1 |
Using paraphrases for improving first story detection in news and twitter
|
|
|
|
In: http://homepages.inf.ed.ac.uk/miles/papers/naacl12.pdf (2012)
|
|
BASE
|
|
Show details
|
|
2 |
Opinion retrieval in twitter
|
|
|
|
In: http://homepages.inf.ed.ac.uk/miles/papers/icwsm12.pdf (2012)
|
|
BASE
|
|
Show details
|
|
3 |
Using paraphrases for improving first story detection in news and twitter
|
|
|
|
In: http://www.aclweb.org/anthology-new/N/N12/N12-1034.pdf (2012)
|
|
BASE
|
|
Show details
|
|
4 |
Constructing parallel corpora for six indian languages via crowdsourcing
|
|
|
|
In: http://www.aclweb.org/anthology/W12-3152/ (2012)
|
|
BASE
|
|
Show details
|
|
5 |
LRscore for evaluating lexical and reordering quality
|
|
|
|
In: http://aclweb.org/anthology-new/W/W10/W10-1749.pdf (2010)
|
|
BASE
|
|
Show details
|
|
6 |
LRscore for evaluating lexical and reordering quality
|
|
|
|
In: http://www.mt-archive.info/WMT-2010-Birch.pdf (2010)
|
|
BASE
|
|
Show details
|
|
7 |
A Gibbs sampler for phrasal synchronous grammar induction
|
|
|
|
In: http://nlp.csie.ncnu.edu.tw/~shin/acl-ijcnlp2009/proceedings/CDROM/ACLIJCNLP/pdf/ACLIJCNLP088.pdf (2009)
|
|
BASE
|
|
Show details
|
|
8 |
Bayesian synchronous grammar induction
|
|
|
|
In: http://books.nips.cc/papers/files/nips21/NIPS2008_0238.pdf (2008)
|
|
BASE
|
|
Show details
|
|
9 |
Modelling lexical redundancy for machine translation
|
|
|
|
In: http://www.mt-archive.info/Coling-ACL-2006-Talbot.pdf (2006)
|
|
BASE
|
|
Show details
|
|
10 |
Modelling lexical redundancy for machine translation
|
|
|
|
In: http://acl.ldc.upenn.edu/P/P06/P06-1122.pdf (2006)
|
|
BASE
|
|
Show details
|
|
11 |
Modelling lexical redundancy for machine translation
|
|
|
|
In: http://www.iccs.informatics.ed.ac.uk/~osborne/papers/acl06.pdf (2006)
|
|
BASE
|
|
Show details
|
|
12 |
Constraining the phrase-based, joint probability statistical translation model
|
|
|
|
In: http://www.mt-archive.info/HLT-NAACL-2006-Birch.pdf (2006)
|
|
BASE
|
|
Show details
|
|
13 |
Constraining the Phrase-Based, Joint Probability Statistical Translation Model
|
|
|
|
In: http://www.statmt.org/wmt06/proceedings/pdf/WMT23.pdf (2006)
|
|
BASE
|
|
Show details
|
|
14 |
1 Statistical Natural Language Processing
|
|
|
|
In: http://www-csli.stanford.edu/~ccb/publications/statistical-natural-language-processing-chapter.pdf (2003)
|
|
BASE
|
|
Show details
|
|
15 |
Statistical Natural Language Processing
|
|
|
|
In: http://www.cogsci.ed.ac.uk/~osborne/csli.pdf (2003)
|
|
BASE
|
|
Show details
|
|
16 |
Using Language Models to Assist in the Correction of Machine Translation Output
|
|
|
|
In: http://www.ling.ed.ac.uk/teaching/postgrad/mscslp/archive/dissertations/2001-2/beatrice_alex.pdf (2002)
|
|
BASE
|
|
Show details
|
|
17 |
Shallow Parsing with PoS Taggers and Linguistic Features
|
|
|
|
In: http://www.ai.mit.edu/projects/jmlr/papers/volume2/megyesi02a/megyesi02a.pdf (2002)
|
|
BASE
|
|
Show details
|
|
18 |
Memory-Based Shallow Parsing
|
|
|
|
In: http://cnts.uia.ac.be/cnts/papers/./ps/20020417.4146.jmlr2002.ps (2002)
|
|
BASE
|
|
Show details
|
|
19 |
Memory-based Shallow Parsing
|
|
|
|
In: http://jmlr.csail.mit.edu/papers/volume2/tks02a/tks02a.pdf (2002)
|
|
BASE
|
|
Show details
|
|
20 |
Using Language Models to Assist in the Correction Of Machine Translation Output
|
|
|
|
In: http://www.cogsci.ed.ac.uk/~osborne/msc-projects/alex.ps.gz (2002)
|
|
Abstract:
Machine translation (MT) systems are renowned for making many translation errors. Spotting such errors can be a time-consuming and labour-intensive process which makes automatic evaluation and correction of MT output highly desirable for both system developers and end-users. Based on the novel approach of using statistical language models to assess the quality of MT, the main aim of this project is to automatically spot sentences containing translation errors in the output of a commercial MT system by means of N-gram models built from a target language corpus. This method, which is presented in this MSc dissertation, aims to differentiate between good- and bad-quality translations of sentences in terms of the cross entropy scores produced by the language model. The cross entropy values assigned to a set of known good-quality human-written sentences translations will be used as a reference point in the pilot experiment. Issues such as sentence length and the occurrence of unseen events in the test data will be addressed and the behaviour of various language modeling parameters, including the N-gram order, the smoothing technique, the amount of training data and the vocabulary size, will be investigated.
|
|
URL: http://www.cogsci.ed.ac.uk/~osborne/msc-projects/alex.ps.gz http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.2840
|
|
BASE
|
|
Hide details
|
|
|
|