This paper introduces the first version of the Arabic Learner Corpus (ALC), which comprises a collection of texts written by learners of Arabic in Saudi Arabia. The corpus covers two types of students, non-native Arabic speakers (NNAS) learning Arabic as a second language (ASL) for academic purpose (AAP), and native Arabic speaking students (NAS) learning to improve their written Arabic. Both groups are males at pre- university level.

In cognitive science, results are obtained following the manipulation of one stimulus' variable and the control of potential confounding variables. To avoid the tedious task of measuring confounding effects, scientists often refer to normative sets of stimuli. The Bank of Standardized Stimuli (BOSS) is one of these sets. It initially included 480 normative stimuli of common objects and norms for seven variables (name, category, familiarity, visual complexity, object's typicality, manipulability and orientation). The BOSS has expanded and provides a wider variety of stimuli in order to fulfill the needs of experiments. To date, the latest version of the BOSS is comprised of 1,420 normative stimuli, including photos of animals, and new norms (color diagnositicity, symmetry, and action related norms). In order to demonstrate the influence of normative variables on cognitions, experiments on episodic memory were completed using the BOSS. Analyses were conducted as a function of the norms and indicated that name agreement, visual complexity, object/viewpoint agreement, symmetry, and color diagnosticity all influenced memory in distinct ways mostly by affecting the performance to new stimuli and by inducing response biases.

A comprehensive count of bigram and trigram frequencies and versatilities was tabulated for words recorded by Ku{\v{c}}era and Francis. Totals of 577 different bigrams and 6,140 different trigrams were found. Their frequencies of occurrence and the number of different words in which they appeared are reported in this article.

A set of rating data was collected which compared the visual similarity of consonants to the auditory similarity of the same letters. Analysis of the rating patterns raises important questions about the use of similarity data in drawing conclusions about mode of memory coding in a variety of situations.

Written word frequency (e.g., Francis {\&} Kucera, 1982; Kucera {\&} Francis, 1967) constitutes a popular measure of word familiarity, which is highly predictive of word recognition. Far less often, researchers employ spoken frequency counts in their studies. This discrepancy can be attributed most readily to the conspicuous absence of a sizeable spoken frequency count for American English. The present article reports the construction of a 1.6-million-word spoken frequency database derived from the Michigan Corpus of Academic Spoken English (Simpson, Swales, {\&} Briggs, 2002). We generated spoken frequency counts for 34,922 words and extracted speaker attributes from the source material to generate relative frequencies of words spoken by each speaker category. We assess the predictive validity of these counts, and discuss some possible applications outside of word recognition studies.

Corpora are an important resource for both teaching and research. Arabic lacks sufficient resources in this field, so a research project has been designed to compile a corpus, which represents the state of the Arabic language at the present time and the needs of end-users. This report presents the result of a survey of the needs of teachers of Arabic as a foreign language (TAFL) and language engineers. The survey shows that a wide range of text types should be included in the corpus. Overall, our survey confirms our view that existing corpora are too narrowly limited in source-type and genre, and that there is a need for a freely-accessible corpus of contemporary Arabic covering a broad range of text-types. We have collected and published an initial version of the Corpus of Contemporary Arabic (CCA) to meet these design issues. The CCA is freely downloadable via WWW from http://www.comp.leeds.ac.uk/arabic.

CVCVC (319) words and paralogs previously assessed for associative reaction time (RT) by Taylor and Kimble were assessed for rated frequency (a′) and scaled rated meaningfulness (m′) following procedures used by Noble. Reliability of the a′ scale, based on three intergroup correlations, resulted in rs of .92, .90 and .89. Reliability of the m′ scale, based on an internal consistency test resulted in a mean discrepancy between the 128 empirical proportions and their corresponding theoretical proportions of 2.4; that is, the average error of reproducing all the original data from m′ scaled values was 2.4{\%}. The r between m′ and RT was .71.

