More Publications (66)

1A Pattern Matching Method for Finding Noun and Proper Noun Translations from Noisy Parallel Corpora1995  Pascale Pungparallel texts. We have previously shown that using a vector representation of the frequency and positional information of a high...

2Semantic Information and Derivation Rules for Robust Dialogue Act Detection in a Spoken Dialogue System. . . , Rl}. Based on PST T (s) and DR set D, a vector representation v(s) for sentence s can be constructed according to...

3Automated Pyramid Scoring of Summaries using Distributional Semanticslargely on observed words. A 100dimension latent vector representation was learned for every span of contiguous words within...

4Learning Semantic Textual Similarity with Structural Representationscombine several structural models into the feature vector representation. The contribution of this paper is as follows: (i)...

5Learning Word Vectors for Sentiment AnalysisBarzilay, 2007). This component of the model uses the vector representation of words to predict the sentiment annotations on contexts...

6ExemplarBased Models for Word Meaning in Context2010  Katrin Erk,Sebastian Padódeciding paraphrase applicability. With a very simple vector representation and just using activation, we outperform the stat...

7IRIS: a Chatoriented Dialogue System based on the Vector Space Model2012  Rafael E. Banchs,Haizhou Liwith all existent utterances in the database, a vector representation of the current dialogue history is also compared...

8Reembedding words2013  Igor Labutov,Hod Lipsonsufficiently small. 1 Introduction Incorporating the vector representation of a word as a feature, has recently been shown to...

9Adaptation Data Selection using Neural Language Models: Experiments in Machine Translationdata selection. We hypothesize that the continuous vector representation of words in neural language models makes them more...

10EntityBased Local Coherence Modelling Using Topological Fields2010  Jackie Chi Kit Cheung,Gerald Pennentity grid representation of it, and c) the feature vector representation of the abbreviated entity grid for transitions of...

11Probabilistic Domain Modelling With Contextualized Distributional Semantic Vectors2013  Jackie Chi Kit Cheung,Gerald Pennidentity, tokens in DSHMM are also associated with a vector representation of their meaning in context according to a distributional...

12A Feature Based Approach to Leveraging Context for Classifying Newsgroup Style Discussion Segmentsminimum of all cosine distance measures between the vector representation of the span of text and that of each of the spans...

13Fixed Length Word Suffix for Factored Statistical Machine Translationby (Koehn et. al. 2007), allow words to have a vector representation. The model can then extend the definition of each...

14Supervised Ranking in OpenDomain Text Summarization2002  Tadashi Nomoto,Yuji Matsumotoas wis is expressed as in Table 1, where ~u is a vector representation of u, consisting of a set of values for features of...

15Making Sense of Sound: Unsupervised Topic Segmentation over Acoustic Inputbetween them. In what follows, we first present a vector representation used in this computation, and then specify the alignment...

16Bridging Languages through Etymology: The case of cross language text categorization2013  Vivi Nastase,Carlo Strapparavathe corpus: W = {w1, ..., wk}. Position j in the vector representation of di corresponds to word wj , and it may have different...

17Discriminative Syntactic Language Modeling for Speech Recognitionparse tree for string w. • Φ(a,w) ∈ Rd is a featurevector representation of an acoustic input a together with a string w....

18HALBased Cascaded Model for VariableLength Semantic Pattern Induction from Psychiatry Web Resourcesrepresents each word in the vocabulary using a vector representation. Each w1 w2 wl2 wl1 wl AObservation window...

19Generalizing semantic role annotations across syntactically similar verbs2007  Andrew S. Gordon,Reid Swansonconverting tree structures into a flat, featurevector representation. For each sentence, we identified all possible parse...

20Structural Semantic Relatedness: A KnowledgeBased Method to Named Entity Disambiguation2010  Xianpei Han,Jun Zhaothe Google Web1T 5gram corpus4. Given the concept vector representation of two name observations oi and oj, their similarity...

21Compositional MatrixSpace Models of Languagesurjective function ψ./ : Rn → Rn′×n′ that translates the vector representation into a matrix representation in a way such that for...

22Generating Image Descriptions Using Dependency Relational Patterns2010  Ahmet Aker,Robert Gaizauskasto the query (toponym) (cosine similarity over the vector representation of the sentence and the query). • centroidSimilarity:...

