... Zbinden, Alan McNaught,Rafael Alc´antara, Michael Darsow, Micka¨el Guedj,and Michael Ashburner. 2008. ChEBI: a databaseand ontology for chemical entities of biologicalinterest. Nucleic Acids ... systemfor the syntac-tic and semanticanalysis of such names.Our system aims at yielding both the de-noted chemical structure and a classifica-tion of a given name. We employ a novelapproach ... transformsyntactic as well as morphological variations ofnames into a normalized name form. Basic trans-formations can be achieved via pattern match-ing (regular expressions) while for more com-plex...
... Analysis of 2012 U.S. Presidential Election Cycle Hao Wang*, Dogan Can**, Abe Kazemzadeh**, François Bar* and Shrikanth Narayanan** Annenberg Innovation Laboratory (AIL)* Signal Analysis ... half a million relevant tweets in just a few hours. This kind of ‘big data’ vastly outpaces the capacity of traditional content analysis approaches, calling for novel computational approaches. ... sentiment annotation on in-domain political data. To create a baseline sentiment model, we used Amazon Mechanical Turk (AMT) to get as varied a population of annotators as possible. We designed an...
... SemanticAnalysis Rodney D. Nielsen1,2, Wayne Ward1,2, James H. Martin1, and Martha Palmer1 1 Center for Computational Language and Education Research, University of Colorado, Boulder ... fine-grained semantic rep-resentation of text and an approach to con-structing it. This representation is largely extractable by today’s technologies and facili-tates more detailed semantic analysis. ... stu-dent answers at this facet level (up to 26% over baseline), particularly given that, in addition to the manual reference answer facet representation, an automatically extracted approximation...
... 'on the table', 'on the floor', 'on the chair', and 'on the roof') and being at an artifact with a given purpose (e.g., 'at the door', 'at ... object; for example, a nail can be lo- cated in a board. The problem is that the located object is 'man', and a man cannot be embedded in a board under normal circum- stances. This ... conceptualized, given a particu- lar language, a particular situation, etc. Typ- ically, in our application, these conceptualiza- tions are geometrical objects, such as points, lines, surfaces, and...
... logical rules fora fragment of the semantic interpretation (and plan recognition) process. The four simple rules we gave already capture a wide variety of semantic and pragmatic phenomena. ... relative clauses. P~t~erences [1] F. Pereira & D. Warren, "Definite clause grammar for language analysis - a survey of the formalism and a comparison with augmented transition networks," ... This has the effect. of concentrating all knowledge about all of an object's names as facts about the best name. Frail will take as input a simple frame representation and translate it...
... wecall View Neutral Mapping Adjuncts(VNMAs). We give a list of the mainVNMAs that appear to be required, andshow how they can be incorporated into a pre-existing system (ATT-Meta) for metaphorical ... idea that Kyle was having an affair wassomething of which Anne had only a very lowdegree of conscious awareness (i. e. on whichAnne had only a very low ability to mentally op-erate in a conscious ... 'type' refers to the classification of anevent, as, for example eat (mary, bread) ,and event rate is relative to event type as well asthe specific event. Logical forms for otherVNMAs have...
... this publicly available2database. The database contains all recorded signal data,frontal face video fora subset of the participants andsubjective ratings from the participants. Also includedis ... found in Table 4. For arousal we found negative correlations in thetheta, alpha, and gamma band. The central alpha powerdecrease for higher arousal matches the findings fromIEEE TRANS. AFFECTIVE ... Results and DiscussionTable 7 shows the average accurac ie s a nd F1-scores(average F1-score for b oth classes) over par ticipants for TABLE 7Average accuracies (ACC) and F1-scores (F1, averageof...