Word associations to 40 homographic stimuli were scored in terms of the semantic features serving as S's apparent functional stimulus, and hierarchies related to the separate sets of features of homographs were determined. For most homographs the dominant meaning in the associative hierarchy was the more frequently occurring meaning in semantic counts, a finding in agreement with a spew-like principle of perceiving homographic stimuli.

Alfred Castaneda, Leila Snyder Fahel, Richard Odom, Associative Characteristics of Sixty-Three Adjectives and Their Relation to Verbal Paired-Associate Learning in Children, Child Development, Vol. 32, No. 2 (Jun., 1961), pp. 297-304

Semantic role labeling is traditionally viewed as a sentence-level task concerned with identifying semantic arguments that are overtly realized in a fairly local context (i.e., a clause or sentence). However, this local view potentially misses important information that can only be recovered if local argument structures are linked across sentence boundaries. One important link concerns semantic arguments that remain locally unrealized (null instantiations) but can be inferred from the context. In this paper, we report on the SemEval 2010 Task-10 on “Linking Events and Their Participants in Discourse”, that addressed this problem. We discuss the corpus that was created for this task, which contains annotations on multiple levels: predicate argument structure (FrameNet and PropBank), null instantiations, and coreference. We also provide an analysis of the task and its difficulties.

This article describes the creation and application of the Turk Bootstrap Word Sense Inventory for 397 frequent nouns, which is a publicly available resource for lexical substitution. This resource was acquired using Amazon Mechanical Turk. In a bootstrapping process with massive collaborative input, substitutions for target words in context are elicited and clustered by sense; then, more contexts are collected. Contexts that cannot be assigned to a current target word’s sense inventory re-enter the bootstrapping loop and get a supply of substitutions. This process yields a sense inventory with its granularity determined by substitutions as opposed to psychologically motivated concepts. It comes with a large number of sense-annotated target word contexts. Evaluation on data quality shows that the process is robust against noise from the crowd, produces a less fine-grained inventory than WordNet and provides a rich body of high precision substitution data at low cost. Using the data to train a system for lexical substitutions, we show that amount and quality of the data is sufficient for producing high quality substitutions automatically. In this system, co-occurrence cluster features are employed as a means to cheaply model topicality.

We introduce the ACL Anthology Network (AAN), a comprehensive manually curated networked database of citations, collaborations, and summaries in the field of Computational Linguistics. We also present a number of statistics about the network including the most cited authors, the most central collaborators, as well as network statistics about the paper citation, author citation, and author collaboration networks.

Social media is a natural laboratory for linguistic and sociological purposes. In micro-blogging platforms such as Twitter, people share hundreds of millions of short messages about their lives and experiences on a daily basis. These messages, coupled with metadata about their authors, provide an opportunity to understand a wide variety of phenomena ranging from political polarization to geographic and demographic lexical variation. Lack of publicly available micro-blogging datasets has been a hindrance to replicable research. In this paper, I introduce Rovereto Twitter n-gram corpus, a publicly available n-gram dataset of Twitter messages, which contains gender-of-the-author and time-of-posting tags associated with the n-grams. I compare this dataset to a more traditional web-based corpus and present a case study which shows the potential of combining an n-gram corpus with demographic metadata.

We present a corpus of transcribed spoken Hebrew that reflects spoken interactions between children and adults. The corpus is an integral part of the CHILDES database, which distributes similar corpora for over 25 languages. We introduce a dedicated transcription scheme for the spoken Hebrew data that is sensitive to both the phonology and the standard orthography of the language. We also introduce a morphological analyzer that was specifically developed for this corpus. The analyzer adequately covers the entire corpus, producing detailed correct analyses for all tokens. Evaluation on a new corpus reveals high coverage as well. Finally, we describe a morphological disambiguation module that selects the correct analysis of each token in context. The result is a high-quality morphologically-annotated CHILDES corpus of Hebrew, along with a set of tools that can be applied to new corpora.

