Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
18625 papers
We evaluate two cross-lingual techniques for adding enhanced dependencies to existing treebanks in Universal Dependencies. We apply a rule-based system developed for English and a data-driven system trained on Finnish to Swedish and Italian. We find that both systems are accurate enough to bootstrap enhanced dependencies in existing UD treebanks. In the case of Italian, results are even on par with those of a prototype language-specific system.
Annotation corpus for discourse relations benefits NLP tasks such as machine translation and question answering. In this paper, we present SciDTB, a domainspecific discourse treebank annotated on scientific articles. Different from widelyused RST-DT and PDTB, SciDTB uses dependency trees to represent discourse structure, which is flexible and simplified to some extent but do not sacrifice structural integrity. We discuss the labeling framework, annotation workflow and some statistics about SciDTB. Furthermore, our treebank is made as a benchmark for evaluating discourse dependency parsers, on which we provide several baselines as fundamental work.
In the modern world it can be easy to encounter advertising slogans that are supposed to grab the attention of a potential recipient as well as affect their imagination and sensitivity. This communication tends to convince the client that buying the advertised product would make them feel exceptional. This article focuses on linguistic gimmicks that are used by marketing experts in order to convince the client to a certain product. The analysis in based on the cosmetics sector. The lexical database consists of websites, television commercials and Internet advertisements.
We present a progress report of the Turkish Treebank concentrating on various aspects of its design and implementation. In addition to a review of the corpus compilation process and the design of the annotation scheme, we describe the details of various pre-processing stages and the computer-assisted annotation process.
This paper describes our system (HIT-SCIR) submitted to the CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies. We base our submission on Stanford's winning system for the CoNLL 2017 shared task and make two effective extensions: 1) incorporating deep contextualized word embeddings into both the part of speech tagger and parser; 2) ensembling parsers trained with different initialization. We also explore different ways of concatenating treebanks for further improvements. Experimental results on the development data show the effectiveness of our methods. In the final evaluation, our system was ranked first according to LAS (75.84%) and outperformed the other systems by a large margin.
Implicit discourse relation recognition is a challenging task as the relation prediction without explicit connectives in discourse parsing needs understanding of text spans and cannot be easily derived from surface features from the input sentence pairs. Thus, properly representing the text is very crucial to this task. In this paper, we propose a model augmented with different grained text representations, including character, subword, word, sentence, and sentence pair levels. The proposed deeper model is evaluated on the benchmark treebank and achieves state-of-the-art accuracy with greater than 48% in 11-way and F1 score greater than 50% in 4-way classifications for the first time according to our best knowledge.
Larysa Kolibaba PhD in Philology, Senior Research Scientist of the Department of Grammar and Scientific Terminology, Institute of the Ukrainian Language of National Academy of Sciences of Ukraine 4 Hrushevskyi St., Kyiv 01001, Ukraine Е-mail: kolibaba.lm@meta.ua Heading: Researches Language: Ukrainian Abstract: In this article the problem of fixing of morphological forms of nouns in the Ukrainian dictionaries of different time and its […]
We introduce the syntactic scaffold, an approach to incorporating syntactic information into semantic tasks. Syntactic scaffolds avoid expensive syntactic processing at runtime, only making use of a treebank during training, through a multitask objective. We improve over strong baselines on PropBank semantics, frame semantics, and coreference resolution, achieving competitive performance on all three tasks. them he After encouraging them, told goodbye and left for STIMULATE _EMOTION
In this paper, we describe the annotation and development of Telugu treebank following the Universal Dependencies framework. We manually annotated 1328 sentences from a Telugu grammar textbook and the treebank is freely available from Universal Dependencies version 2.1.1 In this paper, we discuss some language specific annotation issues and decisions; and report preliminary experiments with POS tagging and dependency parsing. To the best of our knowledge, this is the first freely accessible and open dependency treebank for Telugu.
The article presents a quantitative analysis of some syntactic dependency properties in Czech. A dependency frame is introduced as a linguistic unit and its characteristics are investigated. In particular, a ranked frequencies of dependency frames are observed and modelled and a relationship between particular syntactic functions and the number of dependency frames is examined. For the analysis, the Czech Universal Dependency Treebank is used.
Preview this article: The added value of diachronic treebanks for historical linguistics, Page 1 of 1 < Previous page | Next page > /docserver/preview/fulltext/dia.00004.eck-1.gif
In this paper we describe the extensions we made to an existing treebank query application (GrETEL). These extensions address user needs expressed by multiple linguistic researchers and include (1) facilities for uploading one’s own data and metadata in GrETEL; (2) conversion and cleaning modules for uploading data in the CHAT format; (3) new facilities for analysing the results of the treebank queries in terms of data, metadata and combinations of them. These extensions have been made available in a new version (Version 4) of GrETEL.
