Spain

The Universal Dependencies treebanks are a still-growing collection of treebanks for a wide range of languages, all annotated with a common inventory of dependency relations. Yet, the usages of the relations can be categorically different even for treebanks of the same language. We present a pilot study on identifying such inconsistencies in a language-independent way and conduct an experiment which illustrates that a proper handling of inconsistencies can improve parsing performance by several percentage points.

COLING 2020

Identifying and Handling Cross-Treebank Inconsistencies in UD: A Pilot Study

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

technical paper

The UD framework defines guidelines for a crosslingual syntactic analysis in the framework of dependency grammar, with the aim of providing a consistent treatment across languages that not only supports multilingual NLP applications but also facilitates typological studies. In the paper, we discuss possible UD treatments for several types of constructions encountered when branching out into the annotation of social media or spoken-language data. The examples include constructions where surface relations are deceptive, and constructions that either involve unconnected subtrees or structures with multiply-headed dependents. We argue that a unified treatment of constructions across languages will increase the consistency of the UD annotations and thus the quality of the treebanks for linguistic analysis.

I got a construction looks funny - Representing and recovering non-standard constructions in UD

In this presentation we look at how to compose word representations from token embeddings obtained from BPE sub-word tokens, so we can analyse the grammatical features of words. We explore four different methods of composing word representations and find that using an RNN performs the best consistently across eight different languages with varying typology and tokens-per-word ratio.

Composing Byte-Pair Encodings for Morphological Sequence Classification

In this presentation, we examine three types of multiword expressions (compound, fixed and flat) in the Irish UD Treebank. We provide guidelines on how these labels were applied in the Irish treebank, and discuss how some of our findings will be explored in future work.

Annotating MWEs in the Irish UD Treebank

We use Universal Dependencies treebanks to test whether a well-known typological trade-off between word order freedom and richness of morphological marking of core arguments holds within individual languages. Using Russian and German treebank data, we show that the following phenomenon (sometimes dubbed word order freezing) does occur: those sentences where core arguments cannot be distinguished by morphological means (due to case syncretism or other kinds of ambiguity) have more rigid order of subject, verb and object than those where unambiguous morphological marking is present. In ambiguous clauses, word order is more often equal to the one which is default or dominant (most frequent) in the language. While Russian and German differ with respect to how exactly they mark core arguments, the effect of morphological ambiguity is significant in both languages. It is, however, small, suggesting that languages do adapt to the evolutionary pressure on communicative efficiency and avoidance of redundancy, but that the pressure is weak in this particular respect.

Corpus evidence for word order freezing in Russian and German

In this paper, we introduce Profiling-UD, a new text analysis tool inspired to the principles of linguistic profiling that can support language variation research from different perspectives. It allows the extraction of more than 130 features, spanning across different levels of linguistic description. Beyond the large number of features that can be monitored, a main novelty of Profiling-UD is that it has been specifically devised to be multilingual since it is based on the Universal Dependencies framework. In the second part of the paper, we demonstrate the effectiveness of these features in a number of theoretical and applicative studies in which they were successfully used for text and author profiling.

Profiling--UD: a Tool for Linguistic Profiling of Texts

This article considers the annotation of subjects in UD treebanks. The identification of the subject poses a particular problem in Wolof, due to pronominal indices whose status as a pronoun or a pronominal affix is uncertain. In the UD treebank available for Wolof (Dione, 2019), these have been annotated depending on the construction either as true subjects, or as morphosyntactic features agreeing with the verb. The study of this corpus of 40 000 words allows us to show that the problem is indeed difficult to solve, especially since Wolof has a rich system of auxiliaries and several basic constructions with different properties. Before addressing the case of Wolof, we will present the simpler, but partly comparable, case of French, where subject clitics also tend to behave like affixes, and subjecthood can move from the preverbal to the detached position. We will also make a several annotation recommendations that would avoid overwriting information regarding subjecthood.

Subjecthood and annotation: The cases of French and Wolof

We revisit the problem of extracting dependency structures from the derivation structures of Combinatory Categorial Grammar (CCG). Previous approaches are often restricted to a narrow subset of CCG or support only one flavor of dependency tree. Our approach is more general and easily configurable, so that multiple styles of dependency tree can be obtained. In an initial case study, we show promising results for converting English, German, Italian, and Dutch CCG derivations from the Parallel Meaning Bank into (unlabeled) UD-style dependency trees.

Configurable Dependency Tree Extraction from CCG Derivations

As in any field of inquiry that depends on experiments, the verifiability of experimental studies is important in computational linguistics. Despite increased attention to verification of empirical results, the practices in the field are unclear. Furthermore, we argue, certain traditions and practices that are seemingly useful for verification may in fact be counterproductive. We demonstrate this through a set of multi-lingual experiments on parsing Universal Dependencies treebanks. In particular, we show that emphasis on exact replication leads to practices (some of which are now well established) that hide the variation in experimental results, effectively hindering verifiability with a false sense of certainty. The purpose of the present paper is to highlight the magnitude of the issues resulting from these common practices with the hope of instigating further discussion. Once we, as a community, are convinced about the importance of the problems, the solutions are rather obvious, although not necessarily easy to implement. \end{abstract}


Verification, Reproduction and Replication of NLP Experiments: a Case Study on Parsing Universal Dependencies

The topic of this presentation is a rule-based pipeline for converting constituency treebanks based on the Penn Treebank format to Universal Dependencies (UD). We describe the conversion process, the methods used to deliver a fully automated UD corpus and complications involved. An Icelandic constituency treebank is converted to a UD corpus, and the converter extended to convert a Faroese constituency treebank. The result is an open-source conversion tool, published under an Apache 2.0 license, applicable to a Penn-style treebank for conversion to a UD corpus, along with two new UD corpora, an Icelandic one and a Faroese one. Both are included in version 2.7 of UD.

A Universal Dependencies Conversion Pipeline for a Penn-format Constituency Treebank

To investigate issues that arise in the process of developing a Universal Dependency (UD) treebank for Korean and Japanese, we begin by addressing the typological characteristics of Korean and Japanese. Both Korean and Japanese are agglutinative and head-final languages. And the principle of word segmentation for both languages is different from English, which makes it difficult to apply UD guidelines. Following the typological characteristics of the two languages and the issue of UD application, we review the application of UPOS and DEPREL schemes to the two languages. The annotation principles for AUX, ADJ, DET, ADP and PART are discussed for the UPOS scheme, and the annotation principles for case, aux, iobj, and obl are discussed for the DEPREL scheme.

Identifying and Handling Cross-Treebank Inconsistencies in UD: A Pilot Study

Downloads

Next from COLING 2020

I got a construction looks funny - Representing and recovering non-standard constructions in UD

Similar lecture

5. Sense Embeddings

Identifying and Handling Cross-Treebank Inconsistencies in UD: A Pilot Study

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

I got a construction looks funny - Representing and recovering non-standard constructions in UD

Similar lecture

5. Sense Embeddings

Downloads