Literature review on prosody reveals the lack of corpora for prosodic studies in Catalan and Spanish. In this paper, we present a corpus intended to fill this gap. The corpus comprises two distinct data-sets, a news subcorpus and a dialogue subcorpus, the latter containing either conversational or task-oriented speech. More than 25 h were recorded by twenty eight speakers per language. Among these speakers, eight were professional (four radio news broadcasters and four advertising actors). The entire material presented here has been transcribed, aligned with the acoustic signal and prosodically annotated. Two major objectives have guided the design of this project: (i) to offer a wide coverage of representative real-life communicative situations which allow for the characterization of prosody in these two languages; and (ii) to conduct research studies which enable us to contrast the speakers different speaking styles and discursive practices. All material contained in the corpus is provided under a Creative Commons Attribution 3.0 Unported License.

The impact-es diachronic corpus of historical Spanish compiles over one hundred books—containing approximately 8 million words—in addition to a complementary lexicon which links more than 10,000 lemmas with attestations of the different variants found in the documents. This textual corpus and the accompanying lexicon have been released under an open license (Creative Commons by-nc-sa) in order to permit their intensive exploitation in linguistic research. Approximately 7 % of the words in the corpus (a selection aimed at enhancing the coverage of the most frequent word forms) have been annotated with their lemma, part of speech, and modern equivalent. This paper describes the annotation criteria followed and the standards, based on the Text Encoding Initiative recommendations, used to represent the texts in digital form.

Short Message Service (SMS) messages are short messages sent from one person to another from their mobile phones. They represent a means of personal communication that is an important communicative artifact in our current digital era. As most existing studies have used private access to SMS corpora, comparative studies using the same raw SMS data have not been possible up to now. We describe our efforts to collect a public SMS corpus to address this problem. We use a battery of methodologies to collect the corpus, paying particular attention to privacy issues to address contributors’ concerns. Our live project collects new SMS message submissions, checks their quality, and adds valid messages. We release the resultant corpus as XML and as SQL dumps, along with monthly corpus statistics. We opportunistically collect as much metadata about the messages and their senders as possible, so as to enable different types of analyses. To date, we have collected more than 71,000 messages, focusing on English and Mandarin Chinese.

In recent years, building reference speech corpora was an important part of the activities which provided the necessary linguistic infrastructure in many European countries, for languages with many speakers (e.g., French, German, Spanish, Italian) as well as for those with smaller numbers of speakers (e.g., Swedish, Dutch, Czech, Slovak). This paper describes the process of the creation of a reference speech corpus and its distribution to potential users, as it was done in the case of the Slovene corpus GOS. The corpus structure and fieldwork experiences with recording, labelling system, and two levels of transcription (pronunciation-based and standardized) are described, as well as the main characteristics of the corpus interface (web concordancer) and the availability of the original corpus files.

Extraction and normalization of temporal expressions from documents are important steps towards deep text understanding and a prerequisite for many NLP tasks such as information extraction, question answering, and document summarization. There are different ways to express (the same) temporal information in documents. However, after identifying temporal expressions, they can be normalized according to some standard format. This allows the usage of temporal information in a term- and language-independent way. In this paper, we describe the challenges of temporal tagging in different domains, give an overview of existing annotated corpora, and survey existing approaches for temporal tagging. Finally, we present our publicly available temporal tagger HeidelTime, which is easily extensible to further languages due to its strict separation of source code and language resources like patterns and rules. We present a broad evaluation on multiple languages and domains on existing corpora as well as on a newly created corpus for a language/domain combination for which no annotated corpus has been available so far.