We present PAWS, a multi-lingual parallel treebank with coreference annotation. It consists of English texts from the Wall Street Journal translated into Czech, Russian and Polish. In addition, the texts are syntactically parsed and word-aligned. PAWS is based on PCEDT 2.0 and continues the tradition of multilingual treebanks with coreference annotation. The paper focuses on the coreference annotation in PAWS and its language-specific differences. PAWS offers linguistic material that can be further leveraged in cross-lingual studies, especially on coreference.
The present paper shows how the current Universal Dependency treebanks can be used for language typology studies and can reveal structural syntactic features of languages. Two methods, one existing method and one newly proposed method, based on dependency treebanks as typological measurements, are presented and tested in order to assess both the coherence of the underlying syntactic data and the validity of the methods themselves. The results show that both methods are valid for positioning a language in the typological continuum, although they probably reveal different typological features of languages.
The excellent back-of-the book index contains terms that navigate readers to find the indexed term on the important book page and related to the content of the book. The conceptual characteristic of indexed term is one of the difficulties that faced by the professional book indexers. They should ensure that the indexed term directs the reader to a book page with the relevant information so the readers can understand the meaning or information in the indexed term. This study aims to identify the relevance of the indexed term. We consider the relatedness of the text containing the indexed terms with the book domain. We calculate the semantic relatedness of the data set, using the WordNet lexical database. We have evaluated the performance of semantic-relatedness method on books from the knowledge domain of Biology, Religion and Computer Science using Kappa Statistic Values. The result implies that the relatedness to the knowledge domain of the book influences the relevance of an indexed term. The Kappa values that obtained from the results test show that this semantic relatedness approach is reliable and could contribute to identify the relevant indexed term.
Abstract. Affective science calls for methods to induce mood in an engaging and ecologically valid way. We present a method employing a naturally occurring scenario that fits these criteria: a job interview. Participants got positive or negative feedback from a fictive expert to induce positive or negative mood. After mood induction, we assessed participants’ decision making behavior in the so-called information sampling task (IST). Results show that our mood induction successfully changed valence, dominance, and state self-esteem ratings, while there were no differences in arousal ratings. Decision making in the IST was not influenced by the induced mood. Effect sizes of mood induction were equally high for positive and negative mood concerning valence ratings (d =.8) with participants scoring high on self-control showing smaller mood induction effects. We conclude that our mood induction technique is an effective and natural way to induce mood in the laboratory, meeting current criteria of affective science.
Demand-withdraw is an ineffective communication pattern frequently experienced by distressed couples. Therapists often attempt to address this pattern by helping partners understand and regulate the emotions that underlie these behaviors. To date, there is a lack of research focusing on the emotional experiences underlying the demand-withdraw pattern of interaction in couples. Related lines of research focus on emotional arousal and the expression of hard and soft emotions, but this research does not specifically investigate demand-withdraw interactions. The purpose of this study is to identify what emotions underlie demanding behavior in both men and women during marital demand-withdraw conflict interactions. Six couples were chosen from a five-year longitudinal randomized clinical trial that compared Integrative Behavioral Couple Therapy (IBCT) and Traditional Behavioral Couple Therapy (TBCT). Researchers viewed 10-minute pre-treatment problem-solving interactions to observe the demand-withdraw pattern in vivo among couples seeking therapy. The Behavioral Affective Rating Scale (BARS) was used to code the emotions observed during the interactions. The results indicated that the types of emotions varied not only depending on who initiated the problem-solving interaction (e.g., wife topic-husband topic) but also between the different couples, and when comparing gender. Anxiety (#2) and aggression (#4) were in the top four most commonly observed emotions for husbands, while they were two of the least observed emotions for wives. Moreover, frustration and hurt were the two most observed emotions for wives, while they were the least observed emotions for husbands.
Fibromyalgia syndrome (FMS), a common chronic pain condition, is often incompletely treated by conventional medical therapies. It can cause disability, psychological distress, work-related absenteeism, increased use of healthcare resources, and result in the inability to carry out the tasks of daily living. The purpose of this quantitative, correlational study was to investigate the potential influence of laughter on affect and pain in individuals with FMS. Laughter produces beneficial effects on acute pain and on chronic pain in general and has been found to improve temporary affective states, but there have been no studies testing the effects of laughter on the pain and affect of fibromyalgia patients. Informing this study were the gate control and neuromatrix theories of pain, as well as the dynamic model of affect theory. The research questions addressed whether laughter frequency is associated with affect and or with perceived chronic pain levels in these individuals. Forty-one adult fibromyalgia patients documented all laughter episodes daily and assessed their pain and affective states 3 times per day for 14 days. Hierarchical regressions revealed that increased overall laughter frequency was significantly associated with decreases in overall pain and increases in overall positive affect but was not associated with measures of negative affect. Also, morning laughter frequency was predictive of increased afternoon and evening positive affect ratings, as well as with decreased afternoon pain ratings, but was not significantly associated with evening pain ratings. The knowledge gained from these results may have positive social change implications at the individual level, within those individuals' larger social networks, and within the research and medical communities.
