Filters








118 Hits in 4.5 sec

Learning Lenient Parsing Typing via Indirect Supervision [article]

Toufique Ahmed, Premkumar Devanbu, Vincent Hellendoorn
2021 arXiv   pre-print
We introduce a lenient parser, which can parse & type fragments, even ones with simple errors.  ...  In this paper, we present a novel, indirectly supervised, approach to train a lenient parser, without access to such human-curated training data.  ...  We generate large volumes of training data for parsing & typing erroneous code by starting with code which syntactically correct, and well-typed, which can be parsed and typed with a standard parser, and  ... 
arXiv:1910.05879v3 fatcat:dkdofygmg5boxfffldahiihwwi

Starting from Scratch in Semantic Role Labeling: Early Indirect Supervision [chapter]

Michael Connor, Cynthia Fisher, Dan Roth
2012 Cognitive Aspects of Computational Language Acquisition  
Where do children learning their first languages begin in solving this problem?  ...  To accomplish this, the listener must parse the sentence, find constituents that are candidate arguments, and assign semantic roles to those constituents.  ...  the learning permitted by indirect semantic-role feedback.  ... 
doi:10.1007/978-3-642-31863-4_10 dblp:series/tanlp/ConnorFR13 fatcat:e2rlqdu37be37cilqgtourtohm

English Language Policy and Teacher Effectiveness at Grade Three Senior High Schools

Ebrahim Khodadady, Leila Aryanjam, Mohammad Ghazanfari
2015 Journal of Language Teaching and Research  
In other words, they are forced by regulations to be lenient officially.  ...  It requires harmonizing and choosing appropriate educational content and materials, reforming, supervising and reviewing educational objectives and curriculum by determining the time and effort required  ... 
doi:10.17507/jltr.0603.17 fatcat:oms4uqgcwjggrprzssuxk2mozm

Opinion Mining and Sentiment Analysis [chapter]

Bing Liu
2011 Web Data Mining  
Another approach is to adopt a supervised learning method (see Chapter 13 on Machine Learning).  ...  It should not be surprising then, that state-of-the-art systems again adopt supervised learning approaches to recognise expressions of opinion.  ... 
doi:10.1007/978-3-642-19460-3_11 fatcat:5epiy3et3jed5n24ejzyeavpby

CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

Daniel Zeman, Jan Hajic, Martin Popel, Martin Potthast, Milan Straka, Filip Ginter, Joakim Nivre, Slav Petrov
2018 Conference on Computational Natural Language Learning  
Every year, the Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets.  ...  In 2018, one of two tasks was devoted to learning dependency parsers for a large number of languages, in a real-world setting without any gold-standard annotation on the input.  ...  Unlike LAS, certain types of relations (Table 3) are not evaluated directly. Words attached via such relations (in either system or gold data) are not counted as independent words.  ... 
doi:10.18653/v1/k18-2001 dblp:conf/conll/ZemanHPPSGNP18 fatcat:qwqj2k4mancgrcmcwhdx2frtz4

Unrestricted Bridging Resolution

Yufang Hou, Katja Markert, Michael Strube
2018 Computational Linguistics  
I still remember that I can hear the sound of her typing even we sat in different rooms.  ...  anaphora which indicates that a noun phrase refers back to the same entity introduced by previous descriptions in the discourse, bridging anaphora or associative anaphora links anaphors and antecedents via  ...  This leads to considerable interest in weakly supervised learning and distantly supervised learning. In the following, we discuss works in these two areas respectively. Weakly supervised approaches.  ... 
doi:10.1162/coli_a_00315 fatcat:ezgwhbvbrffi5jgx3edhigvx4a

Statistical Metaphor Processing

Ekaterina Shutova, Simone Teufel, Anna Korhonen
2013 Computational Linguistics  
Our approach is minimally supervised, it relies on the state-of-the-art parsing and lexical acquisition technologies (distributional clustering and selectional preference induction) and operates with a  ...  Characteristic to all areas of human activity (from poetic to ordinary to scientific) and thus to all types of discourse, metaphor becomes an important problem for natural language processing.  ...  Starting from a small set of metaphorical expressions, the system learns the analogies involved in their production in a minimally supervised way.  ... 
doi:10.1162/coli_a_00124 fatcat:dhyjooytrza3dpxsotoyfmn76m

Understanding Information Needs [chapter]

