...  We test this hypothesis on a dataset of English word dyads rated for degrees of metaphoricity, meaningfulness, and familiarity by human participants.  ...  (Cross-Lingual Embeddings for Less-Represented Languages in European News Media).  ... 
doi:10.3389/fpsyg.2019.00765 pmid:31037062 pmcid:PMC6476275 fatcat:4hq6i46kkvhtpao37qpkmwrr3e

Towards generalisable hate speech detection: a review on obstacles and solutions

Wenjie Yin, Arkaitz Zubiaga
2021 PeerJ Computer Science  
the main obstacles, and then proposes directions of future research to improve generalisation in hate speech detection.  ...  This survey paper attempts to summarise how generalisable existing hate speech detection models are and the reasons why hate speech models struggle to generalise, sums up existing attempts at addressing  ...  Thus, future contribution to cross-lingual generalisation can be two-folds: increasing cross-lingual performance through model and dataset development, probing the limit of cross-lingual performance through  ... 
doi:10.7717/peerj-cs.598 fatcat:lhjvmezkdbanje6kycnxet6vmm

Computational linguistics [chapter]

Anne De Roeck
1995 Handbook of Pragmatics  
And finally, thanks to those who have given us advice and assistance in planning this workshop (especially  ...  for taking the time to provide useful detailed comments and suggestions for the improvement of papers; the nine panelists for providing detailed feedback on-site; and the students for their hard work  ...  I am very grateful to Ondřej Bojar (Charles University) for his numerous helpful suggestions and to the Institute of Formal and Applied Linguistics (Charles University) for providing the PCEDT 2.0 corpus  ... 
doi:10.1075/hop.m.comm2 fatcat:3riiqu7glvgrhj6pmqhtseaoqi

Computational Linguistics

A. G. Oettinger
1965 The American mathematical monthly  
And finally, thanks to those who have given us advice and assistance in planning this workshop (especially  ...  for taking the time to provide useful detailed comments and suggestions for the improvement of papers; the nine panelists for providing detailed feedback on-site; and the students for their hard work  ...  I am very grateful to Ondřej Bojar (Charles University) for his numerous helpful suggestions and to the Institute of Formal and Applied Linguistics (Charles University) for providing the PCEDT 2.0 corpus  ... 
doi:10.2307/2313322 fatcat:tm2wij5odzcrpkelrzniy2mrb4

Multi-word Entity Classification in a Highly Multilingual Environment

Sophie Chesney, Guillaume Jacquet, Ralf Steinberger, Jakub Piskorski
2017 Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017)  
We also want to thank the IC1207 COST Action PARSEME and SIGLEX for their endorsement and support, as well as the EACL 2017 organizers.  ...  , and all involved participants for their interest in the workshop.  ...  and Andrew Spencer.  ... 
doi:10.18653/v1/w17-1702 dblp:conf/mwe/ChesneyJSP17 fatcat:bv7aavgth5eurmzuphuowtuuhq

Using the Web as an Implicit Training Set: Application to Noun Compound Syntax and Semantics [article]

Preslav Nakov
2019 arXiv   pre-print
I address the problem of noun compounds syntax by means of novel, highly accurate unsupervised and lightly supervised algorithms using the Web as a corpus and search engines as interfaces to that corpus  ...  I also demonstrate how these paraphrasing verbs can be used to solve various relational similarity problems, and how paraphrasing noun compounds can improve machine translation.  ...  Another information source that seems promising for the syntax and semantics of noun compounds is cross-linguistic evidence, e.g., extracted from parallel multi-lingual corpora like Europarl as described  ... 
arXiv:1912.01113v1 fatcat:3ubstjtd7nhphmw4kbewls3onq

Word Sense Clustering and Clusterability

Diana McCarthy, Marianna Apidianaki, Katrin Erk
2016 Computational Linguistics  
a baseline that relies on the amount of overlap in a soft clustering.  ...  The two views that we use are two different sets of manually constructed lexical substitutes for the target lemma, on the one hand monolingual paraphrases, and on the other hand translations.  ...  We thank the anonymous reviewers for many helpful comments and suggestions.  ... 
doi:10.1162/coli_a_00247 fatcat:tjln73tn7jarren2uqea2vgdda

One Model to Rule them all: Multitask and Multilingual Modelling for Lexical Analysis [article]

Johannes Bjerva
2017 arXiv   pre-print
However, recent advances allow for broadening this approach, by considering data for multiple tasks and languages simultaneously.  ...  When learning a new skill, you take advantage of your preexisting skills and knowledge. For instance, if you are a skilled violinist, you will likely have an easier time learning to play cello.  ...  Cross-lingual Semantic Textual Similarity We will now look at the task of (cross-lingual) STS in more detail.  ... 
arXiv:1711.01100v1 fatcat:njotlhapbjggxkfndwa3wkwg4q

Shallow features as indicators of English–German contrasts in lexical cohesion

Kerstin Kunz, Ekaterina Lapshinova-Koltunski, José Manuel Martínez Martínez, Katrin Menzel, Erich Steiner
2017 Languages in Contrast: International Journal for Contrastive Linguistics  
Descriptive analyses of the corpus are then presented and statistically validated with the help of univariate and multivariate analyses.  ...  ranking and variation.  ...  References The semantic web: The roles of XML and RDF. Internet Computing, IEEE, 4(5): 63-73. Ferrucci, D. and Lally, A. (2004).  ... 
doi:10.1075/lic.16005.kun fatcat:p7pa2crm6rgkrfmsdf7m5265ea

Pretrained Transformers for Text Ranking: BERT and Beyond [article]

Jimmy Lin, Rodrigo Nogueira, Andrew Yates
2021 arXiv   pre-print
The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query.  ...  (i.e., result quality) and efficiency (e.g., query latency, model and index size).  ...  Acknowledgements This research was supported in part by the Canada First Research Excellence Fund and the Natural Sciences and Engineering Research Council (NSERC) of Canada.  ... 
arXiv:2010.06467v3 fatcat:obla6reejzemvlqhvgvj77fgoy

Multi-document arabic text summarisation

Mahmoud El-Haj, Udo Kruschwitz, Chris Fox
2011 2011 3rd Computer Science and Electronic Engineering Conference (CEEC)  
To address both points we created single and multi-document Arabic test collections both automatically and manually using a commonly used English dataset and by having human participants.  ...  The Document Understanding Conference (DUC) and Text Analysis Conference (TAC) at that time provided resources such as gold-standard extractive and abstractive summaries (both human and system generated  ...  Hachey et al. [2005] used a latent semantic space to model sentence similarity over a large corpus for detecting and eliminating redundancy.  ... 
doi:10.1109/ceec.2011.5995822 fatcat:74lmb2yhdzay3plc3nyszn57na
« Previous Showing results 1 — 15 out of 113 results