Hidden understanding models of natural language

Miller, S.L.; Bobrow, Robert; Ingria, Robert; Schwartz, Richard

doi:10.3115/981732.981736

Cited by 59 publications

(34 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Google Now 1 and Apple's Siri 2 ) and academia (e.g. [1,2,3,4,5,6,7,8,9,10,11,12]) have focused on developing semantic understanding techniques for building better spoken dialogue systems (SDS). The role of spoken language understanding (SLU) is of great significance to SDS: in order to capture the variation in language use from dialogue participants, the SLU component must create a mapping between the natural language inputs and a semantic representation that captures users' intentions.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsing

Chen

Wang

Rudnicky

2013

2013 IEEE Workshop on Automatic Speech Recognition and Understanding

View full text Add to dashboard Cite

Spoken dialogue systems typically use predefined semantic slots to parse users' natural language inputs into unified semantic representations. To define the slots, domain experts and professional annotators are often involved, and the cost can be expensive. In this paper, we ask the following question: given a collection of unlabeled raw audios, can we use the frame semantics theory to automatically induce and fill the semantic slots in an unsupervised fashion? To do this, we propose the use of a state-of-the-art frame-semantic parser, and a spectral clustering based slot ranking model that adapts the generic output of the parser to the target semantic space. Empirical experiments on a real-world spoken dialogue dataset show that the automatically induced semantic slots are in line with the reference slots created by domain experts: we observe a mean averaged precision of 69.36% using ASR-transcribed data. Our slot filling evaluations also indicate the promising future of this proposed approach.

show abstract

Section: Introductionmentioning

confidence: 99%

Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsing

Chen

Wang

Rudnicky

2013

2013 IEEE Workshop on Automatic Speech Recognition and Understanding

View full text Add to dashboard Cite

show abstract

“…AT&T's CHRONUS [5]; model based on Probabilistic Context-Free Grammar (PCFG), i.e. BBN's hidden understanding model (HUM) [6]; model proposed by He and Young [7] based on hidden Vector State (HVS) and statistic machine translation model [8]. An approach combined with these two categories makes full use of advantage of them [9].…”

Section: Introductionmentioning

confidence: 99%

Fuzzy Matching of Semantic Class in Chinese Spoken Language Understanding

Zhao

Yan

2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYSemantic concept in an utterance is obtained by a fuzzy matching methods to solve problems such as words' variation induced by automatic speech recognition (ASR), or missing field of key information by users in the process of spoken language understanding (SLU). A twostage method is proposed: first, we adopt conditional random field (CRF) for building probabilistic models to segment and label entity names from an input sentence. Second, fuzzy matching based on similarity function is conducted between the named entities labeled by a CRF model and the reference characters of a dictionary. The experiments compare the performances in terms of accuracy and processing speed. Dice similarity and cosine similarity based on TF score can achieve better accuracy performance among four similarity measures, which equal to and greater than 93% in F1-measure. Especially the latter one improved by 8.8% and 9% respectively compared to q-gram and improved edit-distance, which are two conventional methods for string fuzzy matching.

show abstract

“…Statistical methods are attractive because they can be easily adapted to new conditions using only annotated training data. Statistical methods for SLU have been studied in a Hidden Vector State (HVS) Model (He et al, 2005) and a data-driven statistical models (Miller et al 1994;Pieraccini et al 1992;Wang et al 2006). In addition, Jeong and Lee (2008) proposed a unified probabilistic model (triangular-chain CRF) combining the named entity and dialog-act of SLU.…”

Section: Related Workmentioning

confidence: 99%

A Simultaneous Recognition Framework for the Spoken Language Understanding Module of Intelligent Personal Assistant Software on Smart Phones

Lee

Seo

2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

View full text Add to dashboard Cite

The intelligent personal assistant software such as the Apple's Siri and Samsung's S-Voice has been issued these days. This paper introduces a novel Spoken Language Understanding (SLU) module to predict user's intention for determining system actions of the intelligent personal assistant software. The SLU module usually consists of several connected recognition tasks on a pipeline framework, whereas the proposed SLU module simultaneously recognizes four recognition tasks on a recognition framework using Conditional Random Fields (CRF). The four tasks include named entity, speech-act, target and operation recognition. In the experiments, the new simultaneous recognition method achieves the higher performance of 4% and faster speed of about 25% than other method using a pipeline framework. By a significance test, this improvement is considered to be statistically significant as a p-value of smaller than 0.05.

show abstract

Hidden understanding models of natural language

Cited by 59 publications

References 12 publications

Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsing

Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsing

Fuzzy Matching of Semantic Class in Chinese Spoken Language Understanding

A Simultaneous Recognition Framework for the Spoken Language Understanding Module of Intelligent Personal Assistant Software on Smart Phones

Contact Info

Product

Resources

About