Báo cáo khoa học: "Toward Automatically Assembling Hittite-Language Cuneiform Tablet Fragments into Larger Texts" pdf

Báo cáo khoa học: "Toward Automatically Assembling Hittite-Language Cuneiform Tablet Fragments into Larger Texts" pdf

Báo cáo khoa học: "Toward Automatically Assembling Hittite-Language Cuneiform Tablet Fragments into Larger Texts" pdf

... 2012. c 2012 Association for Computational Linguistics Toward Automatically Assembling Hittite-Language Cuneiform Tablet Fragments into Larger Texts Stephen Tyndall University of Michigan styndall@umich.edu Abstract This ... connect unknown fragments of Hittite cuneiform tablets with larger texts. I’m viewing this as a text classification task, where larger, CTH-numbere...

Ngày tải lên: 16/03/2014, 20:20

5 110 0
Tài liệu Báo cáo khoa học: "Using Automatically Transcribed Dialogs to Learn User Models in a Spoken Dialog System" doc

Tài liệu Báo cáo khoa học: "Using Automatically Transcribed Dialogs to Learn User Models in a Spoken Dialog System" doc

... 121–124, Columbus, Ohio, USA, June 2008. c 2008 Association for Computational Linguistics Using Automatically Transcribed Dialogs to Learn User Models in a Spoken Dialog System Umar Syed Department ... USA jdw@research.att.com Abstract We use an EM algorithm to learn user mod- els in a spoken dialog system. Our method requires automatically transcribed (with ASR) dialog corpora, plus a m...

Ngày tải lên: 20/02/2014, 09:20

4 471 0
Tài liệu Báo cáo khoa học: "Toward finer-grained sentiment identification in product reviews through linguistic and ontological analyses" ppt

Tài liệu Báo cáo khoa học: "Toward finer-grained sentiment identification in product reviews through linguistic and ontological analyses" ppt

... verbs. In the case of subject omission, we converted adjectives or verbs into their corresponding nouns, such as ‘thin’ into ‘thickness’. Hu and Liu (2004) identi- fied attributes of IT products ... the informa- tion about their relation may not be shown in the summary if they are classified into different up- per-level attributes. Consider (1). (1) a. 옷은 맞지만/맞긴 한데, 색상...

Ngày tải lên: 20/02/2014, 09:20

4 337 0
Báo cáo khoa học: "Toward General-Purpose Learning for Information Extraction" ppt

Báo cáo khoa học: "Toward General-Purpose Learning for Information Extraction" ppt

... from text doc- uments automatically. While the problems of retrieval, routing, and filtering have received considerable attention through the years, IE is only now coming into its own as an information ... are derived from parser output. Figure 1 shows part of a link grammar parse and its translation into features. Our object in using Wordnet (Miller, 1995) is to enable 5RV to re...

Ngày tải lên: 08/03/2014, 05:21

5 292 0
Báo cáo khoa học: "Toward Smaller, Faster, and Better Hierarchical Phrase-based SMT" ppt

Báo cáo khoa học: "Toward Smaller, Faster, and Better Hierarchical Phrase-based SMT" ppt

... compositional property of a phrase pair as the capability of decomposing into subphrase pairs. If a phrase pair (˜s, ˜ t) can be de- composed into K subphrase pairs (˜s k , ˜ t k ) already in the phrase ... this paper, the negative logarithm p-value is referred to as the significance value. Therefore, the larger the value, the greater the significance. 2.2 Table pruning with significance v...

Ngày tải lên: 17/03/2014, 02:20

4 113 0
Báo cáo khoa học: "Toward a Redefinition of Yea/No Questions" pot

Báo cáo khoa học: "Toward a Redefinition of Yea/No Questions" pot

... interpretations into question by showing that YNQs may have very different meanings from their alternatlve-questioa counterparts; they also have more restricted paraphrase and intonation patterns. ... under which a response eonnts as an answer to a natural-language query, Hintikka divides qneriq~s into two parts: an imperative or optaGve operator {[). roughly expressing 'bri,g...

Ngày tải lên: 17/03/2014, 19:21

4 331 0
Báo cáo khoa học: "TOWARD TREATING ENGLISH NOMINALS CORRECTLY" doc

Báo cáo khoa học: "TOWARD TREATING ENGLISH NOMINALS CORRECTLY" doc

... nominals in contexts where the default stress pattern is not shifted by phenomena such as as intonational focus or contrastive stress, exemplified below: (1) a. We're only interested ... level of constituent structure recursively, with relative stress values normally preserved as larger pieces of structure are considered. A convenient representation for tallying stress is ......

Ngày tải lên: 17/03/2014, 20:20

7 114 0
Báo cáo khoa học: "Toward a Plan-Based Understanding Model for Mixed-Initiative Dialogues" pptx

Báo cáo khoa học: "Toward a Plan-Based Understanding Model for Mixed-Initiative Dialogues" pptx

... is organized in our model. The domain plan, previously considered a joint plan, is separated into two domain plans, each representing a domain plan of a specific speaker. Each speaker can ... example, if a domain plan is marked [Next] (currently active), the system de- composes the plan into its component plan sequence. Then the first element in the component plan sequence (which...

Ngày tải lên: 23/03/2014, 20:20

8 253 0
Báo cáo khoa học: "Toward Evaluation of Writing Style: Finding Overly Repetitive Word Use in Student Essays" potx

Báo cáo khoa học: "Toward Evaluation of Writing Style: Finding Overly Repetitive Word Use in Student Essays" potx

... particular kind of essay characteristic. For example, to build a capability to identify sentence fragments, a corpus of essay data needs to be annotated for this kind of ungrammatical sentence. ... analysis system. Annotation protocols are required for each task. For identification of sentence fragments, this is reasonably straightforward. In terms of essay-based discourse analysis, it ....

Ngày tải lên: 24/03/2014, 03:20

8 505 0
Báo cáo khoa học: "Toward Statistical Machine Translation without Parallel Corpora" ppt

Báo cáo khoa học: "Toward Statistical Machine Translation without Parallel Corpora" ppt

... Proceedings of EMNLP. Dragos Stefan Munteanu and Daniel Marcu. 2006. Extracting parallel sub-sentential fragments from non-parallel corpora. In Proceedings of the ACL/Coling. Franz Josef Och and Hermann ... S ´ anchez- Martnez, and Juan Antonio P ´ erez-Ortiz. 2011. Integrating shallow-transfer rules into phrase-based statistical machine translation. In Proceedings of the XIII Machine Tra...

Ngày tải lên: 24/03/2014, 03:20

11 255 0
Từ khóa:
w