Articles

In this paper we apply existing directional similarity measures to identify hypernyms with a state-of-the-art distributional semantic model. We also propose a new directional measure that achieves the best performance in hypernym identification. 1...

We investigate the semantic relationship be- tween a noun and its adjectival modifiers. We introduce a class of probabilistic mod- els that enable us to to simultaneously cap- ture both the semantic similarity of nouns and modifiers, and adjective-noun selectional preference. Through a combination of novel and existing evaluations we …...

In this paper, we investigate a full-fledged supervised machine learning framework for identifying English phrasal verbs in a given context. We concentrate on those that we de- fine as the most confusing phrasal verbs, in the sense that they are the most commonly used ones whose occurrence may correspond either …...

Corpus-based thesaurus construction for Mor- phologically Rich Languages (MRL) is a com- plex task, due to the morphological variability of MRL. In this paper we explore alternative term representations, complemented by cluster- ing of morphological variants. We introduce a generic algorithmic scheme for thesaurus con- struction in MRL, and demonstrate …...

The correct choice of words has proven chal- lenging for learners of a second language and errors of this kind form a separate category in error typology. This paper focuses on one known example of two verbs that are often confused by non-native speakers of Germanic languages, to make and …...

Text reuse is common in many scenarios and documents are often based, at least in part, on existing documents. This paper reports an ap- proach to detecting text reuse which identifies not only documents which have been reused verbatim but is also designed to identify cases of reuse when the …...

We present the results of several machine learning tasks designed to predict rhetori- cal relations that hold between clauses in discourse. We demonstrate that organizing rhetorical relations into different granularity categories (based on relative degree of detail) increases average prediction accuracy from 58% to 70%. Accuracy further increases to 80% …...

This paper presents a novel sentence cluster- ing scheme based on projecting sentences over term clusters. The scheme incorporates exter- nal knowledge to overcome lexical variability and small corpus size, and outperforms com- mon sentence clustering methods on two real- life industrial datasets. 1...

Wikipedia is a Web based, freely available multilingual encyclopedia, constructed in a collaborative effort by thousands of contribu- tors. Wikipedia articles on the same topic in different languages are connected via interlin- gual (or translational) links. These links serve as an excellent resource for obtaining lexical translations, or building multilingual …...

This paper explores the hypothesis that se- mantic relatedness may be more reliably in- ferred by using a multilingual space, as com- pared to the typical monolingual representa- tion. Through evaluations using several state- of-the-art semantic relatedness systems, ap- plied on standard datasets, we show that a multilingual approach is …...

We present a novel adaptive clustering model for coreference resolution in which the expert rules of a state of the art deterministic sys- tem are used as features over pairs of clus- ters. A significant advantage of the new ap- proach is that the expert rules can be eas- ily …...

Linking implicit semantic roles is a challeng- ing problem in discourse processing. Unlike prior work inspired by SRL, we cast this prob- lem as an anaphora resolution task and embed it in an entity-based coreference resolution (CR) architecture. Our experiments clearly show that CR-oriented features yield strongest performance exceeding a …...

This paper describes our participation in the task denominated Cross-Lingual Textual En- tailment (CLTE) for content synchronization. We represent an approach to CLTE using machine translation to tackle the problem of multilinguality. Our system resides on ma- chine learning and in the use of WordNet as semantic source knowledge. Results …...

A U.S. Congressional bill is a textual artifact that must pass through a series of hurdles to become a law. In this paper, we focus on one of the most precarious and least understood stages in a bill’s life: its consideration, behind closed doors, by a Congressional committee. We construct …...

With a few exceptions, extensions to latent Dirichlet allocation (LDA) have focused on the distribution over topics for each document. Much less attention has been given to the un- derlying structure of the topics themselves. As a result, most topic models generate topics in- dependently from a single underlying distri- …...

We propose an unsupervised method for clus- tering the translations of a word, such that the translations in each cluster share a com- mon semantic sense. Words are assigned to clusters based on their usage distribution in large monolingual and parallel corpora using the soft K-Means algorithm. In addition to …...

When people describe a scene, they often in- clude information that is not visually apparent; sometimes based on background knowledge, sometimes to tell a story. We aim to sepa- rate visual text—descriptions of what is being seen—from non-visual text in natural images and their descriptions. To do so, we first …...

Concept-to-text generation refers to the task of automatically producing textual output from non-linguistic input. We present a joint model that captures content selection (“what to say”) and surface realization (“how to say”) in an unsupervised domain-independent fashion. Rather than breaking up the generation pro- cess into a sequence of local …...

Not all learning takes place in an educational setting: more and more self-motivated learners are turning to on-line text to learn about new topics. Our goal is to provide such learners with the well-known benefits of testing by au- tomatically generating quiz questions for on- line text. Prior work on …...

We investigate the task of medical concept coreference resolution in clinical text using two semi-supervised methods, co-training and multi-view learning with posterior regulariza- tion. By extracting semantic and temporal features of medical concepts found in clinical text, we create conditionally independent data views; co-training MaxEnt classifiers on this data works …...