A hybrid generative/discriminative framework to train a semantic parser from an un-annotated corpus

We propose a hybrid generative/discriminative framework for semantic parsing which combines the hidden vector state (HVS) model and the hidden Markov support vector machines (HM-SVMs). The HVS model is an extension of the basic discrete Markov model in which context is encoded as a stack-oriented state vector. The HM-SVMs combine the advantages of the hidden Markov models and the support vector machines. By employing a modified K-means clustering method, a small set of most representative sentences can be automatically selected from an un-annotated corpus. These sentences together with their abstract annotations are used to train an HVS model which could be subsequently applied on the whole corpus to generate semantic parsing results. The most confident semantic parsing results are selected to generate a fully-annotated corpus which is used to train the HM-SVMs. The proposed framework has been tested on the DARPA Communicator Data. Experimental results show that an improvement over the baseline HVS parser has been observed using the hybrid framework. When compared with the HM-SVMs trained from the fully-annotated corpus, the hybrid framework gave a comparable performance with only a small set of lightly annotated sentences. © 2008. Licensed under the Creative Commons.

Corpus-driven lexicography

This paper discusses three important aspects of John Sinclair’s legacy: the corpus, lexicography, and the notion of ‘corpus-driven’. The corpus represents his concern with the nature of linguistic evidence. Lexicography is for him the canonical mode of language description at the lexical level. And his belief that the corpus should ‘drive’ the description is reflected in his constant attempts to utilize the emergent computer technologies to automate the initial stages of analysis and defer the intuitive, interpretative contributions of linguists to increasingly later stages in the process. Sinclair’s model of corpus-driven lexicography has spread far beyond its initial implementation at Cobuild, to most EFL dictionaries, to native-speaker dictionaries (e.g. the New Oxford Dictionary of English, and many national language dictionaries in emerging or re-emerging speech communities) and bilingual dictionaries (e.g. Collins, Oxford-Hachette).

Issues in creating a corpus for EAP pedagogy and research

UK universities are accepting increasing numbers of students whose L1 is not English on a wide range of programmes at all levels. These students require additional support and training in English, focussing on their academic disciplines. Corpora have been used in EAP since the 1980s, mainly for research, but a growing number of researchers and practitioners have been advocating the use of corpora in EAP pedagogy, and such use is gradually increasing. This paper outlines the processes and factors to be considered in the design and compilation of an EAP corpus (e.g., the selection and acquisition of texts, metadata, data annotation, software tools and outputs, web interface, and screen displays), especially one intended to be used for teaching. Such a corpus would also facilitate EAP research in terms of longitudinal studies, student progression and development, and course and materials design. The paper has been informed by the preparatory work on the EAP subcorpus of the ACORN corpus project at Aston University. © 2007 Elsevier Ltd. All rights reserved.

Corpus linguistics

Corpora—large collections of written and/or spoken text stored and accessed electronically—provide the means of investigating language that is of growing importance academically and professionally. Corpora are now routinely used in the following fields: The production of dictionaries and other reference materials; The development of aids to translation; Language teaching materials; The investigation of ideologies and cultural assumptions; Natural language processing; and The investigation of all aspects of linguistic behaviour, including vocabulary, grammar and pragmatics.

A statistical analysis of regional variation in adverb position in a corpus of written Standard American English

This paper investigates whether the position of adverb phrases in sentences is regionally patterned in written Standard American English, based on an analysis of a 25 million word corpus of letters to the editor representing the language of 200 cities from across the United States. Seven measures of adverb position were tested for regional patterns using the global spatial autocorrelation statistic Moran’s I and the local spatial autocorrelation statistic Getis-Ord Gi*. Three of these seven measures were indentified as exhibiting significant levels of spatial autocorrelation, contrasting the language of the Northeast with language of the Southeast and the South Central states. These results demonstrate that continuous regional grammatical variation exists in American English and that regional linguistic variation exists in written Standard English.

