Articles

This research studies the text genre of mes- sage board forums, which contain a mix- ture of expository sentences that present fac- tual information and conversational sentences that include communicative acts between the writer and readers. Our goal is to create sentence classifiers that can identify whether a sentence contains …...

Multiword expressions (MWE), a known nui- sance for both linguistics and NLP, blur the lines between syntax and semantics. Previous work on MWE identification has relied primar- ily on surface statistics, which perform poorly for longer MWEs and cannot model discontin- uous expressions. To address these problems, we show that …...

We present the first algorithms to automat- ically identify explicit discourse connectives and the relations they signal for Arabic text. First we show that, for Arabic news, most adjacent sentences are connected via explicit connectives in contrast to English, making the treatment of explicit discourse connectives for Arabic highly important. …...

The last decade has seen many interesting ap- plications of Question Answering (QA) tech- nology. The Jeopardy! quiz show is certainly one of the most fascinating, from the view- points of both its broad domain and the com- plexity of its language. In this paper, we study kernel methods applied …...

Augmented and alternative communication (AAC) devices enable users with certain com- munication disabilities to participate in every- day conversations. Such devices often rely on statistical language models to improve text entry by offering word predictions. These predictions can be improved if the language model is trained on data that closely …...

Decision trees have been applied to a vari- ety of NLP tasks, including language mod- eling, for their ability to handle a variety of attributes and sparse context space. More- over, forests (collections of decision trees) have been shown to substantially outperform individual decision trees. In this work, we in- …...

Context Peter D. Turney Inst. for Info. Tech. NRC Canada Ottawa, Canada peter.turney@nrc-cnrc.gc.ca Yair Neuman Dept. of Education Ben-Gurion Univ. Beer-Sheva, Israel yneuman@bgu.ac.il Dan Assaf Dept. of Education Ben-Gurion Univ. Beer-Sheva, Israel dan.assaf4@googlemail.com Yohai Cohen Gilasio Coding Tel-Aviv, Israel yohai@gilasio.com Abstract Metaphor is ubiquitous in text, even in highly technical …...

We address the creation of cross-lingual tex- tual entailment corpora by means of crowd- sourcing. Our goal is to define a cheap and replicable data collection methodology that minimizes the manual work done by expert annotators, without resorting to preprocess- ing tools or already annotated monolingual datasets. In line with …...

In the last few years, the interest of the re- search community in micro-blogs and social media services, such as Twitter, is growing ex- ponentially. Yet, so far not much attention has been paid on a key characteristic of micro- blogs: the high level of information redun- dancy. The aim …...

Responding to the need for semantic lexical resources in natural language processing ap- plications, we examine methods to acquire noun compounds (NCs), e.g., orange juice, to- gether with suitable fine-grained semantic in- terpretations, e.g., squeezed from, which are directly usable as paraphrases. We employ bootstrapping and web statistics, and utilize …...

In this paper we present a fully unsupervised syntactic class induction system formulated as a Bayesian multinomial mixture model, where each word type is constrained to belong to a single class. By using a mixture model rather than a sequence model (e.g., HMM), we are able to easily add multiple …...

In this paper, we describe a novel approach to cascaded learning and inference on sequences. We propose a weakly joint learning model on cascaded inference on sequences, called multilayer sequence labeling. In this model, inference on sequences is modeled as cas- caded decision. However, the decision on a sequence labeling …...

We present an inference algorithm that orga- nizes observed words (tokens) into structured inflectional paradigms (types). It also natu- rally predicts the spelling of unobserved forms that are missing from these paradigms, and dis- covers inflectional principles (grammar) that generalize to wholly unobserved words. Our Bayesian generative model of the …...

A key factor of high quality word segmenta- tion for Japanese is a high-coverage dictio- nary, but it is costly to manually build such a lexical resource. Although external lexical resources for human readers are potentially good knowledge sources, they have not been utilized due to differences in segmentation cri- …...

We consider the problem of predicting mea- surable responses to scientific articles based primarily on their text content. Specif- ically, we consider papers in two fields (economics and computational linguistics) and make predictions about downloads and within-community citations. Our approach is based on generalized linear models, allowing interpretability; a novel …...

We present a data-driven approach to generat- ing responses to Twitter status posts, based on phrase-based Statistical Machine Translation. We find that mapping conversational stimuli onto responses is more difficult than translat- ing between languages, due to the wider range of possible responses, the larger fraction of unaligned words/phrases, and …...

In recent years, the amount of user-generated opinionated texts (e.g., reviews, user com- ments) continues to grow at a rapid speed: fea- tured news stories on a major event easily at- tract thousands of user comments on a popular online News service. How to consume subjec- tive information of this …...

In this paper, we propose a novel topic model based on incorporating dictionary definitions. Traditional topic models treat words as surface strings without assuming predefined knowledge about word mean- ing. They infer topics only by observing surface word co-occurrence. However, the co-occurred words may not be semanti- cally related in …...

This paper introduces an attribute selection task as a way to characterize the inherent mea- ning of property-denoting adjectives in adjec- tive-noun phrases, such as e.g. hot in hot sum- mer denoting the attribute TEMPERATURE, rather than TASTE. We formulate this task in a vector space model that represents adjec- …...

We consider the problem of performing learn- ing and inference in a large scale knowledge base containing imperfect knowledge with incomplete coverage. We show that a soft inference procedure based on a combination of constrained, weighted, random walks through the knowledge base graph can be used to reliably infer new …...