Krisztian Balog
2018 Advanced Topics in Information Retrieval  
Specifically, in Sect. 7.2, we seek to identify the types or categories of entities that are targeted by the query.  ...  Key to this semi-supervised learning process is to have a small set of seed queries Q 0 .  ...  Sect. 3.3) Supervised Approach Using a supervised learning approach, each (entity, query, mention) triple is described using a set of features.  ... 
doi:10.1007/978-3-319-93935-3_7 fatcat:kbqo7rhshrcivlfsauptk3z3oa

Leveraging Textual Sentiment Analysis with Social Network Modelling: Sentiment Analysis of Political Blogs in the 2008 U.S. Presidential Election [chapter]

Wojciech Gryc, Karo Moilanen
2014 Discourse Approaches to Politics, Society and Culture  
Blog posts further link to each other via highly complex interrelated direct/explicit and indirect/implicit structural, semantic, rhetorical, and temporal chains.  ...  In a similar study, [15] used web-based Pointwise Mutual Information scoring, supervised machine learning, and citation graph clustering (accuracy 68.48%∼73%).  ... 
doi:10.1075/dapsac.55.03gry fatcat:xrxqrm6zajarne4uuyfcquxmay

Opinion Mining and Sentiment Analysis [chapter]

2016 Text Data Management and Analysis: A Practical Introduction to Information Retrieval and Text Mining  
Unsupervised (and supervised) learning also benefitted from the improvements to sub-component systems for tagging, parsing, and so on that occurred due to the application of data-driven techniques in those  ...  And, of course, the importance to supervised learning of having access to labeled data is paramount.  ... 
doi:10.1145/2915031.2915050 fatcat:3ypahumv4rhz5alxmh34ikvm3i

Open-Domain Question–Answering

John Prager
2006 Foundations and Trends in Information Retrieval  
Unsupervised (and supervised) learning also benefitted from the improvements to sub-component systems for tagging, parsing, and so on that occurred due to the application of data-driven techniques in those  ...  And, of course, the importance to supervised learning of having access to labeled data is paramount.  ... 
doi:10.1561/1500000001 fatcat:5xq5eb7idrb37lz3wyzfl4cb34

Computational Text Analysis within the Humanities [chapter]

2020 Reflektierte algorithmische Textanalyse  
The article identifies two central workflow-related issues for this type of collaborative project in the Digital Humanities (DH) and Computational Social Science: (i) a scheduling dilemma, which affects  ...  On the dataset, supervised classifiers can be trained using a standard machine learning library (e. g., the Python library scikit-learn http://scikit-learn.org/).  ...  So, instead of emigration events the corpus can be searched for another type of event. Extraction is realized as a machine learning classifier.  ... 
doi:10.1515/9783110693973-004 fatcat:bmv3fasbu5hwlfx3vncsmcwnx4

Identifying sources of opinions with conditional random fields and extraction patterns

Yejin Choi, Claire Cardie, Ellen Riloff, Siddharth Patwardhan
2005 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05   unpublished
While CRFs model source identification as a sequence tagging task, Au-toSlog learns extraction patterns.  ...  Our research is the first to identify both direct and indirect sources for all types of opinions, emotions, and sentiments.  ...  Step 2: The learned patterns are augmented with selectional restrictions that semantically constrain the types of noun phrases that are legitimate extractions for opinion sources.  ... 
doi:10.3115/1220575.1220620 fatcat:gh32j6j2bzgwxi4vbqpg2vjb6i

Camilla [chapter]

Ingo Gildenhard, John Henderson
2018 Classics Textbooks  
Their speech follows, in indirect discourse (102-5).  ...  Now we suddenly learn that he operates surrounded by a bustling crowd of allies (tum socios…).  ...  In death, they become part of the natural world physically, transformed metaphorically via water.  ... 
doi:10.11647/obp.0158.03 fatcat:ae4x2qpggfg3foxsjux3evmfoe

Annotation concept synthesis and enrichment analysis: a logic-based approach to the interpretation of high-throughput experiments

M. Jiline, S. Matwin, M. Turcotte
2011 Bioinformatics  
A small directed study project completed under his supervision was the seed for the ideas that eventually, after few years, became the foundation of this thesis.  ...  As a subfield of Machine Learning, even more precisely as a type of Supervised Learning, ILP is concerned with the learning of new concepts or rules based on labeled examples.  ...  An example of such direct evaluation is n-fold cross validation approach often used for supervised learning problems.  ... 
doi:10.1093/bioinformatics/btr337 pmid:21743060 pmcid:PMC3157920 fatcat:oftmeieh5jbo7fuutwzdsainiu
« Previous Showing results 1 — 15 out of 118 results