Journal of Language Modelling

QRGS – Question Responses Generation via crowdsourcing

Paweł Łupkowski — 2024-09-03

QRGS stands for the Question Responses Generation System. It is an online game-like framework designed for gathering various types of question responses. A QRGS user is asked to read a simple story and impersonate its main character. As the story unfolds the user is confronted with four questions and (s)he is expected to answer these in the way the main character would. In this way, we obtain responses to questions of a desired type. The data gathered via QRGS is a useful supplement to the linguistic data already present in language corpora – especially for languages for which such resources are sparse. As such, it opens the possibility for better understanding of the use of questions in natural language dialogues and analysing the response space of such questions. In this paper, we present the main idea of QRGS and the results of five studies (in Polish and in English) that test the framework. Our discussion addresses issues concerning the efficiency and accuracy of the proposed approach. We also discuss the availability of the QRGS and its potential future improvements.

The expected sum of edge lengths in planar linearizations of trees

Lluís Alemany-Puig — 2024-02-27

Dependency trees have proven to be a very successful model to represent the syntactic structure of sentences of human languages. In these structures, vertices are words and edges connect syntacticallydependent words. The tendency of these dependencies to be short has been demonstrated using random baselines for the sum of the lengths of the edges or their variants. A ubiquitous baseline is the expected sum in projective orderings (wherein edges do not cross and the root word of the sentence is not covered by any edge), that can be computed in time O(n). Here we focus on a weaker formal constraint, namely planarity. In the theoretical domain, we present a characterization of planarity that, given a sentence, yields either the number of planar permutations or an efficient algorithm to generate uniformly random planar permutations of the words. We also show the relationship between the expected sum in planar arrangements and the expected sum in projective arrangements. In the domain of applications, we derive a O(n)-time algorithm to calculate the expected value of the sum of edge lengths. We also apply this research to a parallel corpus and find that the gap between actual dependency distance and the random baseline reduces as the strength of the formal constraint on dependency structures increases, suggesting that formal constraints absorb part of the dependency distance minimization effect. Our research paves the way for replicating past research on dependency distance minimization using random planar linearizations as random baseline.

Detecting inflectional patterns for Croatian verb stems using class activation mappings

Domagoj Ševerdija — 2024-05-21

All verbal forms in the Croatian language can be derived from two basic forms: the infinitive and the present stems. In this paper, we present a neural computation model that takes a verb in an infinitive form and finds a mapping to a present form. The same model can be applied vice-versa, i.e. map a verb from its present form to its infinitive form. Knowing the present form of a given verb, one can deduce its inflections using grammatical rules. We experiment with our model on the Croatian language, which belongs to the Slavic group of languages. The model learns a classifier through these two classification tasks and uses class activation mapping to find characters in verbs contributing to classification. The model detects patterns that follow established grammatical rules for deriving the present stem form from the infinitive stem form and vice-versa. If mappings can be found between such slots, the rest of the slots can be deduced using a rule-based system.

Control, inner topicalisation, and focus fronting in Mandarin Chinese: modelling in parallel constraint-based grammatical architecture

Chit-Fung Lam — 2024-06-14

This paper proposes a formal analysis of two displacement phenomena in Mandarin Chinese, namely inner topicalisation and focus fronting, capturing their correlational relationships with control and complementation. It examines a range of relevant data, including corpus examples, to derive empirical generalisations. Acceptability-judgment tasks, followed by mixed-effects statistical models, were conducted to provide additional evidence. This paper presents a constraint-based lexicalist proposal that is couched in the framework of Lexical-Functional Grammar (LFG). The lexicon plays an important role in regulating the behaviour of complementation verbs as they participate in the displacement phenomena. Unlike previous analyses that cast inner topicalisation and focus fronting as restructuring phenomena, this lexicalist proposal does not rely on hypothesised clause-size differences. It captures the empirical properties more accurately and accounts for a wider range of empirical patterns. Adopting the formally explicit framework of LFG, this proposal uses constraints that have mathematical precision. The constraints are computationally implemented using the grammar engineering tool Xerox Linguistic Environment, safeguarding their precision.

On German verb sense disambiguation: A three-part approach based on linking a sense inventory (GermaNet) to a corpus through annotation (TGVCorp) and using the corpus to train a VSD classifier (TTvSense)

Dominik Mattern — 2024-09-03

We develop a three-part approach to Verb Sense Disambiguation (VSD) in German. After considering a set of lexical resources and corpora, we arrive at a statistically motivated selection of a subset of verbs and their senses from GermaNet. This sub-inventory is then used to disambiguate the occurrences of the corresponding verbs in a corpus resulting from the union of TüBa-D/Z, Salsa, and E-VALBU. The corpus annotated in this way is called TGVCorp. It is used in the third part of the paper for training a classifier for VSD and for its comparative evaluation with a state-of-the-art approach in this research area, namely EWISER. Our simple classifier outperforms the transformer-based approach on the same data in both accuracy and speed in German but not in English and we discuss possible reasons.