Maritime expressions:a corpus based exploration of maritime metaphors

This study uses a purpose-built corpus to explore the linguistic legacy of Britain’s maritime history found in the form of hundreds of specialised ‘Maritime Expressions’ (MEs), such as TAKEN ABACK, ANCHOR and ALOOF, that permeate modern English. Selecting just those expressions commencing with ’A’, it analyses 61 MEs in detail and describes the processes by which these technical expressions, from a highly specialised occupational discourse community, have made their way into modern English. The Maritime Text Corpus (MTC) comprises 8.8 million words, encompassing a range of text types and registers, selected to provide a cross-section of ‘maritime’ writing. It is analysed using WordSmith analytical software (Scott, 2010), with the 100 million-word British National Corpus (BNC) as a reference corpus. Using the MTC, a list of keywords of specific salience within the maritime discourse has been compiled and, using frequency data, concordances and collocations, these MEs are described in detail and their use and form in the MTC and the BNC is compared. The study examines the transformation from ME to figurative use in the general discourse, in terms of form and metaphoricity. MEs are classified according to their metaphorical strength and their transference from maritime usage into new registers and domains such as those of business, politics, sports and reportage etc. A revised model of metaphoricity is developed and a new category of figurative expression, the ‘resonator’, is proposed. Additionally, developing the work of Lakov and Johnson, Kovesces and others on Conceptual Metaphor Theory (CMT), a number of Maritime Conceptual Metaphors are identified and their cultural significance is discussed.

Creation of a Digital Corpus of Bulgarian Dialects

The paper presents our considerations related to the creation of a digital corpus of Bulgarian dialects. The dialectological archive of Bulgarian language consists of more than 250 audio tapes. All tapes were recorded between 1955 and 1965 in the course of regular dialectological expeditions throughout the country. The records typically contain interviews with inhabitants of small villages in Bulgaria. The topics covered are usually related to such issues as birth, everyday life, marriage, family relationship, death, etc. Only a few tapes contain folk songs from different regions of the country. Taking into account the progressive deterioration of the magnetic media and the realistic prospects of data loss, the Institute for Bulgarian Language at the Academy of Sciences launched in 1997 a project aiming at restoration and digital preservation of the dialectological archive. Within the framework of this project more than the half of the records was digitized, de-noised and stored on digital recording media. Since then restoration and digitization activities are done in the Institute on a regular basis. As a result a large collection of sound files has been gathered. Our further efforts are aimed at the creation of a digital corpus of Bulgarian dialects, which will be made available for phonological and linguistic research. Such corpora typically include besides the sound files two basic elements: a transcription, aligned with the sound file, and a set of standardized metadata that defines the corpus. In our work we will present considerations on how these tasks could be realized in the case of the corpus of Bulgarian dialects. Our suggestions will be based on a comparative analysis of existing methods and techniques to build such corpora, and by selecting the ones that fit closer to the particular needs. Our experience can be used in similar institutions storing folklore archives, history related spoken records etc.

Automatic Generation of Titles for a Corpus of Questions

This paper describes the followed methodology to automatically generate titles for a corpus of questions that belong to sociological opinion polls. Titles for questions have a twofold function: (1) they are the input of user searches and (2) they inform about the whole contents of the question and possible answer options. Thus, generation of titles can be considered as a case of automatic summarization. However, the fact that summarization had to be performed over very short texts together with the aforementioned quality conditions imposed on new generated titles led the authors to follow knowledge-rich and domain-dependent strategies for summarization, disregarding the more frequent extractive techniques for summarization.

On the F word:a corpus-based analysis of the media representation of feminism in British and German press discourse, 1990-2009

Research in social psychology has shown that public attitudes towards feminism are mostly based on stereotypical views linking feminism with leftist politics and lesbian orientation. It is claimed that such attitudes are due to the negative and sexualised media construction of feminism. Studies concerned with the media representation of feminism seem to confirm this tendency. While most of this research provides significant insights into the representation of feminism, the findings are often based on a small sample of texts. Also, most of the research was conducted in an Anglo-American setting. This study attempts to address some of the shortcomings of previous work by examining the discourse of feminism in a large corpus of German and British newspaper data. It does so by employing the tools of Corpus Linguistics. By investigating the collocation profiles of the search term feminism, we provide evidence of salient discourse patterns surrounding feminism in two different cultural contexts. © The Author(s) 2012.

Bilingual Corpus - Digital Repository for Preservation of Language Heritage

The article briefly reviews bilingual Slovak-Bulgarian/Bulgarian-Slovak parallel and aligned corpus. The corpus is collected and developed as results of the collaboration in the frameworks of the joint research project between Institute of Mathematics and Informatics, Bulgarian Academy of Sciences, and Ľ. Štúr Institute of Linguistics, Slovak Academy of Sciences. The multilingual corpora are large repositories of language data with an important role in preserving and supporting the world's cultural heritage, because the natural language is an outstanding part of the human cultural values and collective memory, and a bridge between cultures. This bilingual corpus will be widely applicable to the contrastive studies of the both Slavic languages, will also be useful resource for language engineering research and development, especially in machine translation.

