Tài liệu Báo cáo khoa học: "Automatic Satire Detection: Are You Having a Laugh?" ppt

... research are as follows: (1) we introduce a novel task to the arena of computational linguistics and machine learning, and make available a standardised dataset for re- search on satire detection; and ... validity Lexical approaches are clearly inadequate if we assume that good satirical news articles tend to emulate real news in tone, style, and content. What is needed is an approa...

Ngày tải lên: 20/02/2014, 09:20

... col- lect technical terms that are related to natural lan- guage processing, such as morphological analysis, parsing, information retrieval, and machine transla- tion. The target application of the ... System configuration Automatic acquisition of technical terms in a cer- tain domain has been studied as automatic term recognition (Kageura and Umino, 1996; Kageura and Koyama, 2000), and th...

Ngày tải lên: 20/02/2014, 16:20

... ,, ∑ ∑ ∑ ∈∈ ∈∈∈∈ −= ≤≤∀ = BbAa j BbAaBbAa jj bapbappH kjffor bagbapbagbap We assumed that the constraint of feature sets f i (i ≦ j ≦ k) was defined by Eq. 1. This is where A is a set of categories and B is a set ... thepchai@nectec.or.th Hitoshi ISAHARA †‡ isahara@crl.go.jp Abstract This paper describes a method of detecting grammatical and lexical errors made by Japanese...

Ngày tải lên: 20/02/2014, 16:20

... machine learning systems. Additionally, the intuitive and linguistically motivated rules will allow for manual adaptation of the rule set to new domains and corpora. 1 Motivation Information Extraction ... necessarily accurate) parse tree representations. We first parsed each sentence in the training dataset which contained a negation or speculation cue using the Stanford parser (Klein and M...

Ngày tải lên: 20/02/2014, 04:20

... Abstract Arabic language is a morphologically com- plex language. Affixes and clitics are regu- larly attached to stems which make direct comparison between words not practical. In this paper ... generated headlines are preferred against human evaluations because they are faster, cost effective and can be performed repeatedly. However, they are not trivial because of various...

Ngày tải lên: 20/02/2014, 05:20

... Recognizing Textual En- tailment (RTE) challenges (Dagan et al., 2005; Bar Haim et al., 2006). The comparative results show that (a) we have designed an effective way to automatically learn entailment ... but also on a cross-pair similarity between two pairs (T  , H  ) and (T  , H  ). The latter similarity measure along with aset of annotated examples al- lows a learning algorithm t...

Ngày tải lên: 20/02/2014, 12:20

... a part of our corpus that was actually constructed in the experiment. Note that this paper treats Japanese. The sentences in the Table are translations, and the original sentences are in Japanese. The ... classifica- tion task. Naive Bayes classifier was trained on our corpus and tested on three data sets. The re- sult demonstrated that the classifier achieved more than 80% accuracy in eac...

Ngày tải lên: 20/02/2014, 12:20

... separately as a gold standard. In Table 7, accuracies indicate the agreement between the system and human annotators. The average accuracy 68.0% is comparable with the pair-wise human agreement ... features as reasons. For example, reasons such as You feel like you are in a train station or a busy amusement park that is ill-staffed to meet de- mand!”, “preferential treat...

Ngày tải lên: 20/02/2014, 12:20

... 2109 Australia madras@ics.mq.edu.au Abstract In evaluating the output of language tech- nology applications—MT, natural language generation, summarisation—automatic eval- uation techniques generally ... in applying SVMs here are, first, noting that human translations are generally good and machine translations poor, that binary training data can be created by taking the human translations a...

Ngày tải lên: 20/02/2014, 12:20

... large-scale machine translation evalua- tions. Recently, Turian et al. (2003) indicated that standard accuracy measures such as recall, preci- sion, and the F-measure can also be used in evalua- tion ... factors are LCS-based recall and precision in this case. Melamed et al. (2003) used unigram F-measure to estimate ma- chine translation quality and showed that unigram F-measure was as...

Ngày tải lên: 20/02/2014, 16:20