... machine translationevaluation. Machine Translation, 17(1):43–75.Masaki Murata, Kiyotaka Uchimoto, Qing Ma, ToshiyukiKanamaru, and Hitoshi Isahara. 2005. Analysis ofmachine translation systems’ ... graphical tool for performing human error analysis, from any MT system and for any language pair. BLAST has a graphical user interface, and is designed to be easy1The BiLingual Annotation/Annotator /Analysis ... existing annota-tions, and for searching among annotations.BLAST can handle two types of annotations: er-ror annotations and support annotations. Error an-notations are based on a hierarchical...
... the ACL 2010 Con-ference Short Papers, pages 263–268, Uppsala, Swe-den, July. Association for Computational Linguistics.Aditya Joshi, Balamurali AR, Pushpak Bhattacharyya,and Rajat Mohanty. ... entropy,f-measure, Jaccard, and RandIndex. The system alsohas a Java API that can be used by researchers to de-velop other systems using our code.The system can process any discussion thread thatis ... 48th Annual Meeting of the Asso-ciation for Computational Linguistics, pages 138–147,Uppsala, Sweden, July.Andrea Esuli and Fabrizio Sebastiani. 2006. Sentiword-net: A publicly available...
... Kingdom{m.dzikovska,j.moore}@ed.ac.ukNatalie Steinhauser and Gwendolyn CampbellNaval Air Warfare Center Training Systems Division, Orlando, FL, USA{gwendolyn.campbell,natalie.steihauser}@navy.milElaine FarrowHeriot-Watt ... paraphrases of correct answers. The an-notated data will be used to evaluate the accuracyof existing paraphrasing and textual entailment ap-proaches and to investigate how to combine suchalgorithms ... uses a deep parser and generator, to-gether with a domain reasoner and a diagnoser,to produce detailed analyses of student utterancesand generate feedback automatically. This allowsthe system...
... and usage infor-mation tuned to genres and sublanguages. Suchresources are critical for natural language process-ing (NLP), both for enhancing the performance ofstate-of-art statistical systems ... Computational Linguistics A Systemfor Large-Scale Acquisition of Verbal, Nominal and AdjectivalSubcategorization Frames from CorporaJudita Preiss, Ted Briscoe, and Anna KorhonenComputer LaboratoryUniversity ... constraints on partof speech (pos) and word value (val), or an alreadyinstantiated variable. Unlike in Yallop’s work (Yal-lop et al., 2005), our rules are declarative rather thanprocedural and...
... Alonge, Francesca Bertagna, Nicoletta Calzolari, Christian Girardi, Bernardo Magnini, Rita Marinelli, and Antonio Zampolli. 2003. ItalWordNet: Building a Large Semantic Database for the Automatic ... CNR-IIT Via Moruzzi 1, 56024 Pisa, Italy {maurizio.tesconi,andrea.marchetti}@iit.cnr.it Francesca Bertagna and Monica Monachini and Claudia Soria and Nicoletta Calzolari CNR-ILC Via Moruzzi ... Pisa, Italy {francesca.bertagna,monica.monachini, claudia.soria,nicoletta.calzolari}@ilc.cnr.it Abstract This demo presents LeXFlow, a work-flow management systemfor cross-fertilization...
... transformational g~ammar s. based on message passing, with the goal of running syntax and semantics in parallel and providing seman- tic feedback to the parser. A ~moderator" trans- lates ... then throw away any that don't make sense to the database. If'Our choice of Paragram was largely pragmatic~it w&s avL/l- • ble and does not represent &ny particular commitment ... prepositional phrase in the mall can be attached to a store (since a noun phrase, being a frame, can have a slot-filler pair added to it), and the prepositional phrase from a store in the marl is formed....
... is actually a consequence of basic semantic properties that hold in a seman- tic domain allowing functional application and ab- straction, and are thus independent of a particular 10gical-form ... Interpretation and Information, pages 99-130. Forts, Dor- drecht, Holland. Martha E. Pollack and Fernando C.N. Pereira. 1988. An integrated framework forsemantic and pragmatic interpretation. ... simple and fundamental facts about functional application and abstraction, and can be expressed as constraints on the derivation of possi- ble meanings for sentences rather than constraints...