Linguistic Corpora as International Cultural Heritage: The Corpus of Bulgarian and Ukrainian Parallel Texts

The paper relates about our ongoing work on the creation of a corpus of Bulgarian and Ukrainian parallel texts. We discuss some differences in the approaches and the interpretation of some concepts, as well as various problems associated with the construction of our corpus, in particular the occasional ‘nonparallelism’ of original and translated texts. We give examples of the application of the parallel corpus for the study of lexical semantics and note the outstanding role of the corpus in the lexicographic description of Ukrainian and Bulgarian translation equivalents. We draw attention to the importance of creating parallel corpora as objects of national as well as global cultural heritage.

A corpus-assisted study of the discourse marker well as an indicator of judges' institutional roles in court cases with litigants in person

In this paper, I concentrate on court cases with litigants in person (lay people who act on their own behalf in legal proceedings without a counsel or solicitor) and discuss the challenges of building a corpus of courtroom discourse where it is crucial to distinguish between speakers due to their distinct institutional roles. The corpus incorporates seven sub-corpora of verbatim transcripts from different court cases with litigants in person and comprises over eleven-million tokens. The focus of this paper is on the interplay between the legal and lay discourse types and how judges project their institutional roles through well-initiated turns directed at litigants in person and counsels. As a versatile discourse marker, well provides a good opportunity to explore how judges have to adapt their roles to ensure lay litigants in person receive the necessary support and that their lack of competence does not impede on the fairness of the proceedings. Given the breadth and importance of the topic of litigation in person, I discuss how the tools and approaches of corpus linguistics can be helpful in this multi-disciplinary area where multiple functions and uses of individual linguistic features need to be explored in depth.

Resveratrol stimulates hydrogen sulfide (H2S) formation to relax murine corpus cavernosum

Introduction: Resveratrol (RVT) found in red wine protects against erectile dysfunction and relaxes penile tissue (corpus cavernosum) via a nitric oxide (NO) independent pathway. However, the mechanism remains to be elucidated. Hydrogen sulfide (H2S) is a potent vasodilator and neuromodulator generated in corpus cavernosum. Aims: We investigated whether RVT caused the relaxation of mice corpus cavernosum (MCC) through H2S. Methods: H2S formation is measured by methylene blue assay and vascular reactivity experiments have been performed by DMT strip myograph in CD1 MCC strips. Main Outcome Measures: Endothelial NO synthase (eNOS) inhibitor Nω-Nitro-L-arginine (L-NNA, 0.1mM) or H2S inhibitor aminooxyacetic acid (AOAA, 2mM) which inhibits both cystathionine-β-synthase (CBS) and cystathionine-gamma-lyase (CSE) enzyme or combination of AOAA with PAG (CSE inhibitor) has been used in the presence/absence of RVT (0.1mM, 30min) to elucidate the role of NO or H2S pathways on the effects of RVT in MCC. Concentration-dependent relaxations to RVT, L-cysteine, sodium hydrogen sulfide (NaHS) and acetylcholine (ACh) were studied. Results: Exposure of murine corpus cavernosum to RVT increased both basal and L-cysteine-stimulated H2S formation. Both of these effects were reversed by AOAA but not by L-NNA. RVT caused concentration-dependent relaxation of MCC and that RVT-induced relaxation was significantly inhibited by AOAA or AOAA+PAG but not by L-NNA. L-cysteine caused concentration-dependent relaxations, which are inhibited by AOAA or AOAA+PAG significantly. Incubation of MCC with RVT significantly increased L-cysteine-induced relaxation, and this effect was inhibited by AOAA+PAG. However, RVT did not alter the effect of exogenous H2S (NaHS) or ACh-induced relaxations. Conclusions: These results demonstrate that RVT-induced relaxation is at least partly dependent on H2S formation and acts independent of eNOS pathway. In phosphodiesterase 5 inhibitor (PDE-5i) nonresponder population, combination therapy with RVT may reverse erectile dysfunction via stimulating endogenous H2S formation. Yetik-Anacak G, Dereli MV, Sevin G, Ozzayim O, Erac Y, and Ahmed A. Resveratrol stimulates hydrogen sulfide (H2S) formation to relax murine corpus cavernosum.