Native Language Identification (NLI) is the task of automatically identifying the native language (L1) of an individual based on their language production in a learned language. It is typically framed as a classification task where the set of L1s is known a priori. Two previous shared tasks on NLI have been organized where the aim was to identify the L1 of learners of English based on essays (2013) and spoken responses (2016) they provided during a standardized assessment of academic English proficiency. The 2017 shared task combines the inputs from the two prior tasks for the first time. There are three tracks: NLI on the essay only, NLI on the spoken response only (based on a transcription of the response and i-vector acoustic features), and NLI using both responses. We believe this makes for a more interesting shared task while building on the methods and results from the previous two shared tasks. In this paper, we report the results of the shared task. A total of 19 teams competed across the three different sub-tasks. The fusion track showed that combining the written and spoken responses provides a large boost in prediction accuracy. Multiple classifier systems (e.g. ensembles and meta-classifiers) were the most effective in all tasks, with most based on traditional classifiers (e.g. SVMs) with lexical/syntactic features.

/pdf/a-report-on-the-first-native-language-identification-shared-161d18njrf.pdf

A Report on the First Native Language Identification Shared Task

Many human languages have words for emotions such as "anger" and "fear," yet it is not clear whether these emotions have similar meanings across languages, or why their meanings might vary. We estimate emotion semantics across a sample of 2474 spoken languages using "colexification"-a phenomenon in which languages name semantically related concepts with the same word. Analyses show significant variation in networks of emotion concept colexification, which is predicted by the geographic proximity of language families. We also find evidence of universal structure in emotion colexification networks, with all families differentiating emotions primarily on the basis of hedonic valence and physiological activation. Our findings contribute to debates about universality and diversity in how humans understand and experience emotion.

/pdf/emotion-semantics-show-both-cultural-variation-and-universal-2p9vmivknu.pdf

Emotion semantics show both cultural variation and universal structure

We present the results of the VarDial Evaluation Campaign on Natural Language Processing (NLP) for Similar Languages, Varieties and Dialects, which we organized as part of the fourth edition of the VarDial workshop at EACL’2017 This year, we included four shared tasks: Discriminating between Similar Languages (DSL), Arabic Dialect Identification (ADI), German Dialect Identification (GDI), and Cross-lingual Dependency Parsing (CLP) A total of 19 teams submitted runs across the four tasks, and 15 of them wrote system description papers

/pdf/findings-of-the-vardial-evaluation-campaign-2017-35bwst302c.pdf

Findings of the VarDial Evaluation Campaign 2017

Topic maps are a new ISO standard for describing knowledge structures and associating them with information resources. As such they constitute an enabling technology for knowledge management. Dubbed “the GPS of the information universe”, topic maps are also destined to provide powerful new ways of navigating large and interconnected corpora. While it is possible to represent immensely complex structures using topic maps, the basic concepts of the model – Topics, Associations, and Occurrences (TAO) – are easily grasped. This paper provides a non-technical introduction to these and other concepts (the IFS and BUTS of topic maps), relating them to things that are familiar to all of us from the realms of publishing and information management, and attempting to convey some idea of the uses to which topic maps will be put in the future.

/pdf/the-tao-of-topic-maps-finding-the-way-in-the-age-of-infoglut-44k5mbpjin.pdf

The TAO of Topic Maps finding the way in the age of infoglut

A common approach in text mining tasks such as text categorization, authorship identification or plagiarism detection is to rely on features like words, part-of-speech tags, stems, or some other high-level linguistic features. In this work, an approach that uses character n-grams as features is proposed for the task of native language identification. Instead of doing standard feature selection, the proposed approach combines several string kernels using multiple kernel learning. Kernel Ridge Regression and Kernel Discriminant Analysis are independently used in the learning stage. The empirical results obtained in all the experiments conducted in this work indicate that the proposed approach achieves state of the art performance in native language identification, reaching an accuracy that is 1.7% above the top scoring system of the 2013 NLI Shared Task. Furthermore, the proposed approach has an important advantage in that it is language independent and linguistic theory neutral. In the cross-corpus experiment, the proposed approach shows that it can also be topic independent, improving the state of the art system by 32.3%.