Syntactic parsing plays a crucial role in improving the quality of natural language processing tasks. Although there have been several research projects on syntactic parsing in Vietnamese, the parsing quality has been far inferior than those reported in major languages, such as English and Chinese. In this work, we evaluated representative constituency parsing models on a Vietnamese Treebank to look for the most suitable parsing method for Vietnamese. We then combined the advantages of automatic and manual analysis to investigate errors produced by the experimented parsers and find the reasons for them. Our analysis focused on three possible sources of parsing errors, namely limited training data, part-of-speech (POS) tagging errors, and ambiguous constructions. As a result, we found that the last two sources, which frequently appear in Vietnamese text, significantly attributed to the poor performance of Vietnamese parsing.
Hoarding is a mental and public health problem stemming from difficulty associated with discarding one's possessions and resulting clutter. In the last decade, a visual method, called "Clutter Image Rating" (CIR), has been developed for the assessment of hoarding severity. It involves rating clutter in patient's home on the CIR scale from 1 to 9 using a set of reference images. Such assessment, however, is time-consuming, subjective, and may be non-repeatable. In this paper, we propose a new automatic clutter assessment method from images, according to the CIR scale, based on deep learning. While, ideally, the goal is to perfectly classify clutter, trained professionals admit assigning CIR values within ±1. Therefore, we study two loss functions for our network: one that aims to precisely assign a CIR value and one that aims to do so within ±1. We also propose a weighted combination of these loss functions that, as a byproduct, allows us to control the CIR mean absolute error (MAE). On a recently-collected dataset, we achieved ±1 accuracy of 82% and MAE of 0.88, significantly outperforming our previous results of 60% and 1.58, respectively.
Deep neural networks have advanced the state of the art in numerous fields, but they generally suffer from low computational efficiency and the level of improvement compared to more efficient machine learning models is not always significant. We perform a thorough PoS tagging evaluation on the Universal Dependencies treebanks, pitting a state-of-the-art neural network approach against UDPipe and our sparse structured perceptron-based tagger, efselab. In terms of computational efficiency, efselab is three orders of magnitude faster than the neural network model, while being more accurate than either of the other systems on 47 of 65 treebanks.
The paper explores the American neologism of culturomics, coined on December 16, 2010 by the Harvardian research tandem of Jean-Baptiste Michel and Erez Lieberman Aiden for their article on a “Quantitative Analysis of Culture Using Millions of Digitized Books.” In computer linguistics, it denotes an abbreviated, interdisciplinary amalgam of the words culture and genomics, and such a correct explanation of the notion was provided by the authors themselves, as well as by The Wall Street Journal linguistic columnist Ben Zimmer on December 23, 2010. However, the paper notes that the distinguished British linguist David Crystal associated it with economics and ergonomics, as did most of the readers, although the authentic American suffix is not -onomics but rather the bioscientific and neologistic -omics, whereas Michel and Aiden describe genomics as a study of organisms and their genomes, that is, their integral deoxyribonucleic sequences. Exemplified by a Google Books n-gram search pertaining to an American English usage frequency of the notion of “Croatia” from 1990 to 2008, the paper analyzes a scientific deployment of the new realizations and the development of software facilitating a machine retrieval of a spoken, written, or of a symbolic natural language, thus synthesizing a computerized theory and artificial intelligence with a cognitive psychology, linguistics, and logic to interactively correct or translate the texts and extract information. What is more, such an approach is also observable in a contemporary algorithmic speech synthesis, data mining, search engines, or in text compressors. Thus, an exploratory mining of the data stored in the permanently accessible digital archives of almost unlimited capacities represents a completely new behavioristic study, as well as a research in cultural phenomenology, in the so-called “narrative networks, ” reflected by a usage of certain words in a language. Additionally, the author notices a reality of almost 4% of all the printed editions being scanned by Google Books so far, in a pursuit for an apparently encrypted truth. As the statisticians, having mined that largest contemporary linguistic database of approximately 5.2 million digitized exemplars, computed that the holdings are comprised of the fascinating 500 billion words, emphasized is a fact that more than 360 billion of them are of English provenience, followed by the French, Spanish, German, Chinese, Russian and Hebrew ones. In such a multidisciplinary environment, the application of culturomic principles from the year 2000 on also enables the development of websites, for example, of Google Labs, which philologically function as special algorithmic, chronological search engines for the browsing of tokens, that is, of the developmental forms of a word or of the entire phrases in the history of humankind. Conclusively, the paper examines a necessity to acquire a systematic biological, encyclopedic, engineering or psychological knowledge to basically comprehend what the Program of Evolutionary Dynamics calls a “cultural genome.”
