Automatic extraction of subordinate clauses and its application in second language acquisition research

Abstract

Clause subordination is an important linguistic phenomenon that is relevant to research in psycholinguistics, cognitive and behavioral sciences, language acquisition, and computational information retrieval. The paper presents a comprehensive tool called AutoSubClause, which is specifically designed for extracting subordinate clause (SC) information from natural English production. Using dependency parsing, AutoSubClause is able to extract not only information characterizing the three main types of SCs-complement, adverbial, and relative clauses-but also information regarding the internal structure of different clause types and their semantic and structural relations with elements of the main clause. Robustness testing of the system and its underlying dependency parser Stanford CoreNLP showed satisfactory results. To demonstrate the usefulness of AutoSubClause, we used it to analyze a large-scale learner corpus and investigate the effects of first language (L1) on the acquisition of subordination in second language (L2) English. Our analysis shows that learners from an L1 that is typologically different from the L2 in clause subordination tend to have different developmental trajectories from those whose L1 is typologically similar to the L2. Furthermore, the developmental patterns for different types of SCs also vary. This finding suggests the need to approach clausal subordination as a multi-componential construct rather than a unitary one, as is the case in most previous research. Finally, we demonstrate how NLP technology can support research questions that rely on linguistic analysis across various disciplines and help gain new insights with the increasing opportunities for up-scaled analysis.

Examining the potential influence of crosslinguistic lexical similarity on word-choice transfer in L2 English

“…Finally, note that past studies on the EFCAMDAT found L1 transfer effects on various other linguistic structures and phenomena, including clause subordination [ 46 ], relative clauses [ 47 ], clause-initial prepositional phrases [ 48 ], grammatical morphemes [ 49 ], articles [ 50 ], and capitalization [ 44 ]. X. Jiang et al even found evidence of lexical transfer on the usage rates of certain punctuation marks (e.g., dashes) and phrases (e.g., “to my mind”) [ 48 ].…”

Dependency distance minimization: a diachronic exploration of the effects of sentence length and dependency types

“…A possible explanation for the decreasing tendencies in dependency distance of these three types is that they mark the subordinate clauses. A subordinate clause is embedded within a main clause and functions as a constituent of it (Cristofaro, 2003;Chen et al, 2021). Such a structure has been found to be one of the most important types of grammatical complexity and incur higher cognitive demand on language users (Carter and McCarthy, 2006;Chen et al, 2021).…”

“…A subordinate clause is embedded within a main clause and functions as a constituent of it (Cristofaro, 2003;Chen et al, 2021). Such a structure has been found to be one of the most important types of grammatical complexity and incur higher cognitive demand on language users (Carter and McCarthy, 2006;Chen et al, 2021). As a result, language users may be more pressurized and motivated to simplify such structures in order to reduce the higher processing cost resulted from it.…”

A dynamic domain ontology model based on the optimal matching method of network news

“…Extracting semantic information from unstructured text is crucial to understanding the components of a sentence. Chen et al extracted the complements, adverbials, and relational information of the essential component clause, as well as the semantic and internal structure relations of the sentence through dependent syntactic analysis, and proved through experiments that the subordinate relation of the clause is a multi-component structure rather than a single-component structure [7]. Dong et al used algebraic features and techniques to bridge the semantic gap by analyzing the semantic information of mathematical words, so as to provide a clear and complete solution to automatic mathematical problems.…”