23Parsing with Compositional Vector GrammarsVector Representations In most systems that use a vector representation for words, such vectors are based on cooccurrence...

24Compositionally Derived Representations of Morphologically Complex Words in Distributional Semanticsmapping from and onto word vectors, without requiring a vector representation of bound affixes. The reason at the base of its good...

25An Ontologybased Semantic Tagger for IE system2003  Narjès Boufadenand the result of our experiments. 4.3 Similarity vector representation A similarity vector is a vector where each element...

26Inferring Activity Time in News through Event Modeling2008  Vladimir Eidelmanexpressions present in the document to the feature vector representation of each document. 3.3 IntraArticle Event Representation...

27Automatic Generation of Informationseeking Questions Using Concept Clusters2009  Shuguang Li,Suresh ManandharD3{Indy 500, Truck series, ...}, ...}, and hence the vector representation for a given document Dj using C414 will be

28EventBased Hyperspace Analogue to Language for Query Expansiondirection sensitivity is ignored to obtain a single vector representation of a word by adding corresponding row and column vectors...

29ConfidenceWeighted Learning of Factored Discriminative Language Models2011  Viet Ha Thuc,Nicola Canceddaw>∆t ≥ 1 (2) where ∆t = φ(pt) − φ(nt), φ(x) is the vector representation of sentence x in factored feature space, and Λt is...

30Topic Modeling Based Classification of Clinical Reportsclassification. In our approaches, we used topic vector representation as an alternative to BoW and not additional. This...

31Thematic Segmentation of Texts: Two Methods for Two Kind of Textsbecomes less efficient. In this case, we modify the vector representation by adding information coming from the lexical network...

32Dependency Tree Kernels for Relation Extraction2004  Aron Culotta,Jeffrey S. Sorensensimple kernel function takes the dot product of the vector representation of instances being compared. For example, in document...

33A Kernel PCA Method for Superior Word Sense Disambiguationoccurrences of “art” can be transformed to a binary vector representation containing one dimension for each feature, as shown...

34A Quantitative Analysis of Lexical Differences Between Genders in Telephone Conversationsweighting scheme that needs to be applied to the vector representation. In addition to classification, we have applied feature...

35Are These Documents Written from Different Perspectives? A Test of Different Perspectives Based on Statistical Distribution Divergence2006  WeiHao Lin,Alexander Hauptmannword in a document, i.e., term frequency. Although vector representation, commonly known as a bag of words, is oversimplified...

36Guiding Statistical Word Alignment Models With Prior Knowledge2007  Yonggang Deng,Yuqing GaoLSA, we use the centroid of all source words as its vector representation in the LSAspace. The semantic constraints between...

37Learning Expressive Models for Word Sense Disambiguationselectional preferences, is either preprocessed into a vector representation to accommodate machine learning algorithms, or used...

38Generating Complex Morphology for Machine Translationdimensions and possible values for each dimension in the vector representation space are defined by L. 4.2 The Task We assume that...

39Word Maturity: Computational Modeling of Word Knowledge2011  Kirill Kireyev,Thomas K Landauermeaning in a multidimensional vector space. The LSA vector representation is derived in an unsupervised manner, based on occurrence...

40Supervised Model Learning with Feature Grouping based on a Discrete Constraint2013  Jun Suzuki,Masaaki Nagatapairs, that is, (x,y) ∈ D. w is an N dimensional vector representation of a set of optimization variables, which are also...

41Identifying Opinion Subgroups in Arabic Online Discussionsapproach. This can be explained by the fact that the vector representation is a richer representation and encodes all the di...

42PartOfSpeech Induction From Scratch1993  Hinrich Schutzeand plural noun. Ambiguity is a problem for the vector representation scheme used here, because the two components of an...

43MemoryBased Learning: Using Similarity for Smoothing1997  Jakub Zavrel,Walter Daelemansvectors. Each word has a numeric 25 dimensional vector representation. Using these vectors, in combination with the IG weights...

44FLSA: Extending Latent Semantic Analysis with Features for Dialogue Act Classificationa document in the test set, we first compute its vector representation in the semantic space LSA computed, then we compare...

45Efficient Unsupervised Discovery of Word Categories Using Symmetric Patterns and High Frequency Words2006  Dmitry Davidov,Ari Rappoportuses conjunction and appositive annotations in the vector representation. 2We did not compare against methods that use richer...