The Quranic Arabic Corpus (http://corpus.quran.com) is a collaboratively constructed linguistic resource initiated at the University of Leeds, with multiple layers of annotation including part-of-speech tagging, morphological segmentation (Dukes and Habash 2010) and syntactic analysis using dependency grammar (Dukes and Buckwalter 2010). The motivation behind this work is to produce a resource that enables further analysis of the Quran, the 1,400 year-old central religious text of Islam. This project contrasts with other Arabic treebanks by providing a deep linguistic model based on the historical traditional grammar known as i′rāb (إعراب). By adapting this well-known canon of Quranic grammar into a familiar tagset, it is possible to encourage online annotation by Arabic linguists and Quranic experts. This article presents a new approach to linguistic annotation of an Arabic corpus: online supervised collaboration using a multi-stage approach. The different stages include automatic rule-based tagging, initial manual verification, and online supervised collaborative proofreading. A popular website attracting thousands of visitors per day, the Quranic Arabic Corpus has approximately 100 unpaid volunteer annotators each suggesting corrections to existing linguistic tagging. To ensure a high-quality resource, a small number of expert annotators are promoted to a supervisory role, allowing them to review or veto suggestions made by other collaborators. The Quran also benefits from a large body of existing historical grammatical analysis, which may be leveraged during this review. In this paper we evaluate and report on the effectiveness of the chosen annotation methodology. We also discuss the unique challenges of annotating Quranic Arabic online and describe the custom linguistic software used to aid collaborative annotation.

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.

A wordnet is an important tool for developing natural language processing applications for a language. However, most wordnets are handcrafted by experts, which limits their growth. In this article, we propose an automatic approach to create wordnets by exploiting textual resources, dubbed ECO. After extracting semantic relation instances, identified by discriminating textual patterns, ECO discovers synonymy clusters, used as synsets, and attaches the remaining relations to suitable synsets. Besides introducing each step of ECO, we report on how it was implemented to create Onto.PT, a public lexical ontology for Portuguese. Onto.PT is the result of the automatic exploitation of Portuguese dictionaries and thesauri, and it aims to minimise the main limitations of existing Portuguese lexical knowledge bases.

In this paper, we present the final version of a publicly available treebank of Finnish, the Turku Dependency Treebank. The treebank contains 204,399 tokens (15,126 sentences) from 10 different text sources and has been manually annotated in a Finnish-specific version of the well-known Stanford Dependency scheme. The morphological analyses of the treebank have been assigned using a novel machine learning method to disambiguate readings given by an existing tool. As the second main contribution, we present the first open source Finnish dependency parser, trained on the newly introduced treebank. The parser achieves a labeled attachment score of 81 %. The treebank data as well as the parsing pipeline are available under an open license at http://bionlp.utu.fi/.

Dependency grammar is considered appropriate for many Indian languages. In this paper, we present a study of the dependency relations in Bangla language. We have categorized these relations in three different levels, namely intrachunk relations, interchunk relations and interclause relations. Each of these levels is further categorized and an annotation scheme has been developed. Both syntactic and semantic features have been taken into consideration for describing the relations. In our scheme, there are 63 such syntactico–semantic relations. We have verified the scheme by tagging a corpus of 4167 Bangla sentences to create a treebank (KGPBenTreebank).

Automatic methods for wordnet development in languages other than English generally exploit information found in Princeton WordNet (PWN) and translations extracted from parallel corpora. A common approach consists in preserving the structure of PWN and transferring its content in new languages using alignments, possibly combined with information extracted from multilingual semantic resources. Even if the role of PWN remains central in this process, these automatic methods offer an alternative to the manual elaboration of new wordnets. However, their limited coverage has a strong impact on that of the resulting resources. Following this line of research, we apply a cross-lingual word sense disambiguation method to wordnet development. Our approach exploits the output of a data-driven sense induction method that generates sense clusters in new languages, similar to wordnet synsets, by identifying word senses and relations in parallel corpora. We apply our cross-lingual word sense disambiguation method to the task of enriching a French wordnet resource, the WOLF, and show how it can be efficiently used for increasing its coverage. Although our experiments involve the English–French language pair, the proposed methodology is general enough to be applied to the development of wordnet resources in other languages for which parallel corpora are available. Finally, we show how the disambiguation output can serve to reduce the granularity of new wordnets and the degree of polysemy present in PWN.

