Search

Automatic syntactic analysis of a corpus requires detailed lexical and morphological information that cannot always be harvested from traditional dictionaries. Therefore the development of a treebank presents an opportunity to simultaneously enrich the lexicon. In building NorGramBank, we use an incremental parsebanking approach, in which a corpus is parsed and disambiguated, and after improvements to the grammar and the lexicon, reparsed. In this context we have implemented a text preprocessing interface where annotators can enter unknown words or missing lexical information either before parsing or during disambiguation. The information added to the lexicon in this way may be of great interest both to lexicographers and to other language technology efforts. [ABSTRACT FROM AUTHOR]

We present a syntactic parser of (transcripts of) spoken Hebrew: a dependency parser of the Hebrew CHILDES database. CHILDES is a corpus of child-adult linguistic interactions. Its Hebrew section has recently been morphologically analyzed and disambiguated, paving the way for syntactic annotation. This paper describes a novel annotation scheme of dependency relations reflecting constructions of child and child-directed Hebrew utterances. A subset of the corpus was annotated with dependency relations according to this scheme, and was used to train two parsers (MaltParser and MEGRASP) with which the rest of the data were parsed. The adequacy of the annotation scheme to the CHILDES data is established through numerous evaluation scenarios. The paper also discusses different annotation approaches to several linguistic phenomena, as well as the contribution of morphological features to the accuracy of parsing. [ABSTRACT FROM AUTHOR]

Obtaining syntactic parses is an important step in many NLP pipelines. However, most of the world's languages do not have a large amount of syntactically annotated data available for building parsers. Syntactic projection techniques attempt to address this issue by using parallel corpora consisting of resource-poor and resource-rich language pairs, taking advantage of a parser for the resource-rich language and word alignment between the languages to project the parses onto the data for the resource-poor language. These projection methods can suffer, however, when syntactic structures for some sentence pairs in the two languages look quite different. In this paper, we investigate the use of small, parallel, annotated corpora to automatically detect divergent structural patterns between two languages. We then use these detected patterns to improve projection algorithms and dependency parsers, allowing for better performing NLP tools for resource-poor languages, particularly those that may not have large amounts of annotated data necessary for traditional, fully-supervised methods. While this detection process is not exhaustive, we demonstrate that common patterns of divergence can be identified automatically without prior knowledge of a given language pair, and the patterns can be used to improve performance of syntactic projection and parsing. [ABSTRACT FROM AUTHOR]

We present HamleDT-a HArmonized Multi-LanguagE Dependency Treebank. HamleDT is a compilation of existing dependency treebanks (or dependency conversions of other treebanks), transformed so that they all conform to the same annotation style. In the present article, we provide a thorough investigation and discussion of a number of phenomena that are comparable across languages, though their annotation in treebanks often differs. We claim that transformation procedures can be designed to automatically identify most such phenomena and convert them to a unified annotation style. This unification is beneficial both to comparative corpus linguistics and to machine learning of syntactic parsing. [ABSTRACT FROM AUTHOR]

There are two different levels of interoperability for language resources: operational interoperability and conceptual interoperability. The former refers to the standardization of the formal aspects of language resources so that different resources can work together. The latter refers to the standardization of the notional representation of the semantic content of the analysis. This article addresses both issues but focuses on the latter through a description of the annotation and analysis of the International Corpus of English, which is a corpus for the study of English as a global language. The project is parameterised by component, regional sub-corpora and a set of pre-defined textual categories. The one-million-word British component has been constructed, grammatically tagged, and syntactically parsed. This article is first of all a description of steps taken to ensure conformity within the project. These include corpus design, part-of-speech tagging, and syntactic parsing. The article will then present a study that examines the use of adverbial clauses across speech and writing, illustrating the imminent necessity for interoperable analysis of linguistic data. [ABSTRACT FROM AUTHOR]

We introduce LTAG-spinal, a novel variant of traditional Lexicalized Tree Adjoining Grammar (LTAG) with desirable linguistic, computational and statistical properties. Unlike in traditional LTAG, subcategorization frames and the argument–adjunct distinction are left underspecified in LTAG-spinal. LTAG-spinal with adjunction constraints is weakly equivalent to LTAG. The LTAG-spinal formalism is used to extract an LTAG-spinal Treebank from the Penn Treebank with Propbank annotation. Based on Propbank annotation, predicate coordination and LTAG adjunction structures are successfully extracted. The LTAG-spinal Treebank makes explicit semantic relations that are implicit or absent from the original PTB. LTAG-spinal provides a very desirable resource for statistical LTAG parsing, incremental parsing, dependency parsing, and semantic parsing. This treebank has been successfully used to train an incremental LTAG-spinal parser and a bidirectional LTAG dependency parser. [ABSTRACT FROM AUTHOR]

Unsupervised morphological analysis is the task of segmenting words into prefixes, suffixes and stems without prior knowledge of language-specific morphotactics and morpho-phonological rules. This paper introduces a simple, yet highly effective algorithm for unsupervised morphological learning for Bengali, an Indo–Aryan language that is highly inflectional in nature. When evaluated on a set of 4,110 human-segmented Bengali words, our algorithm achieves an F-score of 83%, substantially outperforming Linguistica, one of the most widely-used unsupervised morphological parsers, by about 23%. [ABSTRACT FROM AUTHOR]

Spoken monologues feature greater sentence length and structural complexity than spoken dialogues. To achieve high-parsing performance for spoken monologues, simplifying the structure by dividing a sentence into suitable language units could prove effective. This paper proposes a method for dependency parsing of Japanese spoken monologues based on sentence segmentation. In this method, dependency parsing is executed in two stages: at the clause level and the sentence level. First, dependencies within a clause are identified by dividing a sentence into clauses and executing stochastic dependency parsing for each clause. Next, dependencies across clause boundaries are identified stochastically, and the dependency structure of the entire sentence is thus completed. An experiment using a spoken monologue corpus shows the effectiveness of this method for efficient dependency parsing of Japanese monologue sentences. [ABSTRACT FROM AUTHOR]