Diane Litman. Classifying cue phrases in text and speech using machine learning. In Proceedings, Twelfth National Conference on Artificial Intelligence, pages 215--223, 1994.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....29b and then go on his way. 7 30 um but the little boy comes, CONTINUE) 31 and uh he doesn t want just a pear, 32 he wants a whole basket. 8 33 So he puts the bicycle down, CONTINUE) 34 and he . you wonder how he s going to take it with this. Figure 11: Excerpt from (Passonneau and Litman, 1994) illustrating Type 1 and Type 2. Each line indicates an empirically verified discourse segment. A sister intention discourse configuration is shown in Figure 9 for segments D and E; E is a sister to D. The Pear Stories narrative in Figure 11 from [Passonneau and Litman, 1996] illustrates two ....

....stuff, 8 but there. the humans beings in it don t say anything. 16 9 He falls over, 10 and then these three other little kids about his same age come walking by. Figure 14: An excerpt from the Pear Corpus illustrating Type 5. Segment boundaries from human judgements taken from Passonneau and Litman, 1994 which re realizes the content of utterance 3, and reintroduces its content in the current context [Walker, 1993a; Walker, 1996] Thus, using hierarchical recency to determine U 1 for the purposes of centering, U is utterance 9 at the beginning of segment 16 and U 1 is utterance 3 at the ....

Diane Litman. Classifying cue phrases in text and speech using machine learning. In Proceedings, Twelfth National Conference on Artificial Intelligence, pages 215--223, 1994.

.... learning techniques have been succes, sfully applied to a number of tasks in natural language processing (NLP) Examples include the use of decision trees for syntactic analysis (Materman, 1995) coreference (Aone and Bennett, 1995; McCarthy and Lehnert, 1995) and cue phrase identification (Litman, 1994); the use of inductive logic programming for learning semantic grammars and building prolog parsers 113 (Zelle and Mooney, 1994; Zelle and Mooney, 1993) the use of conceptual clustering algorithms for rel ative pronoun resolution (Cardie, 1992a; Cardie 1992b) and the use of case based learning ....

Diane J. Litman. 1994. Classify- ing Cue Phrases in Text and Speech Using Machine Learning. In Proceedings of the Twelfth National Conference on Artificial Intelligence, pages 806-813. AAAI Press / MIT Press.

....this one type of contextual feature. The most formal approach to developing models that has been applied to discourse problems makes use of decision trees to define the relationships among various contextual features and discourse ambiguities (Siegel McKeown 1994, Soderland Lehnert 1994, Litman 1994). The tree construction process partitions the data according to the values of one contextual feature before considering the values of the next, thereby treating all features in each branch of the tree as interdependent. In addition, the tree construction process requires a large amount of tagged ....

Litman, D. 1994. Classifying Cue Phrases in Text and Speech Using Machine Learning. In Procs. 12th National Conference on Artificial Intelligence (AAAI94) .

.... levels: Speech recognition [8, 9] PoS tagging [200, 132, 140, 141, 164, 136, 138, 137] word sense disambiguation [26] parsing [132, 92] text categorization [117, 69, 230] text summarization [134] dialogue act tagging [192] co reference resolution [5, 143] cue phrase identification [122], and machine translation (verb classification) 221, 209] In Magerman s approach [132] decision trees are used for a number of simultaneous different decision making problems, such as: Assigning part of speech tags to words, assigning 3 This classification is extracted from [154] 7 ....

.... NLP problems DLs DTs NB TBL EM WSD [240, 150] 26, 150] 86, 150, 112] 67] 203, 166] Text categorization and filtering [117, 69, 230] 117, 190, 119, 142, 196] 162, 163] Dialogue act tagging [192] 193, 192] Co reference and anaphora resolution [5, 143] Cue phrase identification [122] IBL NNs EC SVM Clust WSD [159, 157, 84, 73] 150, 224] 182, 72, 74, 165] 202] Text categorization and filtering [183, 238, 237, 239] 233] 198, 196, 13] 98, 69, 99] Co reference and anaphora resol. 39] 148, 147] 35, 34] Rocchio RI ILP LSM GAs ME WSD [74] Text categorization ....

