Parsing Morphologically Rich Languages: Introduction to the Special Issue

Abstract

International audienceParsing is a key task in natural language processing. It involves predicting, for each natural language sentence, an abstract representation of the grammatical entities in the sentence and the relations between these entities. This representation provides an interface to compositional semantics and to the notions of "who did what to whom." The last two decades have seen great advances in parsing English, leading to major leaps also in the performance of applications that use parsers as part of their backbone, such as systems for information extraction, sentiment analysis, text summarization, and machine translation. Attempts to replicate the success of parsing English for other languages have often yielded unsatisfactory results. In particular, parsing languages with complex word structure and flexible word order has been shown to require non-trivial adaptation. This special issue reports on methods that successfully address the challenges involved in parsing a range of morphologically rich languages (MRLs). This introduction characterizes MRLs, describes the challenges in parsing MRLs, and outlines the contributions of the articles in the special issue. These contributions present up-to-date research efforts that address parsing in varied, cross-lingual settings. They show that parsing MRLs addresses challenges that transcend particular representational and algorithmic choices

Textual Analysis in Accounting and Finance: A Survey

“…Tsarfaty et al. [] and Das and Banerjee [] provide examples of challenges from alternative languages. For example, the German language is much more structured than English, but also suffers from syncretism, which is the case where a word form serves multiple grammatical purposes (e.g., in English, “bid” is both present and past tense).…”

Redefining ‘Chinese’ L1 in SLP: Considerations for the assessment of Chinese bilingual/bidialectal language skills

“…English and other Romance languages, due to their richness in morphological inflections and/or derivations (Tsarfaty, Seddah, Kübler, & Nivre, 2013), have provided SLPs with great opportunities to study morphological markers that may signal language impairment across languages. In turn, most cross-linguistic studies of the morphosyntactic aspects of language impairment focus on morphological problems such as inflections and/or tense marking rather than syntactic issues (Paradis, Crago, & Genesee, 2005).…”

Exploiting Language Variants Via Grammar Parsing Having Morphologically Rich Information

“…The experiments were performed to identify the parsing issues of Urdu and a development of parser was not claimed. Moreover, these data-driven systems are highly criticized on a given set of annotated corpus because they are not able to observe all morphological variants of a word form from it (Tsarfaty et al, 2013).…”

“…Complex morphosyntactic interactions may impose constraints, which lead to explicit encoding of such information. The best broad coverage and robust parsers to date have grammars extracted from treebanks and the depth of information encoded in an annotation correlates with the parsing performance (Tsarfaty et al, 2013).…”