We present a verb–complement dictionary of Modern Hebrew, automatically extracted from text corpora. Carefully examining a large set of examples, we defined ten types of verb complements that cover the vast majority of the occurrences of verb complements in the corpora. We explored several collocation measures as indicators of the strength of the association between the verb and its complement. We then used these measures to automatically extract verb complements from corpora. The result is a wide-coverage, accurate dictionary that lists not only the likely complements for each verb, but also the likelihood of each complement. We evaluated the quality of the extracted dictionary both intrinsically and extrinsically. Intrinsically, we showed high precision and recall on randomly (but systematically) selected verbs. Extrinsically, we showed that using the extracted information is beneficial for two applications, prepositional phrase attachment disambiguation and Arabic-to-Hebrew machine translation.

This paper describes the creation of a fine-grained named entity annotation scheme and corpus for Dutch, and experiments on automatic main type and subtype named entity recognition. We give an overview of existing named entity annotation schemes, and motivate our own, which describes six main types (persons, organizations, locations, products, events and miscellaneous named entities) and finer-grained information on subtypes and metonymic usage. This was applied to a one-million-word subset of the Dutch SoNaR reference corpus. The classifier for main type named entities achieves a micro-averaged F-score of 84.91 %, and is publicly available, along with the corpus and annotations.

Modern paraphrase research would benefit from large corpora with detailed annotations. However, currently these corpora are still thin on the ground. In this paper, we describe the development of such a corpus for Dutch, which takes the form of a parallel monolingual treebank consisting of over 2 million tokens and covering various text genres, including both parallel and comparable text. This publicly available corpus is richly annotated with alignments between syntactic nodes, which are also classified using five different semantic similarity relations. A quarter of the corpus is manually annotated, and this informs the development of an automatic tree aligner used to annotate the remainder of the corpus. We argue that this corpus is the first of this size and kind, and offers great potential for paraphrasing research.

Starting in 2006, the European Commission’s Joint Research Centre and other European Union organisations have made available a number of large-scale highly-multilingual parallel language resources. In this article, we give a comparative overview of these resources and we explain the specific nature of each of them. This article provides answers to a number of question, including: What are these linguistic resources? What is the difference between them? Why were they originally created and why was the data released publicly? What can they be used for and what are the limitations of their usability? What are the text types, subject domains and languages covered? How to avoid overlapping document sets? How do they compare regarding the formatting and the translation alignment? What are their usage conditions? What other types of multilingual linguistic resources does the EU have? This article thus aims to clarify what the similarities and differences between the various resources are and what they can be used for. It will also serve as a reference publication for those resources, for which a more detailed description has been lacking so far (EAC-TM, ECDC-TM and DGT-Acquis).

The paper describes a corpus of texts produced by non-native speakers of Czech. We discuss its annotation scheme, consisting of three interlinked tiers, designed to handle a wide range of error types present in the input. Each tier corrects different types of errors; links between the tiers allow capturing errors in word order and complex discontinuous expressions. Errors are not only corrected, but also classified. The annotation scheme is tested on a data set including approx. 175,000 words with fair inter-annotator agreement results. We also explore the possibility of applying automated linguistic annotation tools (taggers, spell checkers and grammar checkers) to the learner text to support or even substitute manual annotation.

The balanced corpus of contemporary written Japanese (BCCWJ) is Japan’s first 100 million words balanced corpus. It consists of three subcorpora (publication subcorpus, library subcorpus, and special-purpose subcorpus) and covers a wide range of text registers including books in general, magazines, newspapers, governmental white papers, best-selling books, an internet bulletin-board, a blog, school textbooks, minutes of the national diet, publicity newsletters of local governments, laws, and poetry verses. A random sampling technique is utilized whenever possible in order to maximize the representativeness of the corpus. The corpus is annotated in terms of dual POS analysis, document structure, and bibliographical information. The BCCWJ is currently accessible in three different ways including Chunagon a web-based interface to the dual POS analysis data. Lastly, results of some pilot evaluation of the corpus with respect to the textual diversity are reported. The analyses include POS distribution, word-class distribution, entropy of orthography, sentence length, and variation of the adjective predicate. High textual diversity is observed in all these analyses.