D. J. Litman. Classifying Cue Phrases in Text and Speech Using Machine Learning. In Proceedings of the 12th National Conference on Artificial Intelligence, AAAI, pages 806--813, 1994. AAAI Press / MIT Press.

....are useful for many tasks, for example plan recognition, anaphora resolution, and providing coherence in generated text. Some examples are cited in [Moser and Moore 1995] Di Eugenio et al. 1997] cite evidence that proper selection and placement of discourse markers improves reading and recall. Litman [1994] devised a computational approach to distinguish between structural and sentential uses of cue words in text. The word incidentally, for example, can have a structural use as a discourse marker indicating that a diversion follows. It can also occur as an ordinary adverb with no special discourse ....

Litman, Diane J. 1994. "Classifying Cue Phrases in Text and Speech Using Machine Learning," Proceedings of the Twelfth National Conference on Artificial Intelligence (AAAI-94) Seattle, WA, AAAI Press, pp. 806--813.

....to the discourse level semantics, but rather to the semantic meaning of the sentences. Several methods of disambiguating cue phrases have been recently devised, most of them machine learning techniques for the induction of cue phrase disambiguation rules, e.g. some were reported in [Hirshberg and Litman 1993] and [Siegel and McKeown 1994]. Recently, a novel disambiguation approach, presented in [Marcu 1997] extends the problem of cue phrase disambiguation by distinguishing the discourse sense of a cue phrase into finer meanings, corresponding to the rhetorical relations it indicates. This can be further extended, by bringing into ....

D.J. Litman. Classifying cue phrases in text and speech using machine learning. In Proceedings of the 12th National Conference on Artificial Intelligence (AAAI-94), pages 806--813, Seattle, WA, 1994.

....or phrases in the example sentence. Although the technique has only been used with case role type representations, variations might also be useful for the type of lexicon required by the database query task. ILP techniques might also be usefully applied in learning larger discourse structures (Litman, 1994) and in information extraction tasks (Soderland Lehnert, 1994) Larger discourse units might be described in terms of scripts in a suitable logic oriented MRL. ILP could then be used to learn rules for script selection and role binding using techniques similar to those used in the database query ....

Litman, D. J. (1994). Classifying cue phrases in text and speech using machine learning. In Proceedings of the Twelfth National Conference on Artificial Intelligence Seattle, WA.

....here, uses frequency of lexical terms as the criterion by which segmentation is performed. Her method is specific to using this one type of contextual feature. The most formal approach to developing models that has been applied to discourse problems makes use of decision trees [58] 60] and [48]. Above, we cited the advantages of our proposed method over this approach. ....

Litman, D. (1994). Classifying Cue Phrases in Text and Speech Using Machine Learning. Procs. 12th National Conference on Artificial Intelligence (AAAI-94).

....Therefore, dialogue modelling tools like CSLUrp [1] neglect the variety of phenomena in spoken language and build up dialogue from a set of restricted slot filling dialogues. Others apply a supervised learning algorithm using some dialogue structuring theory with a given set of dialogue acts [2 6]. In contrast to other learning approaches to dialog modelling DIA MOLE does not employ theory based dialogue units because they are subject to human interpretation and often cannot be recognized from data available in a spoken language system. A similar approach adopting unsupervised learning for ....

D. J. Litman, "Classifying Cue Phrases in Text and Speech Using Machine Learning", Proc. Annual Meeting of the American Association for Artificial Intelligence, Seattle 1994, pp. 806-813.

....and then go on his i way. 7 30 um but the little boy i comes, CONTINUE) 31 and uh he i doesn t want just a pear, 32 he i wants a whole basket. 8 33 So he i puts the bicycle down, CONTINUE) 34 and he i . you wonder how he i s going to take it with this. Figure 11: Excerpt from (Passonneau and Litman, 1994) illustrating Type 1 and Type 2. Each line indicates an empirically verified discourse segment. A sister intention discourse configuration is shown in Figure 9 for segments D and E; E is a sister to D. The Pear Stories narrative in Figure 11 from [Passonneau and Litman, 1996] illustrates two ....

