183 Hits in 5.7 sec

Verb Sense and Subcategorization: Using Joint Inference to Improve Performance on Complementary Task

Galen Andrew, Trond Grenager, Christopher D. Manning
2004 Conference on Empirical Methods in Natural Language Processing  
Use of the joint model leads to error reductions over competitive independent models on these tasks.  ...  When applied to the word sense and verb subcategorization frame determination tasks, the model learns sharp joint probability distributions which correspond to linguistic intuitions about the correlations  ...  Acknowledgements This paper is based on work supported in part by the Advanced Research and Development Activity (ARDA)'s Advanced Question Answering for Intelligence (AQUAINT) Program, and by the National  ... 
dblp:conf/emnlp/AndrewGM04 fatcat:ksotxw67njdn5lr66pav772aea

Can We Make Information Extraction More Adaptive? [chapter]

Yorick Wilks, Roberta Catizone
1999 Lecture Notes in Computer Science  
In this paper we discuss some methods that have been tried to ease this problem, and to create something more rapid than the bench-mark one-month gure, which was roughly what ARPA teams in IE needed to  ...  Machine Translation, both of which are widely used commercially.  ...  Multilingual IE Given an IE system that performs an extraction task against texts in one language, it is natural to consider how to modify the system to perform the same task against texts in another.  ... 
doi:10.1007/3-540-48089-7_1 fatcat:q33ux5rdg5e6vnpq3mrchi4lpa

German particle verbs: Compositionality at the syntax-semantics interface

Stefan Bott, Sabine Schulte im Walde
2018 Journal of Language Modelling  
Particle verbs (PVs), such as the German auf|essen (to eat up) and the English to blow up, represent a type of multi-word expression (MWE) composed of a base verb (BV) and a particle.  ...  While particle verbs exist in many languages, German PVs are particularly frequent and form a  ...  The use of GermaNet generalizations already tends to improve the performance, although not consistently.  ... 
doi:10.15398/jlm.v6i1.138 fatcat:pnaxjuvszzbu5nwtzqwiazoa5a

Syntactic Transfer Patterns of German Particle Verbs and their Impact on Lexical Semantics

Stefan Bott, Sabine Schulte im Walde
2014 Proceedings of the Third Joint Conference on Lexical and Computational Semantics (*SEM 2014)  
clustering techniques allows us to distinguish particle verb meaning and shows the tight connection between transfer patterns and the semantic classes of particle verbs.  ...  However, while syntactic subcategorization frames tend to be good predictor for the semantics of verbs in general (verbs that are similar in meaning also tend to have similar subcategorization frames and  ...  Acknowledgements This work was funded by the DFG Research Project "Distributional Approaches to Semantic Relatedness" (Stefan Bott, Sabine Schulte im Walde), and the DFG Heisenberg Fellowship SCHU-2580  ... 
doi:10.3115/v1/s14-1022 dblp:conf/starsem/BottW14 fatcat:gb3ee366vnemzkk2nfd522twoe

FrameNet on the Way to Babel: Creating a Bilingual FrameNet Using Wiktionary as Interlingual Connection

Silvana Hartmann, Iryna Gurevych
2013 Annual Meeting of the Association for Computational Linguistics  
Our approach is based on a sense alignment of FrameNet and Wiktionary, and subsequent translation disambiguation into the target language.  ...  It is created through a simple, but powerful approach to construct a FrameNet in any language using Wiktionary as an interlingual representation.  ...  I/82806 and by the German Research Foundation under grant No. GU 798/3-1 and grant No. GU 798/9-1.  ... 
dblp:conf/acl/HartmannG13 fatcat:ej6ixxhn35doda3v4idfaykqoa

Computational approaches for German particle verbs: compositionality, sense discrimination and non-literal language [article]

Maximilian Köper, Universität Stuttgart, Universität Stuttgart
Furthermore, we compare and introduce the methods to find and represent different verb senses. Our findings indicate the usefulness of such sense-specific models.  ...  We model the particle verb senses based only on huge amounts of texts, without access to other resources.  ...  Li and Jurafsky (2015) find that multi-sense embeddings do improve performance on some tasks but they also find that single-sense embeddings with higher dimensionality gain the same improvements.  ... 
doi:10.18419/opus-10113 fatcat:vnkyygmzdjh4ba64rmwaw4e6li

Concurrent Acquisition of Word Meaning and Lexical Categories

Afra Alishahi, Grzegorz Chrupala
2012 Conference on Empirical Methods in Natural Language Processing  
Our results show that the incrementally induced word classes significantly improve word learning, and their contribution is comparable to that of manually assigned part of speech categories.  ...  Learning the meaning of words from ambiguous and noisy context is a challenging task for language learners.  ...  Acknowledgements Grzegorz Chrupała was funded by the German Federal Ministry of Education and Research (BMBF) under grant number 01IC10S01O as part of the Software-Cluster project EMERGENT (www.  ... 
dblp:conf/emnlp/AlishahiC12 fatcat:wctzpp7ksrftbgfdhax6u4uzdy