The need for data about the acquisition of Czech by non-native learners prompted the compilation of the first learner corpus of Czech. After introducing its basic design and parameters, including a multi-tier manual annotation scheme and error taxonomy, we focus on the more technical aspects: the transcription of hand-written source texts, process of annotation, and options for exploiting the result, together with tools used for these tasks and decisions behind the choices. To support or even substitute manual annotation we assign some error tags automatically and use automatic annotation tools (tagger, spell checker).

We present the KELLY project and its work on developing monolingual and bilingual word lists for language learning, using corpus methods, for nine languages and thirty-six language pairs. We describe the method and discuss the many challenges encountered. We have loaded the data into an online database to make it accessible for anyone to explore and we present our own first explorations of it. The focus of the paper is thus twofold, covering pedagogical and methodological aspects of the lists’ construction, and linguistic aspects of the by-product of the project, the KELLY database.

The learner translation corpus developed at the School of Translation and Interpreting of Pompeu Fabra University in Barcelona is a web-searchable resource created for pedagogical and research purposes. It comprises a multiple translation corpus (English–Catalan) featuring automatic linguistic annotation and manual error annotation, complemented with an interface for monolingual or bilingual querying of the data. The corpus can be used to identify common errors in the students’ work and to analyse their patterns of language use. It provides easy access to error samples and to multiple versions of the same source text sequence to be used as learning materials in various courses in the translator-training university curriculum.

Most efforts at automatically creating multilingual lexicons require input lexical resources with rich content (e.g. semantic networks, domain codes, semantic categories) or large corpora. Such material is often unavailable and difficult to construct for under-resourced languages. In some cases, particularly for some ethnic languages, even unannotated corpora are still in the process of collection. We show how multilingual lexicons with under-resourced languages can be constructed using simple bilingual translation lists, which are more readily available. The prototype multilingual lexicon developed comprise six member languages: English, Malay, Chinese, French, Thai and Iban, the last of which is an under-resourced language in Borneo. Quick evaluations showed that 91.2  % of 500 random multilingual entries in the generated lexicon require minimal or no human correction.

Wordnets are large-scale lexical databases of related words and concepts, useful for language-aware software applications. They have recently been built for many languages by using various approaches. The Finnish wordnet, FinnWordNet (FiWN), was created by translating the more than 200,000 word senses in the English Princeton WordNet (PWN) 3.0 in 100 days. To ensure quality, they were translated by professional translators. The direct translation approach was based on the assumption that most synsets in PWN represent language-independent real-world concepts. Thus also the semantic relations between synsets were assumed mostly language-independent, so the structure of PWN could be reused as well. This approach allowed the creation of an extensive Finnish wordnet directly aligned with PWN and also provided us with a translation relation and thus a bilingual wordnet usable as a dictionary. In this paper, we address several concerns raised with regard to our approach, many of them for the first time. We evaluate the craftsmanship of the translators by checking the spelling and translation quality, the viability of the approach by assessing the synonym quality both on the lexeme and concept level, as well as the usefulness of the resulting lexical resource both for humans and in a language-technological task. We discovered no new problems compared with those already known in PWN. As a whole, the paper contributes to the scientific discourse on what it takes to create a very large wordnet. As a side-effect of the evaluation, we extended FiWN to contain 208,645 word senses in 120,449 synsets, effectively making version 2.0 of FiWN currently the largest wordnet in the world by these statistics.

This paper intends to present a machine readable Romanian language pronunciation dictionary called NaviRo. The dictionary contains 138,500 unique words from the DexOnline dictionary together with their phonetic transcriptions in speech assessment method phonetic alphabet. The development of the pronunciation dictionary and the performed validation tests are also described in the paper. NaviRo pronunciation dictionary is freely available on the project website (http://users.utcluj.ro/~jdomokos/naviro) in plain text, Hidden Markov Model Toolkit and Festival speech synthesis system dictionary format. There are also available for download the used grapheme and phoneme sets and the audio samples for the used phonemes. The use of these resources is completely unrestricted for any research purposes in order to speed up Romanian language speech technology research.

