Unsupervised learning of narrative schemas and their participants

Chambers, Nathanael; Jurafsky, Dan

doi:10.3115/1690219.1690231

Cited by 445 publications

(721 citation statements)

References 17 publications

Supporting

Mentioning

692

Contrasting

Unclassified

Order By: Relevance

“…Kuna kasutan suuliselt esitatud jutustusi, tundus otstarbekas käsitleda neid kui narratiivide ahelaid (osaliselt järjestatud narratiivsete juhtumite võrgustik, millel on ühine tegelane ja mille narratiivne sündmus ja osavõtjate korteež esindab tüüpsündmusi ja tendentse (Chambers & Jurafsky 2008), tüüpsünd-muste filtreerimist (valik, saabumine, uue keskkonnaga kokkupuuted, kohanemine)). Mõnevõrra sarnaneb see ka isiklike kogemusjuttude (isikujuttude) uurija William Labovi mudeliga, kelle arvates on narratiiviahela iga narratiiv konstrueeritud kõige jutustamistväärivamast sündmusest: see tähendab, et sündmus on üldine ja tal on kõige laiemad järelmid osavõtjate turvalisuse ja heaolu suhtes.…”

Section: Teoreetilisi Lähenemisiunclassified

Adaptation narratives on the example of Australian Estonians

Kõiva¹

2012

View full text Add to dashboard Cite

Section: Teoreetilisi Lähenemisiunclassified

Adaptation narratives on the example of Australian Estonians

Kõiva¹

2012

View full text Add to dashboard Cite

“…Our previous work on modeling contingency relations in film scripts data compared Causal Potential to methods used in previous work: Bigram event models (Manshadi et al, 2008) and Pointwise Mutual Information (PMI) (Chambers and Jurafsky, 2008) and the evaluations showed that CP obtains better results . In this work, we use CP for inducing contingency relation between events and apply three other models as baselines for comparison: Event-Unigram.…”

Section: Baseline Methodsmentioning

confidence: 99%

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Katagiri

Nakano

Fernández

et al. 2016

View full text Add to dashboard Cite

We extend special thanks to our Local co-Chairs, Ron Artstein and Alesia Gainer, and their team of student volunteers. We know SIGDIAL 2016 would not have been possible without Ron and Alesia, who invested so much effort in arranging the conference venue and accommodations, handling registration, making banquet arrangements, and handling numerous other preparations for the conference. The student volunteers for on-site assistance also deserve our appreciation.Ethan Selfridge, Sponsorships Chair, has earned our appreciation for recruiting and liaising with our conference sponsors, many of whom continue to contribute year after year. Sponsorships support valuable aspects of the program, such as the invited speakers and conference banquet. In recognition of this, we gratefully acknowledge the support of our sponsors: (Platinum level) Microsoft Research, Xerox and PARC, Intel, (Gold level) Facebook, (Silver level) Amazon Alexa, Interactions, Educational Testing Service, Honda Research Institute, and Yahoo!. At the same time, we thank Priscilla Rasmussen at the ACL for tirelessly handling the financial aspects of sponsorship for SIGDIAL 2016, and for securing our ISBN.iii We also thank the SIGdial board, especially officers Amanda Stent, Jason Williams and Kristiina Jokinen for their advice and support from beginning to end.Finally, we thank all the authors of the papers in this volume, and all the conference participants for making this stimulating event a valuable opportunity for growth in the research areas of discourse and dialogue. AbstractThis paper presents an end-to-end framework for task-oriented dialog systems using a variant of Deep Recurrent QNetworks (DRQN). The model is able to interface with a relational database and jointly learn policies for both language understanding and dialog strategy. Moreover, we propose a hybrid algorithm that combines the strength of reinforcement learning and supervised learning to achieve faster learning speed. We evaluated the proposed model on a 20 Question Game conversational game simulator. Results show that the proposed method outperforms the modular-based baseline and learns a distributed representation of the latent dialog state. IntroductionTask-oriented dialog systems have been an important branch of spoken dialog system (SDS) research (Raux et al., 2005; Young, 2006; Bohus and Rudnicky, 2003). The SDS agent has to achieve some predefined targets (e.g. booking a flight) through natural language interaction with the users. The typical structure of a task-oriented dialog system is outlined in Figure 1 (Young, 2006). This pipeline consists of several independently-developed modules: natural language understanding (the NLU) maps the user utterances to some semantic representation. This information is further processed by the dialog state tracker (DST), which accumulates the input of the turn along with the dialog history. The DST outputs the current dialog state and the dialog policy selects the next system action based on the dialog state. Then natural language gene...

