Cross-lingual Parsing with Polyglot Training and Multi-treebank Learning: A Faroese Case Study

Challenge:	Cross-lingual dependency parsing involves transferring syntactic knowledge from one language to another.
Approach:	They compare two approaches to cross-lingual dependency parsing using monolingual source models and a polyglot model which is trained on the combination of all source languages.
Outcome:	The proposed methods improve low-resource dependency parsers by transferring syntactic knowledge from one language to another.

Similar Papers

Overview

Challenge

Approach

Outcome

Parser Training with Heterogeneous Treebanks (P18-2)

Copied to clipboard

Sara Stymne, Miryam de Lhoneux, Aaron Smith, Joakim Nivre

Semantic Text Processing

Challenge:	In the 2017 CoNLL Shared Task on Universal Dependency Parsing, 25 languages have more than one treebank . many teams did not take advantage of the multiple treebanks, however, and trained one model per treebank instead of one model for each language.
Approach:	They propose a method to make the most of heterogeneous treebanks when training a monolingual parser.
Outcome:	The proposed method improves on training with multiple treebanks for a single language.

Treebank Embedding Vectors for Out-of-Domain Dependency Parsing (2020.acl-main)

Copied to clipboard

Joachim Wagner, James Barry, Jennifer Foster

Syntactic Text Processing

Challenge:	a recent advance in monolingual dependency parsing is the idea of a treebank embedding vector . this allows the model to prefer training data from one treebank over another at test time .
Approach:	They propose a method to predict a treebank vector for sentences that do not come from a particular treebank . they also explore what happens when they move away from predefined treebank embedding vectors .
Outcome:	The proposed method can predict treebank vectors for sentences that do not come from a treebank used in training with sufficient accuracy for nine out of ten languages.

Polyglot Contextual Representations Improve Crosslingual Transfer (N19-1)

Copied to clipboard

Phoebe Mulcaire, Jungo Kasai, Noah A. Smith

Semantic Text Processing

Challenge:	Existing methods for crosslingual transfer use multilingual word embeddings, but contextual word representations are not yet available.
Approach:	They propose a method to produce multilingual contextual word representations by training a single language model on text from multiple languages.
Outcome:	The proposed method compares model models to monolingual and non-contextual variants and shows that polyglot learning can be beneficial for multilingual representations.

Cross-Lingual Dependency Parsing Using Code-Mixed TreeBank (D19-1)

Copied to clipboard

Meishan Zhang, Yue Zhang, Guohong Fu

Multilinguality

Challenge:	Treebank translation is a promising method for cross-lingual transfer of syntactic dependency knowledge.
Approach:	They propose to map dependency arcs from source treebank to target translation according to word alignments.
Outcome:	Experiments on university dependency treebanks show that translated treebank translations are more effective than translated treebans.

Cheating a Parser to Death: Data-driven Cross-Treebank Annotation Transfer (L18-1)

Copied to clipboard

Djamé Seddah, Eric de la Clergerie, Benoît Sagot, Héctor Martínez Alonso, Marie Candito

Syntactic Text Processing

Challenge:	Using annotated corpus for linguistic purposes is no longer justified . hand-crafted syntactic resources such as grammars and lexicons can be used as sources of features to guide data driven systems.
Approach:	They propose an efficient method for transferring annotations between two different treebanks of the same language.
Outcome:	The proposed method is based on the Universal Dependency annotation scheme and was evaluated on the gold standard (94.75% of LAS, 99.40% UAS on the test set).

Project-then-Transfer: Effective Two-stage Cross-lingual Transfer for Semantic Dependency Parsing (2021.eacl-main)

Copied to clipboard

Hiroaki Ozaki, Gaku Morio, Terufumi Morishita, Toshinori Miyoshi

Syntactic Text Processing

Challenge:	Several remarkable contributions have been made in syntactic dependency parsing, especially on universal dependencies.
Approach:	They propose to capture cross-linguality by combing annotation projection and model transfer of pre-trained language models.
Outcome:	The proposed model parser almost achieved the approximated upper bound.

Polyglot Semantic Role Labeling (P18-2)

Copied to clipboard

Phoebe Mulcaire, Swabha Swayamdipta, Noah A. Smith

Semantic Parsing

Challenge:	Existing approaches to multilingual semantic dependency parsing treat languages independently, without exploiting similarities between semantic structures across languages.
Approach:	They propose to combine resources from different languages in a CoNLL 2009 shared task to build a single polyglot semantic dependency parser.
Outcome:	The proposed model outperforms monolingual training on a CoNLL 2009 dataset with training data from multiple languages and representations using multilingual word vectors.

Language Embeddings for Typology and Cross-lingual Transfer Learning (2021.acl-long)

Copied to clipboard

Dian Yu, Taiqi He, Kenji Sagae

Semantic Text Processing

Challenge:	Recent efforts to leverage multilingual datasets highlight potential of multilingual models that can perform well across various languages.
Approach:	They propose to generate language representations that capture relationships among languages and evaluate them using WALS and two extrinsic tasks.
Outcome:	The proposed model can be leveraged in cross-lingual tasks without parallel data . the proposed model is based on the World Atlas of Language Structures (WALS) and two extrinsic tasks .

Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections (P19-1)

Copied to clipboard

Junxian He, Zhisong Zhang, Taylor Berg-Kirkpatrick, Graham Neubig

Syntactic Text Processing

Challenge:	Current systems for syntactic analysis tasks rely heavily on large scale annotated data.
Approach:	They propose to learn a generative model with a structured prior that uses labeled source and unlabeled target data jointly.
Outcome:	The proposed model improves on part-of-speech tagging and dependency parsing tasks on English as the only source corpus and on a wide range of target languages.

Scalable Cross-lingual Treebank Synthesis for Improved Production Dependency Parsers (2020.coling-industry)

Copied to clipboard

Yousef El-Kurdi, Hiroshi Kanayama, Efsun Sarioglu Kayi, Vittorio Castelli, Todd Ward, Radu Florian

Language Models

Challenge:	scalable Universal Dependency (UD) treebank synthesis techniques are used to improve production-grade parsers.
Approach:	They propose a data augmentation technique that uses synthetic treebanks to improve production-grade parsers.
Outcome:	The proposed technique improves LAS performance on seven languages by up to two points on production models trained on original UD treebanks.