Predicting sense convergence with distributional semantics : an application to the CogALex-IV 2014 shared task

This paper presents our system to address the CogALex-IV 2014 shared task of identifying a single word most semantically related to a group of 5 words (queries). Our system uses an implementation of a neural language model and identifies the answer word by finding the most semantically similar word representation to the sum of the query representations. It is a fully unsupervised system which learns on around 20% of the UkWaC corpus. It correctly identifies 85 exact correct targets out of 2,000 queries, 285 approximate targets in lists of 5 suggestions.

A speaker rediarization scheme for improving diarization in large two-speaker telephone datasets

In this paper we propose a novel scheme for carrying out speaker diarization in an iterative manner. We aim to show that the information obtained through the first pass of speaker diarization can be reused to refine and improve the original diarization results. We call this technique speaker rediarization and demonstrate the practical application of our rediarization algorithm using a large archive of two-speaker telephone conversation recordings. We use the NIST 2008 SRE summed telephone corpora for evaluating our speaker rediarization system. This corpus contains recurring speaker identities across independent recording sessions that need to be linked across the entire corpus. We show that our speaker rediarization scheme can take advantage of inter-session speaker information, linked in the initial diarization pass, to achieve a 30% relative improvement over the original diarization error rate (DER) after only two iterations of rediarization.

An iterative speaker re-diarization scheme for improving speaker-based entity extraction in multimedia archives

In this paper we present a novel scheme for improving speaker diarization by making use of repeating speakers across multiple recordings within a large corpus. We call this technique speaker re-diarization and demonstrate that it is possible to reuse the initial speaker-linked diarization outputs to boost diarization accuracy within individual recordings. We first propose and evaluate two novel re-diarization techniques. We demonstrate their complementary characteristics and fuse the two techniques to successfully conduct speaker re-diarization across the SAIVT-BNEWS corpus of Australian broadcast data. This corpus contains recurring speakers in various independent recordings that need to be linked across the dataset. We show that our speaker re-diarization approach can provide a relative improvement of 23% in diarization error rate (DER), over the original diarization results, as well as improve the estimated number of speakers and the cluster purity and coverage metrics.

Rescaling clustering trees using impact ratios for robust hierarchical speaker clustering

We present a novel method for improving hierarchical speaker clustering in the tasks of speaker diarization and speaker linking. In hierarchical clustering, a tree can be formed that demonstrates various levels of clustering. We propose a ratio that expresses the impact of each cluster on the formation of this tree and use this to rescale cluster scores. This provides score normalisation based on the impact of each cluster. We use a state-of-the-art speaker diarization and linking system across the SAIVT-BNEWS corpus to show that our proposed impact ratio can provide a relative improvement of 16% in diarization error rate (DER).

From words to models : a bibliometric approach to designing agent-based models in entrepreneurship

Agent-based modeling and simulation (ABMS) may fit well with entrepreneurship research and practice because the core concepts and basic premises of entrepreneurship coincide with the characteristics of ABMS. However, it is difficult to find cases where ABMS is applied to entrepreneurship research. To apply ABMS to entrepreneurship and organization studies, designing a conceptual model is important; thus to effectively design a conceptual model, various mixed method approaches are being attempted. As a new mixed method approach to ABMS, this study proposes a bibliometric approach to designing agent based models, which establishes and analyzes a domain corpus. This study presents an example on the venture creation process using the bibliometric approach. This example shows us that the results of the multi-agent simulations on the venturing process based on the bibliometric approach are close to each nation’s surveyed data on the venturing activities. In conclusion, by the bibliometric approach proposed in this study, all the agents and the agents’ behaviors related to a phenomenon can be extracted effectively, and a conceptual model for ABMS can be designed with the agents and their behaviors. This study contributes to the entrepreneurship and organization studies by promoting the application of ABMS.

Sweden of the Sagas

In this paper, I discuss the representation of Sweden and Swedes in the Íslendingasögur, with an emphasis on identifying patterns across the works, both in terms of narrative structure and content. The aim in doing so is to shed light on modes of representing non-Icelanders in the Íslendingasögur, as well as on medieval Icelandic conceptions of Sweden as a distinct region within Scandinavia. I also aim here to add to a longer-term project that examines the place of foreign visitors to Iceland in the saga corpus more generally. As the scope of this paper is limited to Swedish characters, I am cautious about drawing broad conclusions about their representation – observations given here will need to be framed by a wider study, and one that reads for the characterisation of Swedes in the context both of other genres of saga literature and representations of characters from other regions beside Sweden. However, it is clear that some similarities exist in saga episodes involving Swedish characters: in four of the Íslendingasögur, Swedes are given roles as intruders or outsiders who threaten the community of the saga and whose deaths bring about a change in the for- tunes of their killers.

Coding livecoding

Livecoding is an artistic programming practice in which an artist's low-level interaction can be observed with sufficiently high fidelity to allow for transcription and analysis. This paper presents the first reported" coding" of livecoding videos. From an identified corpus of videos available on the web, we coded performances of two different livecoding artists, recording both the (textual) programming edit events and the musical effect of these edits.

Decision support for the efficient annotation of bioacoustic events

Acoustic sensors allow scientists to scale environmental monitoring over large spatiotemporal scales. The faunal vocalisations captured by these sensors can answer ecological questions, however, identifying these vocalisations within recorded audio is difficult: automatic recognition is currently intractable and manual recognition is slow and error prone. In this paper, a semi-automated approach to call recognition is presented. An automated decision support tool is tested that assists users in the manual annotation process. The respective strengths of human and computer analysis are used to complement one another. The tool recommends the species of an unknown vocalisation and thereby minimises the need for the memorization of a large corpus of vocalisations. In the case of a folksonomic tagging system, recommending species tags also minimises the proliferation of redundant tag categories. We describe two algorithms: (1) a “naïve” decision support tool (16%–64% sensitivity) with efficiency of O(n) but which becomes unscalable as more data is added and (2) a scalable alternative with 48% sensitivity and an efficiency ofO(log n). The improved algorithm was also tested in a HTML-based annotation prototype. The result of this work is a decision support tool for annotating faunal acoustic events that may be utilised by other bioacoustics projects.