Articles

Classifying nouns into semantic categories (e.g., animals, food) is an important line of research in both cognitive science and natural language processing. We present a minimally supervised model for noun classification, which uses symmetric patterns (e.g., “X and Y”) and an iterative variant of the k-Nearest Neighbors algorithm. Unlike most …...

Word Sense Induction is a task of automatically finding word senses from large scale texts. It is general- ly considered as an unsupervised clustering problem. This paper introduces a hypergraph model in which nodes represent instances of contexts where a target word occurs and hyperedges represent high- er-order semantic relatedness …...

This paper describes a new Word Sense Disambiguation (WSD) algorithm which extends two well-known variations of the Lesk WSD method. Given a word and its context, Lesk algorithm exploits the idea of maximum number of shared words (maximum overlaps) between the context of a word and each definition of its …...

We present a submodular function-based framework for query-focused opinion summarization. Within our framework, relevance ordering produced by a statistical ranker, and information coverage with respect to topic distribution and diverse viewpoints are both encoded as submodular functions. Dispersion functions are utilized to minimize the redundancy. We are the first to …...

Information Extraction using multiple information sources and systems is beneficial due to multi- source/system consolidation and challenging due to the resulting inconsistency and redundancy. We integrate IE and truth-finding research and present a novel unsupervised multi-dimensional truth finding framework which incorporates signals from multiple sources, multiple systems and multiple pieces …...

To obtain a complete temporal picture of a relation it is necessary to aggregate fragments of tem- poral information across relation instances in text. This process is non-trivial even for humans because temporal information can be imprecise and inconsistent, and systems face the additional challenge that each of their classifications …...

Disambiguating named entities (NE) in running text to their correct interpretations in a specific knowledge base (KB) is an important problem in NLP. This paper presents two collective disam- biguation approaches using a graph representation where possible KB candidates for NE textual mentions are represented as nodes and the coherence …...

We investigate methods for aggregating the judgements of multiple individuals in a linguistic annotation task into a collective judgement. We define several aggregators that take the relia- bility of annotators into account and thus go beyond the commonly used majority vote, and we empirically analyse their performance on new datasets …...

We present 3arif1, a large-scale corpus of Modern Standard and Egyptian Arabic tweets annotated for epistemic modality2. To create 3arif, we design an interactive crowdsourcing annotation procedure that splits up the annotation process into a series of simplified questions, dispenses with the requirement for expert linguistic knowledge and captures nested …...

We construct a hierarchically aligned Chinese-English parallel treebank by manually doing word alignments and phrase alignments simultaneously on parallel phrase-based parse trees. The main innovation of our approach is that we leave words without a translation counterpart (which are mostly language-particular function words) unaligned on the word level, and locate …...

Explicit continuous vector representation such as vector representation of words, phrases, etc. has been proven effective for various NLP tasks. This paper proposes a novel method of constructing such vector representation for both entity-pairs and relation expressions which link them in text. Based on the insight of the duality of …...

In this paper, we present a novel approach to model arguments, their components and relations in persuasive essays in English. We propose an annotation scheme that includes the annotation of claims and premises as well as support and attack relations for capturing the structure of argu- mentative discourse. We further …...

While discussing a concrete controversial topic, most humans will find it challenging to swiftly raise a diverse set of convincing and relevant claims that should set the basis of their arguments. Here, we formally define the challenging task of automatic claim detection in a given context and discuss its associated …...

While reading a document, a user may encounter concepts, entities, and topics that she is interested in exploring more. We propose models of “interestingness”, which aim to predict the level of interest a user has in the various text spans in a document. We obtain naturally occurring interest signals by …...

Keyphrases have found wide ranging application in NLP and IR tasks such as document sum- marization, indexing, labeling, clustering and classification. In this paper we pose the problem of extracting label specific keyphrases from a document which has document level metadata as- sociated with it namely labels or tags (i.e. …...

In this paper1, we present a novel beam-search decoder for disfluency detection. We first pro- pose node-weighted max-margin Markov networks (M3N) to boost the performance on words belonging to specific part-of-speech (POS) classes. Next, we show the importance of measur- ing the quality of cleaned-up sentences and performing multiple passes …...

In this article, we describe a new approach to distributional semantics. This approach relies on a generative model of sentences with latent variables, which takes the syntax into account by using syntactic dependency trees. Words are then represented as posterior distributions over those latent classes, and the model allows to …...

In this paper, we address the role of syntactic parsing for distributional similarity. On the one hand, we are exploring distributional similarities as an extrinsic test bed for unsupervised parsers. On the other hand, we explore whether single unsupervised parsers, or their combination, can contribute to better distributional similarities, or …...

We manually created a semantic taxonomy called Phased Predicate Template Taxonomy (PPTT) that covers 12,023 predicate templates (i.e., predicates with one argument slot like “rescue X”) and derived from it various semantic relations between these templates on a million-instance scale (70%-80% precision level). The derived relations include entailment (e.g., rescue …...

Automatically identifying anomalous newswire events is a hard problem. We discuss the com- plexity of the problem and introduce a novel technique to model events based on recursive neural networks to represent events as composition of their semantic arguments. Our model learns to differentiate between normal and anomalous events. We …...