抄録
This contribution of this paper is to investigate the utility of exploiting words and predicted detailed semantic tags in the long history to enhance a standard trigram language model. The paper builds on earlier work in the field that also used words and tags in the long history, but offers a cleaner, and ultimately much more accurate system by integrating the application of these new features directly into the decoding algorithm. The features used in our models are derived using a set of complex questions about the tags and words in the history, written by a linguist. Maximum entropy modelling techniques are then used to combine these features with a standard trigram language model. We evaluate the technique in terms of word error rate, on Wall Street Journal test data.
| 元の言語 | English |
|---|---|
| ホスト出版物のタイトル | 6th International Conference on Spoken Language Processing, ICSLP 2000 |
| 出版者 | International Speech Communication Association |
| ISBN（電子版） | 7801501144, 9787801501141 |
| 出版物ステータス | Published - 2000 |
| 外部発表 | Yes |
| イベント | 6th International Conference on Spoken Language Processing, ICSLP 2000 - Beijing, China 継続期間: 2000 10 16 → 2000 10 20 |
Other
| Other | 6th International Conference on Spoken Language Processing, ICSLP 2000 |
|---|---|
| 国 | China |
| 市 | Beijing |
| 期間 | 00/10/16 → 00/10/20 |
Fingerprint
ASJC Scopus subject areas
- Linguistics and Language
- Language and Linguistics
これを引用
A tagger-aided language model with a stack decoder. / Zhang, Ruiqiang; Black, Ezra; Finch, Andrew; Sagisaka, Yoshinori.
6th International Conference on Spoken Language Processing, ICSLP 2000. International Speech Communication Association, 2000.研究成果: Conference contribution
}
TY - GEN
T1 - A tagger-aided language model with a stack decoder
AU - Zhang, Ruiqiang
AU - Black, Ezra
AU - Finch, Andrew
AU - Sagisaka, Yoshinori
PY - 2000
Y1 - 2000
N2 - This contribution of this paper is to investigate the utility of exploiting words and predicted detailed semantic tags in the long history to enhance a standard trigram language model. The paper builds on earlier work in the field that also used words and tags in the long history, but offers a cleaner, and ultimately much more accurate system by integrating the application of these new features directly into the decoding algorithm. The features used in our models are derived using a set of complex questions about the tags and words in the history, written by a linguist. Maximum entropy modelling techniques are then used to combine these features with a standard trigram language model. We evaluate the technique in terms of word error rate, on Wall Street Journal test data.
AB - This contribution of this paper is to investigate the utility of exploiting words and predicted detailed semantic tags in the long history to enhance a standard trigram language model. The paper builds on earlier work in the field that also used words and tags in the long history, but offers a cleaner, and ultimately much more accurate system by integrating the application of these new features directly into the decoding algorithm. The features used in our models are derived using a set of complex questions about the tags and words in the history, written by a linguist. Maximum entropy modelling techniques are then used to combine these features with a standard trigram language model. We evaluate the technique in terms of word error rate, on Wall Street Journal test data.
UR - http://www.scopus.com/inward/record.url?scp=85009070549&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85009070549&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85009070549
BT - 6th International Conference on Spoken Language Processing, ICSLP 2000
PB - International Speech Communication Association
ER -