....stuff, 8 but there. the humans beings in it don t say anything. 16 9 He i falls over, 10 and then these three other little kids about his same age come walking by. Figure 14: An excerpt from the Pear Corpus illustrating Type 5. Segment boundaries from human judgements taken from Passonneau and Litman, 1994 which re realizes the content of utterance 3, and reintroduces its content in the current context [Walker, 1993a; Walker, 1996] Thus, using hierarchical recency to determine U n Gamma1 for the purposes of centering, U n is utterance 9 at the beginning of segment 16 and U n Gamma1 is utterance 3 ....

Diane Litman. Classifying cue phrases in text and speech using machine learning. In Proceedings, Twelfth National Conference on Artificial Intelligence, pages 215--223, 1994.

....was studied by Moser and Moore [1997] and Di Eugenio, Moore, and Paolucci [1997] reflected approximately the same distribution of cue phrases: 181 of the 406 discourse relations that they analyzed were cued relations. that these results can be improved if one uses machine learning techniques [ Litman, 1994, Litman, 1996 ] or genetic algorithms [ Siegel and McKeown, 1994 ] I have taken Hirschberg and Litman s research one step further and designed a comprehensive corpus analysis of cue phrases that enabled me to design algorithms that improved their results and coverage. The method, procedure, and ....

....algorithm on the same texts. The algorithm found 80.8 of the discourse markers with a precision of 89:5 (see table 5. 4) a result that outperforms Hirschberg and Litman s [ 1993 ] In fact, Hirschberg and Litman s algorithm and all its extensions that use machine learning techniques [ Litman, 1994, Litman, 1996 ] or genetic algorithms [ Siegel and McKeown, 1994 ] rely on manually encoded features. In contrast, the algorithm described here is fully automated: it takes as input unrestricted text, it uses the regular expressions described in section 5.2 in order to Text No. of No. of No. of ....

[Article contains additional citation context not shown here]

Diane J. Litman. Classifying cue phrases in text and speech using machine learning. In Proceedings of the Twelfth National Conference on Artificial Intelligence (AAAI--94), volume 1, pages 806--813, Seattle, July 31 -- August 4 1994.

.... machine learning techniques have been successfully applied to a number of tasks in natural language processing (NLP) Examples include the use of decision trees for syntactic analysis (Magerman, 1995) coreference (Aone and Bennett, 1995; McCarthy and Lehnert, 1995) and cue phrase identification (Litman, 1994); the use of inductive logic programming for learning semantic grammars and building prolog parsers (Zelle and Mooney, 1994; Zelle and Mooney, 1993) the use of conceptual clustering algorithms for relative pronoun resolution (Cardie, 1992a; Cardie 1992b) and the use of case based learning ....

Diane J. Litman. 1994. Classifying Cue Phrases in Text and Speech Using Machine Learning. In Proceedings of the Twelfth National Conference on Artificial Intelligence, pages 806--813. AAAI Press / MIT Press.

.... Multiple Knowledge Sources for Discourse Segmentation Diane J. Litman AT T Bell Laboratories 600 Mountain Avenue Murray Hill, NJ 07974 diane research.att.com Rebecca J. Passonneau Bellcore 445 South Street Morristown, NJ 07960 beck bellcore.com Abstract We predict discourse segment boundaries from linguistic features of utterances, using a corpus of spoken ....

Diane J. Litman. 1994. Classifying cue phrases in text and speech using machine learning. In Proc.

No context found.

Lit94. Litman, D.J. Classifying Cue Phrases in Text and Speech Using Machine Learning. In Proc. Annual Meeting of the American Association for Artificial Intelligence, Seattle, 1994, pp. 806-813.

No context found.

Lit94. Litman, D.J. Classifying Cue Phrases in Text and Speech Using Machine Learning. In Proc. Annual Meeting of the American Association for Artificial Intelligence, Seattle, 1994, pp. 806-813.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC