43 |
Societal Biases in Language Generation: Progress and Challenges ...
|
|
|
|
BASE
|
|
Show details
|
|
44 |
UserAdapter: Few-Shot User Learning in Sentiment Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
45 |
QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining ...
|
|
|
|
BASE
|
|
Show details
|
|
47 |
GEM: Natural Language Generation, Evaluation, and Metrics - Part 2 ...
|
|
|
|
BASE
|
|
Show details
|
|
48 |
Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation ...
|
|
|
|
BASE
|
|
Show details
|
|
49 |
Measuring and Increasing Context Usage in Context-Aware Machine Translation ...
|
|
|
|
Abstract:
Read paper: https://www.aclanthology.org/2021.acl-long.505 Abstract: Recent work in neural machine translation has demonstrated both the necessity and feasibility of using inter-sentential context, context from sentences other than those currently being translated. However, while many current methods present model architectures that theoretically can use this extra context, it is often not clear how much they do actually utilize it at translation time. In this paper, we introduce a new metric, conditional cross-mutual information, to quantify usage of context by these models. Using this metric, we measure how much document-level machine translation systems use particular varieties of context. We find that target context is referenced more than source context, and that including more context has a diminishing affect on results. We then introduce a new, simple training method, context-aware word dropout, to increase the usage of context by context-aware models. Experiments show that our method not only ...
|
|
Keyword:
Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
|
|
URL: https://underline.io/lecture/25724-measuring-and-increasing-context-usage-in-context-aware-machine-translation https://dx.doi.org/10.48448/x7mr-nt94
|
|
BASE
|
|
Hide details
|
|
50 |
UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
51 |
Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
52 |
GEM: Natural Language Generation, Evaluation, and Metrics - Part 1 ...
|
|
|
|
BASE
|
|
Show details
|
|
54 |
Meta Learning and Its Applications to Natural Language Processing ...
|
|
|
|
BASE
|
|
Show details
|
|
55 |
CausaLM: Causal Model Explanation Through Counterfactual Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
56 |
Beyond Metadata: What Paper Authors Say About Corpora They Use ...
|
|
|
|
BASE
|
|
Show details
|
|
57 |
Learning Latent Structures for Cross Action Phrase Relations in Wet Lab Protocols ...
|
|
|
|
BASE
|
|
Show details
|
|
59 |
One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers ...
|
|
|
|
BASE
|
|
Show details
|
|
60 |
Exploiting Auxiliary Data for Offensive Language Detection with Bidirectional Transformers ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|