Showing papers in "The Association for Computational Linguistics in 2011"

Findings of the 2011 Workshop on Statistical Machine Translation

Abstract: This paper presents the results of the WMT11 shared tasks, which included a translation task, a system combination task, and a task for machine translation evaluation metrics. We conducted a large-scale manual evaluation of 148 machine translation systems and 41 system combination entries. We used the ranking of these systems to measure how strongly automatic metrics correlate with human judgments of translation quality for 21 evaluation metrics. This year featured a Haitian Creole to English task translating SMS messages sent to an emergency response service in the aftermath of the Haitian earthquake. We also conducted a pilot 'tunable metrics' task to test whether optimizing a fixed system to different metrics would result in perceptibly different translation quality.

Towards tracking semantic change by visual analytics

Abstract: This paper presents a new approach to detecting and tracking changes in word meaning by visually modeling and representing diachronic development in word contexts. Previous studies have shown that computational models are capable of clustering and disambiguating senses, a more recent trend investigates whether changes in word meaning can be tracked by automatic methods. The aim of our study is to offer a new instrument for investigating the diachronic development of word senses in a way that allows for a better understanding of the nature of semantic change in general. For this purpose we combine techniques from the field of Visual Analytics with unsupervised methods from Natural Language Processing, allowing for an interactive visual exploration of semantic change.

Proceedings of the Sixth Workshop on Statistical Machine Translation

Abstract: The EMNLP 2011 Workshop on Statistical Machine Translation (WMT-2011) took place on Saturday and Sunday, July 30--31 in Edinburgh, Scotland, immediately following the Conference on Empirical Methods on Natural Language Processing (EMNLP) 2011, which was hosted by the University of Edinburgh. This is the seventh time this workshop has been held. The first time was in 2005 as part of the ACL 2005 Workshop on Building and Using Parallel Texts. In the following years the Workshop on Statistical Machine Translation was held at HLT-NAACL 2006 in New York City, US, ACL 2007 in Prague, Czech Republic, ACL 2008, Columbus, Ohio, US, EACL 2009 in Athens, Greece, and ACL 2010 in Uppsala, Sweden.

Extracting and classifying Urdu multiword expressions

Abstract: This paper describes a method for automatically extracting and classifying multiword expressions (mWEs) for Urdu on the basis of a relatively small unannotated corpus (around 8.12 million tokens). The mWEs are extracted by an unsupervised method and classified into two distinct classes, namely locations and person names. The classification is based on simple heuristics that take the co-occurrence of mWEs with distinct postpositions into account. The resulting classes are evaluated against a hand-annotated gold standard and achieve an f-score of 0.5 and 0.746 for locations and persons, respectively. A target application is the Urdu ParGram grammar, where mWEs are needed to generate a more precise syntactic and semantic analysis.

Proceedings of the SIGDIAL 2011 Conference

Abstract: It is our great pleasure to present the Proceedings of the SIGDIAL 2011 Conference, the 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue. The conference is held in Portland, Oregon, June 17-18, 2011, co-located with the ACL conference. We received 68 paper submissions: 51 as long papers, 17 as short papers. The members of the Program Committee did a superb job in reviewing the submitted papers, providing helpful comments and contributing to discussions when required. We wish to thank all of them for their advice in selecting the accepted papers and for helping to maintain the high quality of the program. Special thanks go to Nicholas Asher, Dan Bohus, Deborah Dahl, Curry Guinn, Staffan Larsson, Andrei Popescu-Belis, and Antoine Raux for helping out with last minute review requests. Many submissions received strong recommendations from the Program Committee. In line with the SIGDIAL tradition, our aim has been to create a balanced program that could accommodate as many favorably rated papers as possible. Of the 68 submissions, 36 were accepted: 18 of 51 long paper submissions papers were accepted as full papers for plenary presentation, 7 were accepted as long papers for poster presentation, and 5 were accepted as short papers for poster presentation. In addition, 6 of the 17 short paper submissions were accepted for poster presentation, for a total of 18 posters. Of special note this year, four papers were accepted as part of a Special Theme on situated dialogue. In addition, 7 of the 8 demo submissions were presented; the 8th was accepted but withdrawn. This year, the review process continued the mentoring program that was initiated last year, and was coordinated by Ronnie Smith. The mentoring goal is to assist authors of papers that contain innovative ideas to improve their quality regarding English language usage or paper organization. Compared with the first year, reviewers accepted fewer papers that required mentoring, but we hope the initiative will continue and expand.