Search Results for author:
Found 24 papers, 5 papers with code
Interactive Assignments for Teaching Structured Neural NLP
We present a set of assignments for a graduate-level NLP course.
Measuring the Effects of Human and Machine Translation on Website Engagement
With the internet growing increasingly multilingual, it is important to consider translating websites.
Automatic Bilingual Markup Transfer
We describe the task of bilingual markup transfer, which involves placing markup tags from a source sentence into a fixed target translation.
Putting the Con in Context: Identifying Deceptive Actors in the Game of Mafia
In this work, we analyze the effect of speaker role on language use through the game of Mafia, in which participants are assigned either an honest or a deceptive role.
Automatic Correction of Human Translations
We show that human errors in TEC exhibit a more diverse range of errors and far fewer translation fluency errors than the MT errors in automatic post-editing datasets, suggesting the need for dedicated TEC models that are specialized to correct human errors.
Enriched Annotations for Tumor Attribute Classification from Pathology Reports with Limited Labeled Data
Precision medicine has the potential to revolutionize healthcare, but much of the data for patients is locked away in unstructured free-text, limiting research and delivery of effective personalized treatments.
A Streaming Approach For Efficient Batched Beam Search
We propose an efficient batching strategy for variable-length decoding on GPU architectures.
End-to-End Neural Word Alignment Outperforms GIZA++
Although unnecessary for training neural MT models, word alignment still plays an important role in interactive applications of neural machine translation, such as annotation transfer and lexicon injection.
Measuring Immediate Adaptation Performance for Neural Machine Translation
Incremental domain adaptation, in which a system learns from the correct output for each input immediately after making its prediction for that input, can dramatically improve system performance for interactive machine translation.
Adding Interpretable Attention to Neural Translation Models Improves Word Alignment
Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a result.
Guiding Policies with Language via Meta-Learning
However, a single instruction may be insufficient to fully communicate our intent or, even if it is, may be insufficient for an autonomous agent to actually understand how to perform the desired task.
Compact Personalized Models for Neural Machine Translation
We propose and compare methods for gradient-based domain adaptation of self-attentive neural machine translation models.
