Sciweavers

ACL
2012
12 years 1 months ago
PORT: a Precision-Order-Recall MT Evaluation Metric for Tuning
Many machine translation (MT) evaluation metrics have been shown to correlate better with human judgment than BLEU. In principle, tuning on these metrics should yield better syste...
Boxing Chen, Roland Kuhn, Samuel Larkin
ACL
2012
12 years 1 months ago
Improving the IBM Alignment Models Using Variational Bayes
Bayesian approaches have been shown to reduce the amount of overfitting that occurs when running the EM algorithm, by placing prior probabilities on the model parameters. We appl...
Darcey Riley, Daniel Gildea
ACL
2012
12 years 1 months ago
A Broad-Coverage Normalization System for Social Media Language
Social media language contains huge amount and wide variety of nonstandard tokens, created both intentionally and unintentionally by the users. It is of crucial importance to norm...
Fei Liu, Fuliang Weng, Xiao Jiang
ACL
2012
12 years 1 months ago
Lemmatisation as a Tagging Task
We present a novel approach to the task of word lemmatisation. We formalise lemmatisation as a category tagging task, by describing how a word-to-lemma transformation rule can be ...
Andrea Gesmundo, Tanja Samardzic
ACL
2012
12 years 1 months ago
Tense and Aspect Error Correction for ESL Learners Using Global Context
As the number of learners of English is constantly growing, automatic error correction of ESL learners’ writing is an increasingly active area of research. However, most researc...
Toshikazu Tajiri, Mamoru Komachi, Yuji Matsumoto
ACL
2012
12 years 1 months ago
Fast Online Training with Frequency-Adaptive Learning Rates for Chinese Word Segmentation and New Word Detection
We present a joint model for Chinese word segmentation and new word detection. We present high dimensional new features, including word-based features and enriched edge (label-tra...
Xu Sun, Houfeng Wang, Wenjie Li
ACL
2012
12 years 1 months ago
A Web-based Evaluation Framework for Spatial Instruction-Giving Systems
We demonstrate a web-based environment for development and testing of different pedestrian route instruction-giving systems. The environment contains a City Model, a TTS interface...
Srinivasan Janarthanam, Oliver Lemon, Xingkun Liu
ACL
2012
12 years 1 months ago
Tweet Recommendation with Graph Co-Ranking
As one of the most popular micro-blogging services, Twitter attracts millions of users, producing millions of tweets daily. Shared information through this service spreads faster ...
Rui Yan, Mirella Lapata, Xiaoming Li
ACL
2012
12 years 1 months ago
A Feature-Rich Constituent Context Model for Grammar Induction
We present LLCCM, a log-linear variant of the constituent context model (CCM) of grammar induction. LLCCM retains the simplicity of the original CCM but extends robustly to long s...
Dave Golland, John DeNero, Jakob Uszkoreit
ACL
2012
12 years 1 months ago
Mixing Multiple Translation Models in Statistical Machine Translation
Statistical machine translation is often faced with the problem of combining training data from many diverse sources into a single translation model which then has to translate se...
Majid Razmara, George Foster, Baskaran Sankaran, A...