The phrase-table plays an important role in traditional phrase-based statistical machine translation (SMT) system. During translation, a phrase-based SMT system relies heavily on phrase-table to generate outputs. In this paper, we propose two methods for enhancing the quality of phrase-table. The first method is to recompute phrase-table weights by using vector representations similarity. The remaining method is to enrich the phrase-table by integrating new phrase-pairs from an extended dictionary and projections of word vector presentations on the target-language space. Our methods produce an attainment of up to 0.21 and 0.44 BLEU scores on in-domain and cross-domain (Asian Language Treebank - ALT) English - Vietnamese datasets respectively.
Emotion mobilizes and demobilizes a social movement while the movement itself impacts people's emotions. An evidence base is needed for developing timely emotion-focused counseling services for affected populations worldwide. This experience sampling study investigated the impact of a social movement on everyday emotional reactivity, variability, instability, and persistence, and whether and how these predicted subsequent psychological distress and well-being among 108 community-dwelling adults. Fifty-four participants reported momentary events and emotions 5 times daily over 7 days during the Umbrella Movement in Hong Kong. An age-matched, sex-matched comparison group (n = 54) participated during a period without major social/political movement. Psychological distress and well-being were assessed at baseline (Time 1 [T1]) and 3-month follow-up (Time 2 [T2]). Hierarchical linear modeling revealed lower valence ratings of positive events during the Umbrella Movement. Lower positive emotional reactivity and higher negative emotional reactivity in positive events were reported during the movement. Controlling for demographics and T1 scores, the positive association between negative emotional reactivity in positive events and T2 depressive symptoms, and the inverse association between positive emotional instability and T2 positive emotions, were significant only among the comparison group. The positive association between positive emotions in positive events and T2 life satisfaction was significant only among the Umbrella Movement group. People could experience significant changes in their emotions in everyday life during a social movement, even if it is short and relatively nonviolent like the Umbrella Movement. Maximizing positive emotions in positive events during a social movement can uniquely contribute to higher subsequent psychological well-being. (PsycINFO Database Record
The authors try to answer two questions: 1. How the Polish philology students understand the concept of linguistic norm? and 2. When, according to those students, people should follow it? The article presents the results of the survey conducted among 200 respondents. It turns out that the students understand the concept of norm well, usually as a set of rulles, which are established by linguists or/and accepted by society. They also think that the respect of rules takes effect in varying degrees in different communication situations.
Valency coercion phenomena arise when constructions and verbs are combined in novel and flexible ways. This flexibility is one of the main supporting of argument constructions as structural units of language, with abstract and independent semantics that dynamically interact with the semantics of the main verb (Goldberg, 1995; Michaelis, 2005; Pustejovsky et al., 2010; Lauwers and Willems, 2011; Perek, 2015). Despite the pivotal role of coercion in construction grammar, however, little research has been done outside the domain of English (Gonzalvez-Garcia, 2007; Boas and Gonzalvez-Garcıa, 2014; Booji and Audring, 2015), and – to our knowledge – no attempt has been previously made to analyse constructional flexibility in Italian.\t \nWe propose the results of an empirical study on Italian valency coercion, which aims to contribute both to a still lacking constructionist description of Italian and to a cross-linguistic debate on the cognitive reality of constructions. The first part of the research was carried out by means of an acceptability rating test based on Perek and Hilpert (2014): the experiment is structured around 9 argument structure constructions of Italian; a set of 21 sentences was created for each construction, divided in 3 experimental conditions: grammatical, coercion, impossible. Between conditions, sentences differ only in their verb, to insert as little variation as possible. \n1)\ta. Gianni ha detto che verrà domani (Gianni said that he will come tomorrow) \nb. Gianni ha fischiettato che verrà domani (Gianni whistled that he will come tomorrow) \nc. Gianni ha cucinato che verrà domani (Gianni cooked that he will come tomorrow) \n120 Italian native speakers from three age groups were tested: adolescents, young adults (18 - 35 years old), and adults (over 40). The data was analysed both with statistical tests and with linear mixed effect modelling. Results show coercion as an “intermediate” condition, significantly different from both grammatical and ungrammatical sentences. Moreover, the recognition of coercion appears to vary with age, as older speakers tended to polarise their answers towards the extremities of the scale (1 or 7). \nThe data also showed inter-construction variability. Constructions appeared to have different degrees of flexibility, that we are addressing in the second part of the study. We are constructing a corpus-based distributional model to operationalize the notion of (partial) productivity of constructions (Barðdal, 2008; Zeschel, 2015). Our assumption is that coercion mechanisms are influenced both by the productivity of the construction and by the distance between source and target meaning of the verb embedded in the creative structure (Barak and Goldberg, 2017; Perek and Goldberg, 2017). We measure the latter by representing construction meaning with distributional vectors trained on a large Italian corpus, following the approach in Lebani and Lenci (2017). As data, we matched syntactic frames automatically extracted from the Universal Dependency Italian treebank (Rambelli et al., 2016) to our constructions and identified the more frequent verbs. The results of the second part of the study, which are still being processed, will provide distributional evidence to shed new light on Italian constructions’ flexibility.
To reinforce sports informatization management and the sports service quality on college campuses, this paper researches combined multi-agent technology, and structures undergraduate sports service system framework. It has elaborated functions of every feature and workflow of the system, and puts forward agent design procedure based on JADE. What is more, it also adopts FIPAACl linguistic norms between Agents communication and proposes some advices which based on the fundamental of Agent.
Currently, the biaffine classifier has been attracting attention as a method to introduce an attention mechanism into the modeling of binary relations. For instance, in the field of dependency parsing, the Deep Biaffine Parser by Dozat and Manning has achieved state-of-the-art performance as a graph-based dependency parser on the English Penn Treebank and CoNLL 2017 shared task. On the other hand, it is reported that parameter redundancy in the weight matrix in biaffine classifiers, which has O(n^2) parameters, results in overfitting (n is the number of dimensions). In this paper, we attempted to reduce the parameter redundancy by assuming either symmetry or circularity of weight matrices. In our experiments on the CoNLL 2017 shared task dataset, our model achieved better or comparable accuracy on most of the treebanks with more than 16% parameter reduction.
Annotation Guidelines for Text Analytics in Social Media A person's language use reveals much about their profile, however, research in author profiling has always been constrained by the limited availability of training data, since collecting textual data with the appropriate meta-data requires a large collection and annotation effort (Maamouri et al. 2010; Diab et al. 2008; Hawwari et al. 2013).For every text, the characteristics of the author have to be known in order to successfully profile the author. Moreover, when the text is written in a dialectal variety such as the Arabic text found online in social media a representative dataset need to be available for each dialectal variety (Zaghouani et al. 2012; Zaghouani et al. 2016).The existing Arabic dialects are historically related to the classical Arabic and they co-exist with the Modern Standard Arabic in a diglossic relation. While the standard Arabic, has a clearly defined set of orthographic standards, the various Arabic dialects have no official orthographies and a given word could be written in multiple ways in different Arabic dialects (Maamouri et al. 2012; Jeblee et al. 2014).This abstract presents the guidelines and annotation work carried out within the framework of the Arabic Author profiling project (ARAP), a project that aims at developing author profiling resources and tools for a set of 12 regional Arabic dialects. We harvested our data from social media which reflect a natural and spontaneous writing style in dialectal Arabic from users in different regions of the Arabworld.For the Arabic language and its dialectal varieties as foundin social media, to the best of our knowledge, there is nocorpus available for the detection of age, gender, nativelanguage and dialectal variety. Most of the existingresources are available for English or other Europeanlanguages. Having a large amount of annotated data remains the key to reliable results in the taskof author profiling. In order to start the annotation process, we createdguidelines for the annotation of the Tweets according totheir dialectal variety, their native language, the gender of the user and the age. Before starting theannotation process, we hired and trained a group of annotators and we implemented a smooth annotation pipeline to optimize the annotation task. Finally, we followed a consistent annotation evaluation protocol to ensure a high inter-annotator agreement.The Annotations were done by carefully analyzing each ofthe user's profiles, their tweets, and when possible, weinstructed the annotators to use external resources such asLinkedIn or Facebook. We created a general profilesvalidation guidelines and task-specific guidelines toannotate the users according to their gender, age, dialectand their native language. For some accounts, the annotators were not able to identifythe gender as this was based in most of the cases on thename of the person or his profile photo and in some casesby their biography or profile description. In case thisinformation is not available, we instructed the annotators toread the user posts and find linguistic indicators of thegender of the user.Like many other languages, Arabic conjugates verbsthrough numerous prefixes and suffixes and the gender issometimes clearly marked such as in the case of the verbsending in taa marbuTa which is usually of femininegender.In order to annotate the users for their age, we used threecategories: under 20 years, between 20 years and 40 years,and 40 years and up.In our guidelines, we asked our annotators to try their bestto annotate the exact age, for example, they can check theeducation history of the users in LinkedIn and Facebookprofile and find when the graduated from high school forexample in order to guess the age of the users. As the dialect and the regions are known in advance to theannotators, we instructed them to double check and markthe cases when the profile appears to be from a differentdialect group. This is possible despite our initial filteringbased on distinctive regional keywords. We noticed that inmore than 90% the profiles selected belong to the specifieddialect group. Moreover, we asked the annotators to mark and identifyTwitter profiles with a native language other than Arabic,so they are considered as Arabic L2 speakers. In order tohelp the annotators identify those, we instructed them tolook for various cues such as the writing style, the sentence structure, the word order and the spelling errors.AcknowledgementsThis publication was made possible by NPRP grant #9-175-1-033 from the Qatar National Research Fund (a member ofQatar Foundation). The statements made herein are solelythe responsibility of the authors. ReferencesDiab Mona, Aous Mansouri, Martha Palmer, Olga Babko-Malaya, Wajdi Zaghouani, Ann Bies, Mohammed Maamouri. A Pilot Arabic Propbank; LREC 2008, Marrakech, Morocco, May 28-30, 2008.Hawwari, A.; Zaghouani, W.; O»Gorman, T.; Badran, A.; Diab, M., «Building a Lexical Semantic Resource for Arabic Morphological Patterns,» Communications, Signal Processing, and their Applications (ICCSPA), 2013, vol., no., pp.1,6, 12-14 Feb. 2013. Jeblee Serena; Houda Bouamor; Wajdi Zaghouani; Kemal Oflazer. CMUQ@QALB-2014: An SMT-based System for Automatic Arabic Error Correction. In Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP), Doha, Qatar, October 2014.Maamouri Mohamed, Ann Bies, Seth Kulick, Wajdi Zaghouani, Dave Graff and Mike Ciul. 2010. From Speech to Trees: Applying Treebank Annotation to Arabic Broadcast News. In Proceedings of LREC 2010, Valetta, Malta, May 17-23, 2010.Maamouri Mohammed, Wajdi Zaghouani, Violetta Cavalli-Sforza, Dave Graff and Mike Ciul. 2012. Developing ARET: An NLP-based Educational Tool Set for Arabic Reading Enhancement. In Proceedings of The 7th Workshop on Innovative Use of NLP for Building Educational Applications, NAACL-HLT 2012, Montreal, Canada.Obeid Ossama, Wajdi Zaghouani, Behrang Mohit, Nizar Habash, Kemal Oflazer and Nadi Tomeh. A Web-based Annotation Framework For Large- Scale Text Correction. In Proceedings of IJCNLP'2013, Nagoya, Japan.Zaghouani Wajdi, Nizar Habash, Ossama Obeid, Behrang Mohit, Houda Bouamor, Kemal Oflazer. 2016. Building an arabic machine translation post-edited corpus: Guidelines and annotation. In Proceedings of the International Conference on Language Resources and Evaluation (LREC»2016).Zaghouani Wajdi, Abdelati Hawwari and Mona Diab. 2012. A Pilot PropBank Annotation for Quranic Arabic. In Proceedings of the first workshop on Computational Linguistics for Literature, NAACL-HLT 2012, Montreal, Canada.
A puzzling fact about linguistic norms is that they are mainly stable, but the conventional variant sometimes changes. These transitions seem to be mostly S-shaped and, therefore, directed. Previous models have suggested possible mechanisms to explain these directed changes, mainly based on a bias favoring the innovative variant. What is still debated is what is the mechanism that leads to such a bias. In this paper we propose a refined taxonomy of mechanisms of language change and identify a family a mechanisms explaining self-actuated language changes. We exemplify this type of mechanism with the preference-based selection mechanism that relies on agents having dynamical preferences for different variants of the linguistic norm. The key point is that if these preferences can align through social interactions, then new changes can be actuated. We present results of a multi-agent model and demonstrate that the model produces trajectories that are typical of language change.
Abstract This chapter addresses interlingual relations between constructions. The perspective is contrastive rather than typological, with an aim towards multilingual constructicon development. Building on previous work on the alignment of frame-based multilingual lexical databases, we explore possibilities and problems for multilingual constructicography. By comparing the dataset of Berkeley’s English constructicon to Brazilian Portuguese and Swedish, we discuss the alignment of constructicons vis á vis the existence of more or less equivalent constructions or the deployment of different linguistic strategies in different languages.
This chapter takes up the issue of authenticity in language pedagogy. Traditional views of authenticity take the native speaker to be the primary authority for linguistic norms. Written standard language is especially highly valued here. It is argued herein that TELL environments are equally valid as learning environments, and that students can use the freedom they provide to develop their own locally negotiated cultural and linguistic norms. Evidence is provided that students on a net-based MA program develop their own norms for reducing language, and use them and other means to mark membership of a local TELL community. Thus, TELL is a rich and authentic environment for learners of English to become what is referred to as “language practitioners.”
Abstract In the context of the Index Thomisticus Treebank project, we have enhanced the full text of Bellum Catilinae by Sallust with semantic annotation. The annotation style resembles the one used for the so called “tectogrammatical” layer of the Prague Dependency Treebank. By exploiting the results of semantic role labeling, ellipsis resolution and coreference analysis, this paper presents a network-based study of the main Actors and Actions (and their relations) in Bellum Catilinae.
Facebook is the most popular social networking website. Every post on Facebook actually can imply the user's emotion or opinion. In this paper, we present our analysis on posts associated with left- and right-wing politics in the United States of America. Our dataset contains posts several related Facebook fan pages. We analyze sentiment of posts for the prediction of left- or right-wing politics. We build sentiment features for the prediction and evaluate prediction performance. The results show that F1-score can be as high as 0.95 when TF-IDF is used with a decision tree. Posts generally involve emotional words. We use the lexical databases for sentiment analysis. Our experiment results show that the sentiment analysis is sensitive to some classification algorithms.
This paper presents SimpleNLG-NL, an adaptation of the SimpleNLG surface realisation engine for the Dutch language. It describes a novel method for determining and testing the grammatical constructions to be implemented, using target sentences sampled from a treebank.
The thesis is devoted to the study of language planning in Soviet Ukraine in the interwar period. It presents and discusses some ideas, schools, debates and results of the normalization of the Ukrainian language in this period. The aim of the dissertation is to promote a better knowledge and understanding of an important phase in the history of the Ukrainian language, and identify the epistemological and cultural background which inspired some of the linguistic descriptions and prescriptions in the interwar period. \nThe thesis consists of index, introduction, four chapters, conclusions, bibliographical references, annexes and abstracts. \nThe first chapter summarizes the historical, linguistic and cultural background of the work on the norm of the Ukrainian language in the 1920s and 1930s, paying special attention to the importance of the relationship between language-people-nation in the Ukrainian culture, the influence of German Romanticism and Völkerpsychologie on Ukrainian normalizers, the concepts of language policy and planning and of linguistic norm and their application in Soviet Ukraine. It also provides the Western/Italian reader with some explanations of specific Ukrainian/Slavonic terms which need to be contextualized in order to be understood. \nThe second chapter focuses on the two schools of normalizers active during the so-called ‘Ukrainization’ (1925-1932): the ethnographic one (O. Kurylo in her early writings, Je. Tymčenko, A. Kryms’kyj, I. Ohijenko, S. Smerečyns’kyj, V. Simovyč in his early writings, M. Hladkyj) and the synthetic one (O. Synjavs’kyj, M. Sulyma, O. Kurylo in her later writings). We identify and define what each of the linguists presented considered to be the norm of the Ukrainian language. Our analysis confirms that the main difference between the ethnographic and synthetic school is that the former focused on folk vernacular, was extremely puristic and therefore tended to reject terms and syntactic structures patterned on or too close to Russian or Polish, whereas the latter was moderately puristic, less categorical in its prescriptions and more open to external influences. The chapter ends with a presentation of the main results of the activity of corpus planning. \nIn the third chapter some important aspects of Ukrainian morphosyntax are discussed. The diachronic perspective is taken into account in order to detect the level of linguistic purism of some prescriptions. The syntactic rules proposed by the ethnographic school of linguists reveal a close connection between syntactic constructions and structures of thought. In other words, syntax, according to the ethnographic school, seems to represent one of the main markers of national belonging, while the synthetic school shows a less radical approach. Generally speaking, the epistemological starting point used in their analysis is represented on the one hand by linguistic psychologism, and on the other by Völkerpsychologie. The chapter ends with an analysis of a polemical pamphlet written by Kost’ Nimčynov (1934) and some manuals, written after 1933: these sources testify that many of the ‘puristic’ opinions on morphosyntactic features of Ukrainian were rejected in the following period. \nThe fourth and last chapter deals with the orthographic question. Due to the symbolic and identity-making value of the written word, and the relationship between Orhodoxy and orthography, spelling rules were and remain one of the most debated fields of linguistic normalization in Ukraine. The process of orthographic normalization during the 1920s and the first half of the 1930s is reconstructed and discussed: the Main rules approved by the Academy of Sciences in 1921, the 1926 project, the debates on the periodical press between 1926-27, the orthographic conference convened in Charkiv in 1927, the elaboration of the 1928-29 spelling system and its main features, the 1933 spelling code and its sovietizing or russifying tendence are presented. \nThe analysis discusses plus and minuses of the two main spelling systems (1928-29 and 1933) and highlights the introduction of some rules of the 1933 spelling code in the political newspaper Visti before its official adoption in September 1933. All the facts presented and investigated prove the importance that was (and still is) attached to orthography in Ukraine. \n \n
並列構造解析の主たるタスクは並列する句の範囲を同定することである.並列構造は文の構文・意味の解析において有用な特徴となるが,これまで決定的な解析手法が確立されておらず,現在の最高精度の構文解析器においても誤りを生じさせる主たる要因となっている.既存の並列句範囲の曖昧性解消手法は並列構造の類似性のみの特性や構文解析器の結果に強く依存しているという問題があった.本研究では,近年自然言語解析に広く使用されているリカレントニューラルネットワークを用いて,構文解析の結果を用いずに単語の表層形と品詞情報のみから並列句の類似性と可換性の特徴ベクトルを計算し,並列構造の範囲を予測する手法を提案する.Penn Treebank と GENIA コーパスを用いた実験の結果,提案手法によって先行研究を上回る解析精度を得た.
