Syntactic Nuclei in Dependency Parsing – A Multilingual Exploration

Syntactic Nuclei in Dependency Parsing – A Multilingual Exploration Ali Basirat Uppsala University Dept. of Linguistics and Philology ali.basirat@lingfil.uu.se Joakim Nivre Uppsala University Dept. of Linguistics and Philology joakim.nivre@lingfil.uu.se Abstract Standard models for syntactic dependency parsing take words to be the elementary units that enter into dependency relations. In this paper, we investigate whether there are any benefits from enriching these models with the more abstract notion of nucleus proposed by Tesni`ere. We do this by showing how the con- cept of nucleus can be defined in the frame- work of Universal Dependencies and how we can use composition functions to make a transition-based dependency parser aware of this concept. Experiments on 12 languages show that nucleus composition gives small but significant improvements in parsing accuracy. Further analysis reveals that the improvement mainly concerns a small number of depen- dency relations, including relations of coordi- nation, direct objects, nominal modifiers, and main predicates. 1 Introduction A syntactic dependency tree consists of directed arcs, representing syntactic relations like subject and object, connecting a set of nodes, represent- ing the elementary syntactic units of a sentence. In contemporary dependency parsing, it is gener- ally assumed that the elementary units are word forms or tokens, produced by a tokenizer or word segmenter. A consequence of this assumption is that the shape and size of dependency trees will vary systematically across languages. In particu- lar, morphologically rich languages will typically have fewer elementary units and fewer relations than more analytical languages, which use inde- pendent function words instead of morphological inflection to encode grammatical information. This is illustrated in Figure 1, which contrasts two equiv- alent sentences in English and Finnish, annotated with dependency trees following the guidelines of Universal Dependencies (UD) (Nivre et al., 2016, 2020), which assume words as elementary units. An alternative view, found in the seminal work of Tesni`ere (1959), is that dependency relations hold between slightly more complex units called nuclei, semantically independent units consisting of a con- tent word together with its grammatical markers, regardless of whether the latter are realized as in- dependent words or not. Thus, a nucleus will often correspond to a single word – as in the English verb chased, where tense is realized solely through mor- phological inflection – but it may also correspond to several words – as in the English verb group has chased, where tense is realized by morphologi- cal inflection in combination with an auxiliary verb. The latter type is known as a dissociated nucleus. If we assume that the elementary syntactic units of a dependency tree are nuclei rather than word forms, then the English and Finnish sentences will have the same dependency trees, visualized in Figure 2, and will differ only in the realization of their nuclei. In particular, while nominal nuclei in Finnish are consistently realized as single nouns inflected for case, the nominal nuclei in English involve stan- dalone articles and the preposition from. In this paper, we set out to investigate whether research on …

Content truncated to 500 words