Skip to search formSkip to main contentSkip to account menu
Comparative Study of CNN and RNN for Natural Language Processing
TLDR
This work is the first systematic comparison of CNN and RNN on a wide range of representative NLP tasks, aiming to give basic guidance for DNN selection.
View PDF on arXiv
Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?
TLDR
It is observed that intermediate tasks requiring high-level inference and reasoning abilities tend to work best and that target task performance is strongly correlated with higher-level abilities such as coreference resolution, but it is failed to observe more granular correlations between probing and target taskperformance.
View on ACL
MED: The LMU System for the SIGMORPHON 2016 Shared Task on Morphological Reinflection
This paper presents MED, the main system of the LMU team for the SIGMORPHON 2016 Shared Task on Morphological Reinflection as well as an extended analysis of how different design choices contribute…
View on ACL
Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages
TLDR
This work proposes two novel multi-task training approaches—one with, one without need for external unlabeled resources—, and two corresponding data augmentation methods, improving over the neural baseline for all languages, and explores cross-lingual transfer as a third way to fortify the neural model.
View on ACL
Neural Morphological Analysis: Encoding-Decoding Canonical Segments
TLDR
A character-based neural encoderdecoder model for Canonical morphological segmentation is proposed and extended to include morphemelevel and lexical information through a neural reranker.
View on ACL
Training Data Augmentation for Low-Resource Morphological Inflection
TLDR
It is found that autoencoding random strings works sur-prisingly well, outperformed only slightly by autoenCoding words from an unlabelled corpus and the random string method also works well in the 10,000-example setting despite not being tuned for it.
View on ACL
Single-Model Encoder-Decoder with Explicit Morphological Representation for Reinflection
TLDR
This work reduces the amount of required training data for this architecture and achieves state-of-the-art results, making encoder-decoder models applicable to morphological reinflection even for low-resource languages.
View on ACL
Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?
TLDR
It is observed that intermediate tasks requiring high-level inference and reasoning abilities tend to work best and that target task performance is strongly correlated with higher-level abilities such as coreference resolution, but it is failed to observe more granular correlations between probing and target taskperformance.
View PDF on arXiv
Probing for Semantic Classes: Diagnosing the Meaning Content of Word Embeddings
TLDR
A large dataset based on manual Wikipedia annotations and word senses, where word senses from different words are related by semantic classes is presented, and a classifier can accurately predict whether a word is single-sense or multi-sense, based only on its embedding.
View on ACL
The LMU System for the CoNLL-SIGMORPHON 2017 Shared Task on Universal Morphological Reinflection
We present the LMU system for the CoNLL-SIGMORPHON 2017 shared task on universal morphological reinflection, which consists of several subtasks, all concerned with producing an inflected form of a…
View on ACL
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License