Báo cáo khoa học: "Kernel Based Discourse Relation Recognition with Temporal Ordering Information" pot

... 11-16 July 2010. c 2010 Association for Computational Linguistics Kernel Based Discourse Relation Recognition with Temporal Ordering Information WenTing Wang 1 Jian Su 1 Chew Lim Tan 2 1 Institute ... leve- rage on temporal ordering information to constrain the interpretation of discourse relation, which also demonstrate statistic- al significant improvements f...

Ngày tải lên: 30/03/2014, 21:20

... antecedent. The candidate with the highest confidence value will be selected as the antecedent of the pronominal anaphor. 3.1 Feature Space As with many other learning -based approaches, the knowledge ... POS-tagging, Text Chunking and Named-Entity Recognition. The texts were parsed using the maximum-entropy- based Charniak parser (Charniak, 2000), based on which the structured featu...

Ngày tải lên: 20/02/2014, 11:21

... receives a user utterance and outputs a speech recognition hypothesis. 2. The language understanding component re- ceives the speech recognition hypothesis. The syntactic and semantic analysis ... speech. This paper deals with the discourse understand- ing component. Since we are resolving the ambi- guity of speech understanding from the discourse point of view and not within the sp...

Ngày tải lên: 31/03/2014, 03:20

... Association -based Natural Language Processing with Neural Networks KIMURA Kazuhiro SUZUOKA Takashi AMANO Sin-ya Information ... Combining an associative net- work with a conventional system contributes to semantic disambiguation in the process of interpretation. The model is employed within a kana-kanji conversion system ... practical treatment of con- text dependency within the...

Ngày tải lên: 17/03/2014, 08:20

... by the first sentence, but this discourse sounds awkward and the continuation with a state in (4) is clearly preferred. 4 (4) Er war auf dem Weg nach Hause. Discourse (3) shows that for the ... Smith's formalisation within Discourse Represen- tation Theory (DRT) (Kamp & Reyle, 1993).6 4Note that the PP at this time is not required for the English discourse to be full...

Ngày tải lên: 17/03/2014, 09:20

... Rather, there is a continuum of potential mispronunciations ranging from slightly accented forms with only minor allophonic shifts up to heavily accented pronunciations with extreme de- viations from ... the Deutsche Forschungsgemein- schaft (DFG). Automatic Speech Recognition (ASR), this may cause a significant decline of the recognition per- formance. In recent years, a number of...

Ngày tải lên: 24/03/2014, 03:20

... one of C&S’s co-trained classifiers uses features based on capitalization, but Bengali is case-insensitive. Second, C&S identify potential NEs based on proper nouns, but unlike English, (1) ... has a category whose name starts with “Born on” or “Death on,” we label the corresponding ti- tle with PER. Similarly, if it has a category whose name starts with “Cities of” or “Count...

Ngày tải lên: 24/03/2014, 03:20

... supervision model with which to learn patterns for relation extraction with no manual intervention. Results are promising, we could obtain new relations that are not in Free- Base with a high precision ... have very different results for new relation acquisition vs. finding sentence support for new relations. The reason is that these relations are very correlated to other relations t...

Ngày tải lên: 30/03/2014, 17:20

... min )1 [41]. The difference is probably associated with the less pre- cise determination of enzyme active sites with the Bradford method than with cofactor release by alkali denaturation, a method ... specific activity measured with 20 mm KYN was 9 · 10 )6 lmolÆmin )1 Ælg )1 , which is four orders of magnitude lower than that measured with BCA. Reactivity of KATII with cysteine sul...

Ngày tải lên: 06/03/2014, 00:21

... contain words with similar syntactic/semantic properties. To arrive at WCs having both (method COMB), we determine TL WCs with the first method and afterwards we determine SL WCs with the sec- ... shows how the application of those rules works in principle. We arrive at a list of word hypotheses with probabilities for each po- sition. Neglecting the language model, the best dec...

Ngày tải lên: 08/03/2014, 05:21