46Automatically Extracting Nominal Mentions of Events with a Bootstrapped Probabilistic Classifier2006  Cassandre Creswell,Matthew J. Beal,John Chen,Thomas L. Cornell,Lars Nilsson,Rohini K. Sriharitriples (Lin, 1998; Gorman and Curran, 2005). Our vector representation of the behavior of a word type across all its instances...

47Using Bilingual Comparable Corpora and Semisupervised Clustering for Topic Tracking2006  Fumiyo Fukumoto,Yoshimi Suzukidistance (measured by cosine similarity) between a vector representation of the test story and each centroid g of the clusters...

48A Grammardriven Convolution Tree Kernel for Semantic Role Classificationdefine the new kernel by beginning with the feature vector representation of a parse tree T as follows: ( )Tφ =′ (# subtree1(T)...

49Learning to Extract Relations from the Web using Minimal Supervision2007  Razvan Bunescu,Raymond J. Mooneya bag X ∈ X , let φ(x) be the (implicit) feature vector representation of x. Then the corresponding SVM optimization problem...

50Distributional Identification of NonReferential Pronounswere no matches of the 〈UNK〉 type, #4). 3.3 Feature Vector Representation There are many possible ways to use the above counts...

51WeaklySupervised Acquisition of OpenDomain Classes and Class Attributes from Web Documents and Query Logs2008  Marius Paşca,Benjamin Van Durmeconstruction of a reference internal searchsignature vector representation for a small set of seed attributes provided as input...

52Grounded Language Modeling for Automatic Speech Recognition of Sports Video2008  Michael Fleischman,Deb Roystreams is treated as the value of an element in the vector representation for that video. Thus, a video is represented...

53ChineseEnglish Backward Transliteration Assisted with Mining Monolingual Web Pagesway, the word in list can also be transformed into vector representation. So the similarity can be calculated as the inner...

54Towards OpenDomain Semantic Role Labelingvectors −→ h are available for the semantic heads h, a vector representation −−→ FEk for the role FEk can be obtained from the...

55Learning 5000 Relational Extractorslists in our corpus don’t contain duplicates. This vector representation supports the simple cosine definition of list similarity...

56Efficient Staggered Decoding for Sequence Labelingw is the weight vector, and φ(x,y) is the feature vector representation of the pair (x,y). By making the firstorder Markov...

57BeamWidth Prediction for Efficient ContextFree Parsingtuples: Φ(S, i, j) = (x, y) (1) where x is a featurevector representation of the chart cell and y is the target class 1 if the...

58TemplateBased Information Extraction without the Templatesof these relation counts, calling this its coref vector representation. Selectional preferences (SPs) are also useful in...

59A TransitionBased Dependency Parser Using a Dynamic Parsing StrategyrectT , c) update c with bestCorrectT a feature vector representation for a transition t applying to a configuration c....

60Generating Synthetic Comparable Questions for News Articles2013  Oleg Rokhlenko,Idan Szpektorand the supervised models that given this feature vector representation assess the correctness of an instantiation. 4.2.1...

61Statistical Machine Translation Improves Question Retrieval in Community Question Answering via Matrix Factorizationwhere qi represents a queried question, and qi is a vector representation of qi. 5Statistical machine translation quality is...

62The Role of Syntax in Vector Space Models of Compositional Semantics2013  Karl Moritz Hermann,Phil BlunsomThe unsupervised method described so far learns a vector representation for each sentence. Such a representation can be useful...

63Question Answering Using Enhanced Lexical Semantic Models2011). Each row vector of this matrix is the dense vector representation of the corresponding word in the vocabulary. Perhaps...

64Dialogue Management in VectorBased Call Routinggiven by Bt,a = At,a x IDF(t)/(~~x
Vector Representation To reduce the dimensionality of our vector representations... 
65Discriminative Language Modeling with Conditional Random Fields and the Perceptron Algorithmof xi. All that remains is to define the featurevector representation, Φ(x, y). In the general case, each component Φi(x...

66Piggyback: Using Search Engines for Robust CrossDomain Named Entity Recognitionsearch term wi. We then compute features for the vector representation of wi based on the snippets. We again refer to the...