Discriminative Reranking for Spoken Language Understanding

Dinarelli, Marco; Moschitti, Alessandro; Riccardi, Giuseppe

doi:10.1109/tasl.2011.2162322

Cited by 23 publications

(19 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conditional Random Fields (Lafferty et al, 2001) have been applied (e.g. Wang and Acero (2006a;Dinarelli et al (2012)); He and Young (2005) present an approach based on Hidden Markos Models. However, evaluations have shown that even in case of applying machine learning techniques or probabilistic models, semantic parsing of ASR transcriptions is affected by much more errors compared to parsing of correct transcriptions (De Mori, 2011).…”

Section: Background and Related Workmentioning

confidence: 99%

Semantic parsing of speech using grammars learned with weak supervision

Gaspers

Cimiano

Wrede

2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Semantic grammars can be applied both as a language model for a speech recognizer and for semantic parsing, e.g. in order to map the output of a speech recognizer into formal meaning representations. Semantic speech recognition grammars are, however, typically created manually or learned in a supervised fashion, requiring extensive manual effort in both cases. Aiming to reduce this effort, in this paper we investigate the induction of semantic speech recognition grammars under weak supervision. We present empirical results, indicating that the induced grammars support semantic parsing of speech with a rather low loss in performance when compared to parsing of input without recognition errors. Further, we show improved parsing performance compared to applying n-gram models as language models and demonstrate how our semantic speech recognition grammars can be enhanced by weights based on occurrence frequencies, yielding an improvement in parsing performance over applying unweighted grammars.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Semantic parsing of speech using grammars learned with weak supervision

Gaspers

Cimiano

Wrede

2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…However, such classification is not completely aligned to our purpose, since our goal is to select the best (i.e., the most correct) DT from k candidate DTs; i.e., a ranking task. We adopt a preference reranking technique as described in Dinarelli et al, 2011).…”

Section: Kernels For Reranking Discourse Treesmentioning

confidence: 99%

“…However, their model does not con- sider long range dependencies between DT constituents, which are encoded by our kernels. Regarding the latter, our work is surely inspired by (Collins and Duffy, 2002), which uses TK for syntactic parsing reranking or in general discriminative reranking, e.g., (Collins and Koo, 2005;Charniak and Johnson, 2005;Dinarelli et al, 2011). However, such excellent studies do not regard discourse parsing, and in absolute they achieved lower improvements than our methods.…”

Section: Related Workmentioning

confidence: 99%

Discriminative Reranking of Discourse Parses Using Tree Kernels

Joty¹,

Moschitti²

2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

View full text Add to dashboard Cite

In this paper, we present a discriminative approach for reranking discourse trees generated by an existing probabilistic discourse parser. The reranker relies on tree kernels (TKs) to capture the global dependencies between discourse units in a tree. In particular, we design new computational structures of discourse trees, which combined with standard TKs, originate novel discourse TKs. The empirical evaluation shows that our reranker can improve the state-of-the-art sentence-level parsing accuracy from 79.77% to 82.15%, a relative error reduction of 11.8%, which in turn pushes the state-of-the-art documentlevel accuracy from 55.8% to 57.3%.

show abstract

“…Discriminative re-ranking in other domains. Discriminative re-ranking of multiple solutions is a dominant paradigm in domains like speech [9,10] and natural language processing [8,25]. In fact, the title of this paper is a reference to such speech & NLP papers.…”

Section: Related Workmentioning

confidence: 99%

Discriminative Re-ranking of Diverse Segmentations

Yadollahpour

Batra

Shakhnarovich

2013

2013 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

This paper introduces a two-stage approach to semantic image segmentation. In the first stage a probabilistic model generates a set of diverse plausible segmentations. In the second stage, a discriminatively trained re-ranking model selects the best segmentation from this set. The re-ranking stage can use much more complex features than what could be tractably used in the probabilistic model, allowing a better exploration of the solution space than possible by simply producing the most probable solution from the probabilistic model. While our proposed approach already achieves state-of-the-art results (48.1%) on the challenging VOC 2012 dataset, our machine and human analyses suggest that even larger gains are possible with such an approach.

show abstract

Discriminative Reranking for Spoken Language Understanding

Cited by 23 publications

References 47 publications

Semantic parsing of speech using grammars learned with weak supervision

Semantic parsing of speech using grammars learned with weak supervision

Discriminative Reranking of Discourse Parses Using Tree Kernels

Discriminative Re-ranking of Diverse Segmentations

Contact Info

Product

Resources

About