/pdf/can-characters-reveal-your-native-language-a-language-ab38ho9czy.pdf

Can characters reveal your native language? A language-independent approach to native language identification

This paper reports our contribution to the 2013 NLI Shared Task. The purpose of the task was to train a machine-learning system to identify the native-language affiliations of 1,100 texts written in English by nonnative speakers as part of a high-stakes test of general academic English proficiency. We trained our system on the new TOEFL11 corpus, which includes 11,000 essays written by nonnative speakers from 11 native-language backgrounds. Our final system used an SVM classifier with over 400,000 unique features consisting of lexical and POS n-grams occurring in at least two texts in the training set. Our system identified the correct nativelanguage affiliations of 83.6% of the texts in the test set. This was the highest classification accuracy achieved in the 2013 NLI Shared Task.

Maximizing Classification Accuracy in Native Language Identification

Advances in computer-assisted linguistic research have been greatly influential in reshaping linguistic research. With the increasing availability of interconnected datasets created and curated by researchers, more and more interwoven questions can now be investigated. Such advances, however, are bringing high requirements in terms of rigorousness for preparing and curating datasets. Here we present CLICS, a Database of Cross-Linguistic Colexifications (CLICS). CLICS tackles interconnected interdisciplinary research questions about the colexification of words across semantic categories in the world's languages, and show-cases best practices for preparing data for cross-linguistic research. This is done by addressing shortcomings of an earlier version of the database, CLICS2, and by supplying an updated version with CLICS3, which massively increases the size and scope of the project. We provide tools and guidelines for this purpose and discuss insights resulting from organizing student tasks for database updates.

/pdf/the-database-of-cross-linguistic-colexifications-25bmcdj974.pdf

The Database of Cross-Linguistic Colexifications, reproducible analysis of cross-linguistic polysemies.

Geir Ove Grønmo Ontopia Waldemar Thranes gt. 98 Oslo, 0175 Norway phone +47 23233080 fax +47 23233081 email grove@ontopia.net web http://www.ontopia.net This paper is concerned with the issue of scope in topic maps. Topic maps are a form of knowledge representation suitable for solving a number of complex problems in the area of information management, ranging from findability (navigation and querying) to knowledge management and enterprise application integration (EAI). The topic map paradigm has its roots in efforts to understand the essential semantics of back-of-book indexes in order that they might be captured in a form suitable for computer processing. Once understood, the model of a back-ofbook index was generalised in order to cover the needs of digital information, and extended to encompass glossaries and thesauri, as well as indexes. The resulting core model, of typed topics, associations, and occurrences, has many similarities with the semantic networks developed by the artificial intelligence community for representing knowledge structures. (For a more detailed introduction to the topic map model, see [Pepp 00].) One key requirement of topic maps from the earliest days was to be able to merge indexes from disparate origins. This requirement accounts for two further concepts that greatly enhance the power of topic maps: subject identity and scope. This paper concentrates on scope, but also includes a brief discussion of the feature known as the topic naming constraint, with which it is closely related. It is based on the authors’ experience in creating topic maps (in particular, the Italian Opera Topic Map [Pepp 01]), and in implementing processing systems for topic maps (in particular, the Ontopia Topic Map Engine and Navigator [Onto 01]).

Towards a General Theory of Scope

This article provides an introduction to the new topic map standard (ISO/IEC 13250) with particular reference to the domain of encyclopaedia publishing, and discusses the relationship between topic maps and the W3C recommendation Resource Description Framework (RDF). It is based on the author’s participation in the development of the topic map standard (representing Norway in SC34, the ISO committee responsible for SGML and related standards), and two years’ collaboration with leading reference works publishers in Norway, Denmark, Sweden, Poland and Germany.

Steve Pepper

Papers

The TAO of Topic Maps finding the way in the age of infoglut

Maximizing Classification Accuracy in Native Language Identification

The Database of Cross-Linguistic Colexifications, reproducible analysis of cross-linguistic polysemies.

Towards a General Theory of Scope

Navigating haystacks and discovering needles: introducing the new topic map standard