Articles

Cost-sensitive classification, where the features used in machine learning tasks have a cost, has been explored as a means of balancing knowl- edge against the expense of incrementally ob- taining new features. We introduce a setting where humans engage in classification with incrementally revealed features: the collegiate trivia circuit. By …...

We present a systematic analysis of exist- ing multi-domain learning approaches with re- spect to two questions. First, many multi- domain learning algorithms resemble ensem- ble learning algorithms. (1) Are multi-domain learning improvements the result of ensemble learning effects? Second, these algorithms are traditionally evaluated in a balanced class la- …...

Taxonomies can serve as browsing tools for document collections. However, given an ar- bitrary collection, pre-constructed taxonomies could not easily adapt to the specific topic/task present in the collection. This paper explores techniques to quickly derive task-specific tax- onomies supporting browsing in arbitrary document collections. The supervised ap- proach directly …...

Bridging the lexical gap between the user’s question and the question-answer pairs in the Q&A archives has been a major challenge for Q&A retrieval. State-of-the-art approaches address this issue by implicitly expanding the queries with additional words using statistical translation models. While useful, the effec- tiveness of these models is …...

We annotate and resolve a particular case of abstract anaphora, namely, this- issue anaphora. We propose a candidate ranking model for this-issue anaphora resolution that explores different issue- specific and general abstract-anaphora features. The model is not restricted to nominal or verbal antecedents; rather, it is able to identify antecedents …...

Pairwise coreference resolution models must merge pairwise coreference decisions to gen- erate final outputs. Traditional merging meth- ods adopt different strategies such as the best- first method and enforcing the transitivity con- straint, but most of these methods are used independently of the pairwise learning meth- ods as an isolated …...

We explore the interplay of knowledge and structure in co-reference resolution. To inject knowledge, we use a state-of-the-art system which cross-links (or “grounds”) expressions in free text to Wikipedia. We explore ways of using the resulting grounding to boost the performance of a state-of-the-art co-reference resolution system. To maximize the …...

Adjectival modification, particularly by ex- pressions that have been treated as higher- order modifiers in the formal semantics tradi- tion, raises interesting challenges for semantic composition in distributional semantic mod- els. We contrast three types of adjectival mod- ifiers – intersectively used color terms (as in white towel, clearly first-order), …...

Decoding algorithms for syntax based ma- chine translation suffer from high compu- tational complexity, a consequence of in- tersecting a language model with a con- text free grammar. Left-to-right decoding, which generates the target string in order, can improve decoding efficiency by simpli- fying the language model evaluation. This paper …...

Single-word vector space models have been very successful at learning lexical informa- tion. However, they cannot capture the com- positional meaning of longer phrases, prevent- ing them from a deeper understanding of lan- guage. We introduce a recursive neural net- work (RNN) model that learns compositional vector representations for phrases …...

Existing vector space models typically map synonyms and antonyms to similar word vec- tors, and thus fail to represent antonymy. We introduce a new vector space representation where antonyms lie on opposite sides of a sphere: in the word vector space, synonyms have cosine similarities close to one, while antonyms …...

Approximate search algorithms, such as cube pruning in syntactic machine translation, rely on the language model to estimate probabili- ties of sentence fragments. We contribute two changes that trade between accuracy of these estimates and memory, holding sentence-level scores constant. Common practice uses lower- order entries in an N-gram model …...

We introduce a model of coherence which captures the intentional discourse structure in text. Our work is based on the hypothesis that syntax provides a proxy for the communica- tive goal of a sentence and therefore the se- quence of sentences in a coherent discourse should exhibit detectable structural patterns. …...

PCFGs can grow exponentially as additional annotations are added to an initially simple base grammar. We present an approach where multiple annotations coexist, but in a factored manner that avoids this combinatorial explo- sion. Our method works with linguistically- motivated annotations, induced latent struc- ture, lexicalization, or any mix of …...

This paper presents PATTY: a large resource for textual patterns that denote binary relations between entities. The patterns are semanti- cally typed and organized into a subsumption taxonomy. The PATTY system is based on ef- ficient algorithms for frequent itemset mining and can process Web-scale corpora. It har- nesses the …...

We present a method for exact optimization and sampling from high order Hidden Markov Models (HMMs), which are generally han- dled by approximation techniques. Motivated by adaptive rejection sampling and heuris- tic search, we propose a strategy based on sequentially refining a lower-order language model that is an upper bound …...

This paper deals with the problem of predict- ing structures in the context of NLP. Typically, in structured prediction, an inference proce- dure is applied to each example independently of the others. In this paper, we seek to op- timize the time complexity of inference over entire datasets, rather than …...

Conditional random fields and other graphi- cal models have achieved state of the art re- sults in a variety of tasks such as coreference, relation extraction, data integration, and pars- ing. Increasingly, practitioners are using mod- els with more complex structure—higher tree- width, larger fan-out, more features, and more data—rendering …...

Many NLP tasks rely on accurate statis- tics from large corpora. Tracking com- plete statistics is memory intensive, so recent work has proposed using compact approx- imate “sketches” of frequency distributions. We describe 10 sketch methods, including ex- isting and novel variants. We compare and study the errors (over-estimation and …...

Short listings such as classified ads or product listings abound on the web. If a computer can reliably extract information from them, it will greatly benefit a variety of applications. Short listings are, however, challenging to process due to their informal styles. In this paper, we present an unsupervised information …...