Articles

AbstractWe present a large scale study of the languages spoken by bilingual workers on Mechanical Turk (MTurk). We establish a methodology for determining the language skills of anonymous crowd workers that is more robust than simple surveying. We validate workers’ self-reported language skill claims by measuring their ability to correctly …...

AbstractWe propose to use the visual denotations of linguistic expressions (i.e. the set of images they describe) to define novel denotational similarity metrics, which we show to be at least as beneficial as distributional similarities for two tasks that require semantic inference. To compute these denotational similarities, we construct a …...

AbstractWe consider a multilingual weakly supervised learning scenario where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide the learning in other languages. Past approaches project labels across bitext and use them as features or gold labels for training. We propose a new method that …...

AbstractParsers that parametrize over wider scopes are generally more accurate than edge-factored models. For graph-based non-projective parsers, wider factorizations have so far implied large increases in the computational complexity of the parsing problem. This paper introduces a “crossing-sensitive” generalization of a third-order factorization that trades off complexity in the model …...

AbstractWe present an incremental dependency parsing model that jointly performs disfluency detection. The model handles speech repairs using a novel non-monotonic transition system, and includes several novel classes of features. For comparison, we evaluated two pipeline systems, using state-of-the-art disfluency detectors. The joint model performed better on both tasks, with …...

AbstractWe develop parsing oracles for two transition-based dependency parsers, including the arc-standard parser, solving a problem that was left open in (Goldberg and Nivre, 2013). We experimentally show that using these oracles during training yields superior parsing accuracies on many languages....

AbstractLanguage identification is the task of automatically detecting the language(s) present in a document based on the content of the document. In this work, we address the problem of detecting documents that contain text from more than one language (multilingual documents). We introduce a method that is able to detect …...

AbstractWe present heterogeneous networks as a way to unify lexical networks with relational data. We build a unified ACL Anthology network, tying together the citation, author collaboration, and term-cooccurence networks with affiliation and venue relations. This representation proves to be convenient and allows problems such as name disambiguation, topic modeling, …...

AbstractWe present FLORS, a new part-of-speech tagger for domain adaptation. FLORS uses robust representations that work especially well for unknown words and for known words with unseen tags. FLORS is simpler and faster than previous domain adaptation methods, yet it has significantly better accuracy than several baselines....

AbstractThe past 10 years of event ordering research has focused on learning partial orderings over document events and time expressions. The most popular corpus, the TimeBank, contains a small subset of the possible ordering graph. Many evaluations follow suit by only testing certain pairs of events (e.g., only main verbs …...

AbstractPrepositional phrase (PP) attachment disambiguation is a known challenge in syntactic parsing. The lexical sparsity associated with PP attachments motivates research in word representations that can capture pertinent syntactic and semantic features of the word. One promising solution is to use word vectors induced from large amounts of raw text. …...

AbstractThis paper presents the results of a large-scale evaluation study of window-based Distributional Semantic Models on a wide variety of tasks. Our study combines a broad coverage of model parameters with a model selection methodology that is robust to overfitting and able to capture parameter interactions. We show that our …...

AbstractLanguage proficiency tests are used to evaluate and compare the progress of language learners. We present an approach for automatic difficulty prediction of C-tests that performs on par with human experts. On the basis of detailed analysis of newly collected data, we develop a model for C-test difficulty introducing four …...

AbstractIn this paper, we study the problems of opinion expression extraction and expression-level polarity and intensity classification. Traditional fine-grained opinion analysis systems address these problems in isolation and thus cannot capture interactions among the textual spans of opinion expressions and their opinion-related properties. We present two types of joint approaches …...

AbstractWe define two proper subclasses of subsequential functions based on the concept of Strict Locality (McNaughton and Papert, 1971; Rogers and Pullum, 2011; Rogers et al., 2013) for formal languages. They are called Input and Output Strictly Local (ISL and OSL). We provide an automata-theoretic characterization of the ISL class …...

AbstractSemantic parsing is the task of translating natural language utterances into a machine-interpretable meaning representation. Most approaches to this task have been evaluated on a small number of existing corpora which assume that all utterances must be interpreted according to a database and typically ignore context. In this paper we …...

. Analogy-based Text Normalization : the case of unknowns words. In this paper, we describe and evaluate a system for improving the quality of noisy texts containing non-word errors. It is meant to be integrated into a full information extraction architecture, and aims at improving its results. For each word …...

. In the course of the last two decades, numerous algorithms have sprouted up that successfully capture the semantics of single words by looking at their distribution in text, and comparing these distributions in a vector space model. However, it is not straightforward to construct meaning representations beyond the level …...

. In this paper, we test two distinct approaches to chunk transcribed oral data, trying to minimize the phases of manual correction. First, we use an existing chunker, learned from written texts, then we try to learn a new specific chunker from a small amount of manually corrected labeled oral …...

De-identifying textual data is an important task for publishing and sharing the data among researchers while protecting privacy of indi- viduals referenced therein. While supervised learning approaches are successfully applied to the task in the clinical domain, existing methods are hard to transfer to different do- mains and languages because …...