Jakob D. Havtorn, Jan Latko, Joakim Edin, Lars Maaløe, Lasse Borgholt, Lorenzo Belgrano, Nicolai Jacobsen, Regitze Sdun, Željko Agić. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.

Current methods of cross-lingual parser transfer focus on predicting the best parser for a lowresource target language globally, that is, "at treebank level".In this work, we propose and argue for a novel cross-lingual transfer paradigm: instance-level parser selection (ILPS), and present a proof-of-concept study focused on instance-level selection in the framework of delexicalized parser transfer.Our work is motivated by an empirical observation that different source parsers are the best choice for different Universal POS-sequences (i.e., UPOS sentences) in the target language.We then propose to predict the best parser at the instance level.To this end, we train a supervised regression model, based on the Transformer architecture, to predict parser accuracies for individual POS-sequences.We compare ILPS against two strong single-best parser selection baselines (SBPS): (1) a model that compares POS n-gram distributions between the source and target languages (KL) and ( 2) a model that selects the source based on the similarity between manually created language vectors encoding syntactic properties of languages (L2V).The results from our extensive evaluation, coupling 42 source parsers and 20 diverse low-resource test languages, show that ILPS outperforms KL and L2V on 13/20 and 14/20 test languages, respectively.Further, we show that by predicting the best parser "at treebank level" (SBPS), using the aggregation of predictions from our instance-level model, we outperform the same baselines on 17/20 and 16/20 test languages.

The two most common paradigms for end-to-end speech recognition are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models. It has been argued that the latter is better suited for learning an implicit language model. We test this hypothesis by measuring temporal context sensitivity and evaluate how the models perform when we constrain the amount of contextual information in the audio input. We find that the AED model is indeed more context sensitive, but that the gap can be closed by adding self-attention to the CTC model. Furthermore, the two models perform similarly when contextual information is constrained. Finally, in contrast to previous research, our results show that the CTC model is highly competitive on WSJ and LibriSpeech without the help of an external language model.

Viable cross-lingual transfer critically depends on the availability of parallel texts.Shortage of such resources imposes a development and evaluation bottleneck in multilingual processing.We introduce JW300, a parallel corpus of over 300 languages with around 100 thousand parallel sentences per language pair on average.In this paper, we present the resource and showcase its utility in experiments with crosslingual word embedding induction and multisource part-of-speech projection.

We introduce DSDS: a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision, and realistically scales to hundreds of low-resource languages.The model exploits annotation projection, instance selection, tag dictionaries, morphological lexicons, and distributed representations, all in a uniform framework.The approach is simple, yet surprisingly effective, resulting in a new state of the art without access to any gold annotated data.

Héctor Martínez Alonso, Željko Agić, Barbara Plank, Anders Søgaard. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 2017.

How do we parse the languages for which no treebanks are available? This contribution addresses the cross-lingual viewpoint on statistical dependency parsing, in which we attempt to make use of resource-rich source language treebanks to build and adapt models for the under-resourced target languages. We outline the benefits, and indicate the drawbacks of the current major approaches. We emphasize synthetic treebanking: the automatic creation of target language treebanks by means of annotation projection and machine translation. We present competitive results in cross-lingual dependency parsing using a combination of various techniques that contribute to the overall success of the method. We further include a detailed discussion about the impact of part-of-speech label accuracy on parsing results that provide guidance in practical applications of cross-lingual methods for truly under-resourced 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 tagging and parsing models for over 100 languages. All that is needed are freely available parallel texts, and taggers and parsers for resource-rich languages. The empirical evaluation across 30 test languages shows that our method consistently provides top-level accuracies, close to established upper bounds, and outperforms several competitive baselines.

Anders Søgaard, Željko Agić, Héctor Martínez Alonso, Barbara Plank, Bernd Bohnet, Anders Johannsen. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

Using automatic measures such as labeled and unlabeled attachment scores is common practice in dependency parser evaluation.In this paper, we examine whether these measures correlate with human judgments of overall parse quality.We ask linguists with experience in dependency annotation to judge system outputs.We measure the correlation between their judgments and a range of parse evaluation metrics across five languages.The humanmetric correlation is lower for dependency parsing than for other NLP tasks.Also, inter-annotator agreement is sometimes higher than the agreement between judgments and metrics, indicating that the standard metrics fail to capture certain aspects of parse quality, such as the relevance of root attachment or the relative importance of the different parts of speech.

Cross-lingual learning has become a popular approach to facilitate the development of resources and tools for low density languages. Its underlying idea is to make use of existing tools and annotations in resource-rich languages to create similar tools and resources for resource-poor languages. Typically, this is achieved by either projecting annotations across parallel corpora, or by transferring models from one or more source languages to a target language. In this paper, we explore a third strategy by using machine translation to create synthetic training data from the original source-side annotations. Specifically, we apply this technique to dependency parsing, using a cross-lingually unified treebank for adequate evaluation. Our approach draws on annotation projection but avoids the use of noisy source-side annotation of an unrelated parallel corpus and instead relies on manual treebank annotation in combination with statistical machine translation, which makes it possible to train fully lexicalized parsers. We show that this approach significantly outperforms delexicalized transfer parsing.% despite the error-prone translation step.

Xavier Carreras, Lluís Padró, Lei Zhang, Achim Rettinger, Zhixing Li, Esteban García-Cuesta, Željko Agić, Božo Bekavac, Blaz Fortuna, Tadej Štajner. Proceedings of the Demonstrations at the 14th Conference of the European Chapter of the Association for Computational Linguistics. 2014.