Multilingual part-of-speech tagging with bidirectional long short-term memory models and auxiliary loss
Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful
for various NLP sequence modeling tasks, but little is known about their reliance to input …
for various NLP sequence modeling tasks, but little is known about their reliance to input …
Many languages, one parser
We train one multilingual model for dependency parsing and use it to parse sentences in
several languages. The parsing model uses (i) multilingual word clusters and …
several languages. The parsing model uses (i) multilingual word clusters and …
Robust multilingual part-of-speech tagging via adversarial training
Adversarial training (AT) is a powerful regularization method for neural networks, aiming to
achieve robustness to input perturbations. Yet, the specific effects of the robustness obtained …
achieve robustness to input perturbations. Yet, the specific effects of the robustness obtained …
Multilingual projection for parsing truly low-resource languages
We propose a novel approach to cross-lingual part-of-speech tagging and dependency
parsing for truly low-resource languages. Our annotation projection-based approach yields …
parsing for truly low-resource languages. Our annotation projection-based approach yields …
SemEval-2016 Task~ 10: Detecting Minimal Semantic Units and their Meanings (DiMSUM)
N Schneider, D Hovy, A Johannsen… - … Workshop on Semantic …, 2016 - research.ed.ac.uk
This task combines the labeling of multiword expressions and supersenses (coarse-grained
classes) in an explicit, yet broad-coverage paradigm for lexical semantics. Nine systems …
classes) in an explicit, yet broad-coverage paradigm for lexical semantics. Nine systems …
Cross-lingual morphological tagging for low-resource languages
Morphologically rich languages often lack the annotated linguistic resources required to
develop accurate natural language processing tools. We propose models suitable for …
develop accurate natural language processing tools. We propose models suitable for …
Do LSTMs really work so well for PoS tagging?–A replication study
T Horsmann, T Zesch - Proceedings of the 2017 conference on …, 2017 - aclanthology.org
A recent study by Plank et al.(2016) found that LSTM-based PoS taggers considerably
improve over the current state-of-the-art when evaluated on the corpora of the Universal …
improve over the current state-of-the-art when evaluated on the corpora of the Universal …
Surface statistics of an unknown language indicate how to parse it
We introduce a novel framework for delexicalized dependency parsing in a new language.
We show that useful features of the target language can be extracted automatically from an …
We show that useful features of the target language can be extracted automatically from an …
Sparse coding of neural word embeddings for multilingual sequence labeling
G Berend - Transactions of the Association for Computational …, 2017 - direct.mit.edu
In this paper we propose and carefully evaluate a sequence labeling framework which
solely utilizes sparse indicator features derived from dense distributed word representations …
solely utilizes sparse indicator features derived from dense distributed word representations …
[PDF][PDF] Cross-lingual tagger evaluation without test data
We address the challenge of cross-lingual POS tagger evaluation in absence of manually
annotated test data. We put forth and evaluate two dictionary-based metrics. On the tasks of …
annotated test data. We put forth and evaluate two dictionary-based metrics. On the tasks of …