We present the Finnish PropBank, a resource for semantic role labeling (SRL) of Finnish based on the Turku Dependency Treebank whose syntax is annotated in the well-known Stanford Dependency (SD) scheme. The contribution of this paper consists of the lexicon of the verbs and their arguments present in the treebank, as well as the predicate-argument annotation of all verb occurrences in the treebank text. We demonstrate that the annotation is of high quality, that the SD scheme is highly compatible with PropBank annotation, and further that the additional dependencies present in the Turku Dependency Treebank are clearly beneficial for PropBank annotation. Further, we also use the PropBank to provide a strong baseline for automated Finnish SRL using a machine learning SRL system developed for the SemEval’14 shared task on broad-coverage semantic dependency parsing. The PropBank as well as the SRL system are available under a free license at http://bionlp.utu.fi/.

This paper presents the IULA Spanish LSP Treebank, an open-source treebank of over 40,000 sentences, developed in the framework of the European project METANET4U. The IULA Spanish LSP Treebank is the first technical corpus of Spanish annotated at surface syntactic level, following the dependency grammar theory. We present the method we used to create the resource and the linguistic annotations that the treebank provides, using examples and comparing with similar resources. We also provide the statistics of the treebank and the evaluation results.

In this paper we present a language-independent, fully modular and automatic approach to bootstrap a wordnet for a new language by recycling different types of already existing language resources, such as machine-readable dictionaries, parallel corpora, and Wikipedia. The approach, which we apply here to Slovene, takes into account monosemous and polysemous words, general and specialised vocabulary as well as simple and multi-word lexemes. The extracted words are then assigned one or several synset ids, based on a classifier that relies on several features including distributional similarity. Finally, we identify and remove highly dubious (literal, synset) pairs, based on simple distributional information extracted from a large corpus in an unsupervised way. Automatic, manual and task-based evaluations show that the resulting resource, the latest version of the Slovene wordnet, is already a valuable source of lexico-semantic information.

Treebanks, especially the Penn treebank for natural language processing (NLP) in English, play an essential role in both research into and the application of NLP. However, many languages still lack treebanks and building a treebank can be very complicated and difficult. This work has a twofold objective. Firstly, to share our results in constructing a large Vietnamese treebank (VTB) with three levels of annotation including word segmentation, part-of-speech tagging, and syntactic analysis. Major steps in the treebank construction process are described with particular regard to specific Vietnamese properties such as lack of word delimiter and isolation. Those properties make sentences highly syntactically ambiguous, and therefore it is difficult to ensure a high level of agreement among annotators. Various studies of Vietnamese syntax were employed not only to define annotations but also to systematically deal with ambiguities. Annotators were supported by automatic labelling tools, which are based on statistical machine learning methods, for sentence pre-processing and a tree editor for supporting manual annotation. As a result, an annotation agreement of around 90 % was achieved. Our second objective is to present our method for automatically finding errors and inconsistencies in treebank corpora and its application to the construction of the VTB. This method employs the Shannon entropy measure in a manner that the more reduced entropy the more corrected errors in a treebank. The method ranks error candidates by using a scoring function based on conditional entropy. Our experiments showed that this method detected high-error-density subsets of original error candidate sets, and that the corpus entropy was significantly reduced after error correction. The size of these subsets was only about one third of the whole set, while these subsets contained 80–90 % of the total errors. This method can also be applied to languages similar to Vietnamese.

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.

To investigate the differences in communicative activities by the same interlocutors in Japanese (their L1) and in English (their L2), an 8-h multimodal corpus of multiparty conversations was collected. Three subjects participated in each conversational group, and they had conversations on free-flowing and goal-oriented topics in Japanese and in English. Their utterances, eye gazes, and gestures were recorded with microphones, eye trackers, and video cameras. The utterances and eye gazes were manually annotated. Their utterances were transcribed, and the transcriptions of each participant were aligned with those of the others along the time axis. Quantitative analyses were made to compare the communicative activities caused by the differences in conversational languages, the conversation types, and the levels of language expertise in L2. The results reveal different utterance characteristics and gaze patterns that reflect the differences in difficulty felt by the participants in each conversational condition. Both total and average durations of utterances were shorter in their L2 than in their L1 conversations. Differences in eye gazes were mainly found in those toward the information senders: Speakers were gazed at more in their second-language than in their native-language conversations. Our findings on the characteristics of conversations in the second language suggest possible directions for future research in psychology, cognitive science, and human–computer interaction technologies.