show abstract

“…Though many early AI systems employed hand-encoded scripts, more recent work has attempted to induce scripts with automatic and scalable techniques. In particular, several related techniques approach the problem of script induction as one of learning narrative chains from text corpora (Chambers and Jurafsky, 2008;Chambers and Jurafsky, 2009;Jans et al, 2012;Pichotta and Mooney, 2014). These statistical approaches have focused on open-domain script acquisition, in which a large number of scripts may be learned, but the acquisition of any particular set of scripts is not guaranteed.…”

Section: Introductionmentioning

confidence: 99%

“…Several followup papers introduce variations and improvements on this original model for learning narrative chains (Chambers and Jurafsky, 2009;Jans et al, 2012;Pichotta and Mooney, 2014). It is from this body of work that we borrow techniques to apply to the Dinners from Hell dataset.…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics

2015

View full text Add to dashboard Cite

will take place in Denver on June 4 and 5 and is colocated with SemEval and NAACL. As in 2014 at COLING, also on this occasion *SEM and SemEval chose to coordinate their programs by featuring a joint invited talk. In this way, *SEM aims to bring together the ACL SIGLEX and ACL SIGSEM communities.The acceptance rate of *SEM 2015 was quite competitive: out of 98 submissions, we accepted 36 papers for an overall acceptance of 37%. The acceptance rate of long paper that were accepted for oral presentation (18 out of 62) is 29%. The papers cover a wide range of topics including distributional semantics; lexical semantics and lexical acquisition; formal and linguistic semantics; discourse semantics; lexical resources, linked data and ontologies; semantics for applications; and extra-propositional semantics: sentiment and figurative meaning.The *SEM 2015 program consists of oral presentations for selected long papers and a poster session for long and short papers.Day One, June 4th:• Joint *SEM SemEval keynote talk by Marco Baroni;• Oral presentation sessions on distributional semantics, lexical semantics, and extra-propositional semantics;• Poster session.Day Two, June 5th:• Keynote talk by Preslav Natkov;• Oral presentation sessions on semantics for applications, lexical resources and ontologies, formal semantics, and discourse semantics;• *SEM Best Paper Award.We cannot finish without saying that *SEM 2015 would not have been possible without the considerable efforts of our area chairs, their reviewers, and the computational semantics community in general.We hope you will enjoy *SEM 2015, Distributional semantic methods have some a priori appeal as models of human meaning acquisition, because they induce word representations from contextual distributions naturally occurring in corpus data without need for supervision. However, learning the meaning of a (concrete) word also involves establishing a link between the word and its typical visual referents, which is beyond the scope of classic, text-based distributional semantics. Since recently several proposals have been put forward about how to induce multimodal word representations from linguistic and visual contexts, it is natural to ask if this line of work, besides its practical implications, can help us to develop more realistic, grounded models of human word learning within the distributional semantics framework.In my talk, I will report about two studies in which we used multimodal distributional semantics (MDS) to simulate human word learning. In one study, we first measured the ability of subjects to link a nonce word to relevant linguistic and visual associates when prompted only by exposure to minimal corpus evidence about it. We then simulated the same task with an MDS model, finding its behavior remarkably similar to that of subjects. In the second study, we constructed a corpus in which child-directed speech is aligned with real-life pictures of the objects mentioned by care-givers. We then trained our MDS model on these data, and inspected the generaliza...

show abstract

Unsupervised learning of narrative schemas and their participants

Cited by 445 publications

References 17 publications

Adaptation narratives on the example of Australian Estonians

Adaptation narratives on the example of Australian Estonians

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics

Contact Info

Product

Resources

About