Exploring the Application of the Random Matrix Thinking Model in Teaching English Predicate Constructions

Pengyuan Liu, Jue Wen, Ning Cao
2022 Mathematical Problems in Engineering  
The BERT-based English predicative verb recognition model improves the former approach by taking full advantage of the input corpus and improving the model performance.  ...  This paper, the random matrix thinking model, studies the grammatical features of verbs on random matrix and logical relations and designs a model for teaching English predicate constructions by combining  ...  Acknowledgments is work was supported by School of Information and Communication Engineering, Hubei University of Economics.  ... 
doi:10.1155/2022/3865898 fatcat:hmxiv4lhcnb4denifnx722xlza

The Disambiguation of Nominalizations

Maria Lapata
2002 Computational Linguistics  
We combine these distinct information sources using Ripper, a system that learns sets of rules from data, and achieve an accuracy of 86.1% (over a baseline of 61.5%) on the British National  ...  Even an approximation that maps the compound head to its underlying verb provides insufficient evidence.  ...  Thanks to Frank Keller, Alex Lascarides, Scott McDonald, and three anonymous reviewers for valuable comments.  ... 
doi:10.1162/089120102760276018 fatcat:ryhm2wztlbe53hecebptlvtepm

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)  
iii resources to predict the compositionality of MWEs. The program also included a panel discussion on the future directions of the MWE community and the SIGLEX Section.  ...  We would like to thank the members of the program committee for the timely reviews, authors for their valuable contributions, shared task organizers, annotators, and system developers for their hard work  ...  In addition, we would like to thank Lauren Rudat for her suggestions on improving the stimuli, and to the anonymous reviewers for their suggestions on improving the paper.  ... 
doi:10.18653/v1/w17-1702 dblp:conf/mwe/ChesneyJSP17 fatcat:bv7aavgth5eurmzuphuowtuuhq

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
Our system gives a better performance than all the learning-based systems from the CoNLL-2011 shared task on the same dataset.  ...  We explore ways of using the resulting grounding to boost the performance of a state-of-the-art co-reference resolution system.  ...  We show that using the mode topic ID assigned during the inference method of LDA, used to annotate unseen documents, improves performance by stabilizing the obtained topics.  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

Probabilistic Distributional Semantics with Latent Variable Models

Diarmuid Ó Séaghdha, Anna Korhonen
2014 Computational Linguistics  
We consider LDA and a number of extensions to the model and evaluate them on a variety of semantic prediction tasks, demonstrating that our approach attains state-of-the-art performance.  ...  We describe a probabilistic framework for acquiring selectional preferences of linguistic predicates and for using the acquired representations to model the effects of context on word meaning.  ...  information and advice; and to the anonymous Computational Linguistics reviewers, whose suggestions have substantially improved the quality of this article.  ... 
doi:10.1162/coli_a_00194 fatcat:nk735ka77vgqte4oxhkudwcmv4

Multiword Expression Processing: A Survey

Mathieu Constant, Gülşen Eryiğit, Johanna Monti, Lonneke van der Plas, Carlos Ramisch, Michael Rosner, Amalia Todirascu
2017 Computational Linguistics  
For each of the two MWE processing subtasks and for each of the two use cases, we conclude on open issues and research perspectives.  ...  Many of the approaches in the literature can be differentiated according to how MWE processing is timed with respect to underlying use cases.  ...  Special thanks to Federico Sangati, who not only provided valuable suggestions, references, and feedback, but also contributed important initial written material to the foundations of this survey.  ... 
doi:10.1162/coli_a_00302 fatcat:rjrfyfbfpfblfbtwpbdqnpgsiu

Semi-Supervised Semantic Role Labeling via Structural Alignment

Hagen Fürstenau, Mirella Lapata
2012 Computational Linguistics  
Experimental results on semantic role labeling show that the automatic annotations produced by our method improve performance over using hand-labeled instances alone.  ...  Large-scale annotated corpora are a prerequisite to developing high-performance semantic role labeling systems.  ...  Acknowledgments We are grateful to the anonymous referees, whose feedback helped to substantially improve this article.  ... 
doi:10.1162/coli_a_00087 fatcat:2cu3d2t4r5addh6zegg4qpse6a

CLiFF Notes: Research in the Language, Information and Computation Laboratory of the University of Pennsylvania [article]

Editors: Matthew Stone, Libby Levison
1995 arXiv   pre-print
Short abstracts by computational linguistics researchers at the University of Pennsylvania describing ongoing individual and joint projects.  ...  Acknowledgements Thanks to all the contributors.  ...  To understand how tools fit into the tasks described by verbs, the system also needs to be able to compose and decompose verb and noun meanings.  ... 
arXiv:cmp-lg/9506008v1 fatcat:aidgv3pdzvfatc7yjygdvthcjq
« Previous Showing results 1 — 15 out of 183 results