Building an HPSG Chinese grammar (Zhong)

Abstract

This thesis describes the development of Zhong, a computational resource grammar for Chinese, in the framework of Head-driven Phrase Structure Grammar (HPSG: Pollard & Sag, 1994) using Minimal Recursion Semantics (Copestake et al., 2005). In order to increase the grammar's coverage for practical applications, a corpus-driven approach was adopted to systematically expand its lexical and syntactic coverage. The lexicon was expanded through semi-automatic learning lexical entries from an annotated Chinese corpus. Various language phenomena commonly observed in corpora have been analyzed and modeled in the grammar, especially those involving the particle 的 DE. The entire grammar and associated tools are available under an open-source license. A treebank with 798 sentences has been built with the parse trees from the grammar's output. With appropriate trees manually selected from the parses, the treebank was used as a gold standard to train a statistical model which can be used to rank the grammar's output parse trees, both to improve its performance in applications and to be helpful to grammar engineers during development and debugging. To evaluate the grammar's suitability to support applications like grammar feedback systems for second language learners, a small extension of the grammar is also built with MALrules and MAL-types to enable the parsing of sentences containing grammatical errors and detecting the specific errors. The information provided by the grammar would thus allow the feedback system to identify the errors and give appropriate suggestions to the learner.

Using rich models of language in grammatical error detection

“…ZHONG (Fan et al, 2015a,b;Fan, 2019) is an open-source HPSG computational grammar based on the LinGO Grammar Matrix system (Bender et al, , 2010, producing MRS semantics.…”

“…ZHONG was born through the adaptation of ManGO: Mandarin Grammar Online (Flickinger and Yang, 2011), first started in 2011. This adaptation was done by Fan Zhenzhen (Fan, 2019), as the focus of her PhD studies at NTU. During this cycle of development, ZHONG was expanded from a 'toy grammar' (with an extremely limited vocabulary) to a 'resource grammar' -a computational resource aiming to cover naturally occurring language, so it could be used in a variety of Natural Language Processing tasks.…”

“…Basic verb-frames provided by the English Princeton WordNet (Fellbaum, 1998) were used to provide fine-grained mapping of verbal types. However, due to the coarse nature of verbframes provided by the Princeton WordNet, the process was noisy -introducing many erroneous lexical entries that were left to be checked in the future (Fan, 2019).…”

“…This chapter presents the main contributions made to the ZHONG (Fan, 2019) -an open-source HPSG grammar for Mandarin Chinese. The nature of these contributions vary widely, and include bug-fixes, reanalyses of certain phenomena, implementation of missing phenomena and, of course, the implementation of mal-rules.…”

“…For Mandarin Chinese, where existing technology was less mature, I have both improved an existing Mandarin Chinese grammar (Fan et al, 2015a,b;Fan, 2019) and introduced dozens of mal-rules, effectively transforming it into a full-fledged error detection system.…”