BUCC @ ACL

12 papers28 directions

Papers by Year

2017 2
2015 2
2013 2
2011 6

Top Research Directions

Research directions most represented by papers from this venue.

Filtering Noisy Parallel Corpora for Machine Translation 3
End-to-End Representation Learning in Natural Language Processing 2
Cross-Lingual Alignment via Temporal Burst Correlation 1
Iterative Feature Construction through Decision Tree Induction 1
Semantic Similarity Thresholds for Noise Reduction 1
Maximum Entropy Modeling for Flexible Feature Integration 1
Optimizing Decision Thresholds for Precision-Recall Control 1
Multi-Metric Similarity Fusion 1
Bridging the Transliteration Translation Gap 1
Iterative Bootstrapping for Cross Lingual Alignment 1
The Impact of Alignment Quality on Machine Translation 1
Constructing Specialized Corpora for Targeted Language Processing 1
Summarizing the Non-Linear Structure of Multi-Party Dialogues 1
Grounding Machine Translation with Multilingual Knowledge Graphs 1
Modeling Human Subjectivity in Natural Language Evaluation 1

Top Authors

AuthorPapers
Philippe Langlais4
Heng Ji2
Alan Ritter1
Alberto Barrón-Cedeño1
Cristina España-Bonet1
Pascale Fung1
Sophia Ananiadou1
Tiejun Zhao1
Wei Xu1
Xiang Li1

Impactful Papers

Papers from this venue that shaped research clusters.

Influential

Papers

TitleYear
BUCC 2017 Shared Task: a First Attempt Toward a Deep Learning Framework for Identifying Parallel Sentences in Comparable Corpora2017
Users and Data: The Two Neglected Children of Bilingual Natural Language Processing Research2017
A Factory of Comparable Corpora from Wikipedia2015
Projective methods for mining missing translations in DBpedia2015
Gathering and Generating Paraphrases from Twitter with Application to Normalization2013
Using a Random Forest Classifier to recognise translations of biomedical terms across languages2013
Active Learning of Extractive Reference Summaries for Lecture Speech Summarization2011
Cross-lingual Slot Filling from Comparable Corpora2011
Exploiting Comparable Corpora with TER and TERp2011
Identifying Parallel Documents from a Large Bilingual Collection of Texts: Application to Parallel Article Extraction in Wikipedia2011
Mining Name Translations from Comparable Corpora by Creating Bilingual Information Networks2011
Train the Machine with What It Can Learn - Corpus Selection for SMT2011