The paper presents the Chinese Discourse TreeBank, a corpus annotated with Penn Discourse TreeBank style discourse relations that take the form of a predicate taking two arguments. We first characterize the syntactic and statistical distributions of Chinese discourse connectives as well as the role of Chinese punctuation marks in discourse annotation, and then describe how we design our annotation strategy procedure based on this characterization. The Chinese-specific features of our annotation strategy include annotating explicit and implicit discourse relations in one single pass, defining the argument labels on semantic, rather than syntactic, grounds, as well as annotating the semantic type of implicit discourse relations directly. We also introduce a flat, 11-valued semantic type classification scheme for discourse relations. We finally demonstrate the feasibility of our approach with evaluation results.

This paper introduces the South East Asia Mandarin–English corpus, a 63-h spontaneous Mandarin–English code-switching transcribed speech corpus suitable for LVCSR and language change detection/identification research. The corpus is recorded under unscripted interview and conversational settings from 157 Singaporean and Malaysian speakers who spoke a mixture of Mandarin and English within a single sentence. About 82 % of the transcribed utterances are intra-sentential code-switching speech and the corpus will be release by LDC in 2015. This paper presents an analysis of the code-switching statistics of the corpus, such as the duration of monolingual segments and the frequency of language turns in code-switch utterances. We also summarize the development effort, details such as the processing time for transcription, validation and language boundary labelling. Lastly, we present textual analyses of code-switch segments examining the word length of monolingual segments in code-switch utterances and the most common single word and two-word phrase of such segments.

We describe the creation of a massively parallel corpus based on 100 translations of the Bible. We discuss some of the difficulties in acquiring and processing the raw material as well as the potential of the Bible as a corpus for natural language processing. Finally we present a statistical analysis of the corpora collected and a detailed comparison between the English translation and other English corpora.

A corpus of French tales is presented. Its two parts, a text corpus and a speech corpus, were designed for studying the relationships between the textual structures of tales and speech prosody, with the targeted application of an expressive text-to-speech synthesis system embedded in a humanoid robot. The 89-tale text corpus, and the 12-tale speech corpus were annotated using a common tale description framework. Lexical level annotations include extended definitions of enumerations, time, place and person named entities, as well as part of speech tags. Supra-lexical level annotations include the segmentation of tales into a sequence of episodes, the localization and attribution of direct quotations, together with tale protagonists co-references. Annotation distributions and inter-annotator agreement were analyzed. The largest coverage and strongest agreement were observed for person named entities, characters’ direct quotations, and their associated coreference chains. Speech corpus annotations were extended to allow the analysis of the relations between tale linguistic information and prosodic properties observed in associated speech. Word and phoneme boundaries were inferred through semi-automatic procedures, resulting in linguistic annotations aligned with the speech signal. Intonation stylization models were used to ease the visual and statistical analysis of tale’s prosody. Additional meta-information is provided with the speech corpus, allowing describing tale characters according to their gender, age, size, valence and kind. The corpora described in this article are publicly available through the European Language Resources Association catalog.

Learner corpora consist of texts produced by non-native speakers. In addition to these texts, some learner corpora also contain error annotations, which can reveal common errors made by language learners, and provide training material for automatic error correction. We present a novel type of error-annotated learner corpus containing sequences of revised essay drafts written by non-native speakers of English. Sentences in these drafts are annotated with comments by language tutors, and are aligned to sentences in subsequent drafts. We describe the compilation process of our corpus, present its encoding in TEI XML, and report agreement levels on the error annotations. Further, we demonstrate the potential of the corpus to facilitate research on textual revision in L2 writing, by conducting a case study on verb tenses using ANNIS, a corpus search and visualization platform.