In this paper we question the almost universal assumption that in neural networks each token should be represented by a single vector. In fact, it is so natural to use one vector per word that most people do not even consider it as an assumption of their various models. Via a series of experiments on dependency parsing, in which we let each token in a sentence be represented by a sequence of vectors, we show that the “one single vector per token” assumption might be too strong for recurrent neural networks. Indeed, biaffine parsers seem to work better when their encoder accesses its input’s tokens’ representations in several time steps rather than all at once. This seems to indicate that having only one occasion to look at a token through its vector is too strong a constraint for recurrent neural networks and calls for further studies on the way tokens are fed to neural networks.

Polysemies, or “colexifications”, are of great interest in cognitive and historical linguistics, since meanings that are frequently expressed by the same lexeme are likely to be conceptually similar, and lie along a common pathway of semantic change. We argue that these types of inferences can be more reliably drawn from polysemies of cognate sets (which we call “dialexifications”) than from polysemies of lexemes. After giving a precise definition of dialexification, we introduce Evosem, a cross-linguistic database of etymologies scraped from several online sources. Based on this database, we measure for each pair of senses how many cognate sets include them both — i.e. how often this pair of senses is “dialexified”. This allows us to construct a weighted dialexification graph for any set of senses, indicating the conceptual and historical closeness of each pair. We also present an online interface for browsing our database, including graphs and interactive tables. We then discuss potential applications to NLP tasks and to linguistic research.

Nous présentons un système automatique de génération de blagues au format « Monsieur et Madame ».Ces blagues seront ensuite rendues accessibles sur un site internet où les visiteurs seront invités à lesnoter. Le tout servira ensuite à créer un corpus pour des études ultérieures.

In this paper, we introduce the first dependency treebank for the Umbrian language (an extinct Indo-European language from the Italic family, once spoken in modern day Italy). We present the source of the corpus : a set of seven bronze tablets describing religious ceremonies, written using two different scripts, unearthed in Umbria in the XVth century. The corpus itself has already been studied extensively by specialists of old Italic and classical Indo-European languages. So we discuss a number of challenges that we encountered as we annotated the corpus following Universal Dependencies’ guidelines from existing textual analyses.

We evaluate the efficacy of predicted UPOS tags as input features for dependency parsers in lower resource settings to evaluate how treebank size affects the impact tagging accuracy has on parsing performance. We do this for real low resource universal dependency treebanks, artificially low resource data with varying treebank sizes, and for very small treebanks with varying amounts of augmented data. We find that predicted UPOS tags are somewhat helpful for low resource treebanks, especially when fewer fully-annotated trees are available. We also find that this positive impact diminishes as the amount of data increases.

The lack of annotated data is a big issue for building reliable NLP systems for most of the world’s languages. But this problem can be alleviated by automatic data generation. In this paper, we present a new data augmentation method for artificially creating new dependency-annotated sentences. The main idea is to swap subtrees between annotated sentences while enforcing strong constraints on those trees to ensure maximal grammaticality of the new sentences. We also propose a method to perform low-resource experiments using resource-rich languages by mimicking low-resource languages by sampling sentences under a low-resource distribution. In a series of experiments, we show that our newly proposed data augmentation method outperforms previous proposals using the same basic inputs.

We present the system submission from the FASTPARSE team for the EUD Shared Task at IWPT 2020. We engaged with the task by focusing on efficiency. For this we considered training costs and inference efficiency. Our models are a combination of distilled neural dependency parsers and a rule-based system that projects UD trees into EUD graphs. We obtained an average ELAS of 74.04 for our official submission, ranking 4th overall.

Languages evolve and diverge over time. Their evolutionary history is often depicted in the shape of a phylogenetic tree. Assuming parsing models are representations of their languages grammars, their evolution should follow a structure similar to that of the phylogenetic tree. In this paper, drawing inspiration from multi-task learning, we make use of the phylogenetic tree to guide the learning of multi-lingual dependency parsers leveraging languages structural similarities. Experiments on data from the Universal Dependency project show that phylogenetic training is beneficial to low resourced languages and to well furnished languages families. As a side product of phylogenetic training, our model is able to perform zero-shot parsing of previously unseen languages.

This paper presents a simple framework for characterizing morphological complexity and how it encodes syntactic information. In particular, we propose a new measure of morpho-syntactic complexity in terms of governor-dependent preferential attachment that explains parsing performance. Through experiments on dependency parsing with data from Universal Dependencies (UD), we show that representations derived from morphological attributes deliver important parsing performance improvements over standard word form embeddings when trained on the same datasets. We also show that the new morpho-syntactic complexity measure is predictive of the gains provided by using morphological attributes over plain forms on parsing scores, making it a tool to distinguish languages using morphology as a syntactic marker from others.

This paper presents a new approach to the problem of cross-lingual dependency parsing, aiming at leveraging training data from different source languages to learn a parser in a target language. Specifically, this approach first constructs word vector representations that exploit structural (i.e., dependency-based) contexts but only considering the morpho-syntactic information associated with each word and its contexts. These delexicalized word embeddings, which can be trained on any set of languages and capture features shared across languages, are then used in combination with standard language-specific features to train a lexicalized parser in the target language. We evaluate our approach through experiments on a set of eight different languages that are part the Universal Dependencies Project. Our main results show that using such delexicalized embeddings, either trained in a monolingual or multilingual fashion, achieves significant improvements over monolingual baselines.