There exist distinctive words that are used to express same semantics and as a result of this it has become hard to quantify the exact matching of words. To deal with this issue, past investigations endeavored to ascertain a likeness between distinctive pair of words. Conventional methodologies for computing word similarity are based on repositories like WordNet. It is a manually created lexical database and it processes semantic connection between various words. However, WordNet is a universally useful asset but wide range of words are not present in it and furthermore there exist an issue of identifying the meaning of words. Implication of words are diverse in WordNet when we utilize it in a textual framework. There exists a need of the refined approach that can gauge words resemblance in light of their co-occurrence. In this examination, we proposed an approach that registers likeness in text particular words, with the assistance of literary substance of various posts on StackOverflow. Our proposed strategy figures out word similarities in text by ascertaining the weighted co-occurrence in view of Computing Term Cooccurrence (CTC) and SentiWordNet. The exploratory outcome demonstrates that our system proposed an arrangement of words that are identified with text data is exceptional. Moreover, when it was compared with WordNet-based strategy named as WordNetres, it results with better outcomes.
Language models, which are used in various tasks including speech recognition and sentence completion, are usually used with texts covering various domains. Therefore, domain adaptation has been a long-ongoing challenge in language model research. Conventional methods mainly work by the addition of a domain dependent bias. In this paper, we propose a novel way to adapt neural network-based language models. Our proposed approach relies on a linear combination of factorised hidden layers, which are learnt by the network. For domain adaptation, we use topic features from latent Dirichlet allocation. These features are input into an auxiliary network, and the output of this network is used to calculate the hidden layer weights. Both the auxiliary network and the main network can be trained jointly by error backpropagation. This makes our proposed approach completely unsupervised. To evaluate our method, we show results for the well-known Penn Treebank and the TED-LIUM dataset.
Ratings are important in attracting foreign capital so they play a great role in the financial system of a country. The aim of the study is to investigate the impact of macroeconomic indicators on sovereign credit ratings assigned by Fitch. For this aim Panel ordered probit model was applied to the annual data from 2000 to 2011. The analysis rests on panel of 44 countries. According to the results obtained it can be concluded that gross domestic product growth rate, per capita gross domestic product, unemployment, export, default history and the level of economic development significantly affect ratings.
Estimating the entropy based on data is one of the prototypical problems in distribution property testing and estimation. For estimating the Shannon entropy of a distribution on $S$ elements with independent samples, [Paninski2004] showed that the sample complexity is sublinear in $S$, and [Valiant--Valiant2011] showed that consistent estimation of Shannon entropy is possible if and only if the sample size $n$ far exceeds $\frac{S}{\log S}$. In this paper we consider the problem of estimating the entropy rate of a stationary reversible Markov chain with $S$ states from a sample path of $n$ observations. We show that: (1) As long as the Markov chain mixes not too slowly, i.e., the relaxation time is at most $O(\frac{S}{\ln^3 S})$, consistent estimation is achievable when $n \gg \frac{S^2}{\log S}$. (2) As long as the Markov chain has some slight dependency, i.e., the relaxation time is at least $1+Ω(\frac{\ln^2 S}{\sqrt{S}})$, consistent estimation is impossible when $n \lesssim \frac{S^2}{\log S}$. Under both assumptions, the optimal estimation accuracy is shown to be $Θ(\frac{S^2}{n \log S})$. In comparison, the empirical entropy rate requires at least $Ω(S^2)$ samples to be consistent, even when the Markov chain is memoryless. In addition to synthetic experiments, we also apply the estimators that achieve the optimal sample complexity to estimate the entropy rate of the English language in the Penn Treebank and the Google One Billion Words corpora, which provides a natural benchmark for language modeling and relates it directly to the widely used perplexity measure.