Articles

We propose two hashing-based solutions to the problem of fast and effective personal names spelling correction in People Search applications. The key idea behind our meth- ods is to learn hash functions that map similar names to similar (and compact) binary code- words. The two methods differ in the data …...

This paper addresses the problem of learn- ing to map sentences to logical form, given training data consisting of natural language sentences paired with logical representations of their meaning. Previous approaches have been designed for particular natural languages or specific meaning representations; here we present a more general method. The …...

We reveal a previously unnoticed connection between dependency parsing and statistical machine translation (SMT), by formulating the dependency parsing task as a problem of word alignment. Furthermore, we show that two well known models for these respective tasks (DMV and the IBM models) share com- mon modeling assumptions. This motivates …...

Inducing a grammar directly from text is one of the oldest and most challenging tasks in Computational Linguistics. Significant progress has been made for inducing depen- dency grammars, however the models em- ployed are overly simplistic, particularly in comparison to supervised parsing models. In this paper we present an approach …...

We propose an approach to adjective-noun composition (AN) for corpus-based distribu- tional semantics that, building on insights from theoretical linguistics, represents nouns as vectors and adjectives as data-induced (lin- ear) functions (encoded as matrices) over nominal vectors. Our model significantly out- performs the rivals on the task of reconstruct- ing …...

Linguistic Steganography is concerned with hiding information in natural language text. One of the major transformations used in Lin- guistic Steganography is synonym substitu- tion. However, few existing studies have stud- ied the practical application of this approach. In this paper we propose two improvements to the use of synonym …...

Mining sentiment from user generated content is a very important task in Natural Language Processing. An example of such content is threaded discussions which act as a very im- portant tool for communication and collabo- ration in the Web. Threaded discussions in- clude e-mails, e-mail lists, bulletin boards, newsgroups, and …...

We present an approach to grammar induc- tion that utilizes syntactic universals to im- prove dependency parsing across a range of languages. Our method uses a single set of manually-specified language-independent rules that identify syntactic dependencies be- tween pairs of syntactic categories that com- monly occur across languages. During infer- …...

We introduce tiered clustering, a mixture model capable of accounting for varying de- grees of shared (context-independent) fea- ture structure, and demonstrate its applicabil- ity to inferring distributed representations of word meaning. Common tasks in lexical se- mantics such as word relatedness or selec- tional preference can benefit from modeling …...

We present a novel approach for (written) di- alect identification based on the discrimina- tive potential of entire words. We generate Swiss German dialect words from a Standard German lexicon with the help of hand-crafted phonetic/graphemic rules that are associated with occurrence maps extracted from a linguis- tic atlas created …...

With the proliferation of user-generated arti- cles over the web, it becomes imperative to de- velop automated methods that are aware of the ideological-bias implicit in a document col- lection. While there exist methods that can classify the ideological bias of a given docu- ment, little has been done toward …...

The computation of meaning similarity as operationalized by vector-based models has found widespread use in many tasks ranging from the acquisition of synonyms and para- phrases to word sense disambiguation and tex- tual entailment. Vector-based models are typ- ically directed at representing words in isola- tion and thus best suited …...

Recurrent event queries (REQ) constitute a special class of search queries occurring at regular, predictable time intervals. The fresh- ness of documents ranked for such queries is generally of critical importance. REQ forms a significant volume, as much as 6% of query traffic received by search engines. In this work, …...

In contrast with the booming increase of inter- net data, state-of-art QA (question answering) systems, otherwise, concerned data from spe- cific domains or resources such as search en- gine snippets, online forums and Wikipedia in a somewhat isolated way. Users may welcome a more general QA system for its capability …...

Determining whether two terms in text have an ancestor relation (e.g. Toyota and car) or a sibling relation (e.g. Toyota and Honda) is an essential component of textual inference in NLP applications such as Question Answer- ing, Summarization, and Recognizing Textual Entailment. Significant work has been done on developing stationary …...

Although many algorithms have been devel- oped to harvest lexical resources, few organize the mined terms into taxonomies. We pro- pose (1) a semi-supervised algorithm that uses a root concept, a basic level concept, and re- cursive surface patterns to learn automatically from the Web hyponym-hypernym pairs sub- ordinated to …...

Even the entire Web corpus does not explic- itly answer all questions, yet inference can un- cover many implicit answers. But where do inference rules come from? This paper investigates the problem of learn- ing inference rules from Web text in an un- supervised, domain-independent manner. The SHERLOCK system, described …...

In this paper, we conducted a systematic com- parative analysis of language in different con- texts of bursty topics, including web search, news media, blogging, and social bookmark- ing. We analyze (1) the content similarity and predictability between contexts, (2) the cov- erage of search content by each context, and …...

In this paper we develop an approach to tackle the problem of verb selection for learners of English as a second language (ESL) by using features from the output of Semantic Role La- beling (SRL). Unlike existing approaches to verb selection that use local features such as n-grams, our approach …...

In this paper, we introduce a method that au- tomatically builds text classifiers in a new lan- guage by training on already labeled data in another language. Our method transfers the classification knowledge across languages by translating the model features and by using an Expectation Maximization (EM) algorithm that naturally …...