SMT and SPE machine translation systems for WMT'09

Schwenk, Holger; Rauf, Sadaf Abdul; Mans, France#TAB# Loic BarraultUniversity of Le; Sénellart, Jean

doi:10.3115/1626431.1626458

Cited by 12 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 The video recordings, audio track, metadata, synopsis, cast, detected shots, detected faces, visual concepts, subtitles, and two automatic transcripts, provided by LIMSI [15] and LIUM [23], are available together with the recordings themselves.…”

Section: Search and Hyperlinking Datamentioning

confidence: 99%

Experiments with Segmentation Strategies for Passage Retrieval in Audio-Visual Documents

Galuščáková

Pecina

2014

Proceedings of International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

This paper deals with Information Retrieval from audiovisual recordings. Such recordings are often quite long and users may want to find the exact starting points of relevant passages they search for. In Passage Retrieval, the recordings are automatically segmented into smaller parts, on which the standard retrieval techniques are applied. In this paper, we discuss various techniques for segmentation of audio-visual recordings and focus on machine learning approaches which decide on segment boundaries based on various features combined in a decision-tree model. Our experiments are carried out on the data used for the Search and Hyperlinking Task and Similar Segments in Social Speech Task of the MediaEval Benchmark 2013.

show abstract

Section: Search and Hyperlinking Datamentioning

confidence: 99%

Experiments with Segmentation Strategies for Passage Retrieval in Audio-Visual Documents

Galuščáková

Pecina

2014

Proceedings of International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

show abstract

“…One of the simplest strategies, which has already been put into practice with the Apertium bilingual dictionaries (Tyers 2009;Sanchez-Cartagena and Pérez-Ortiz 2010), consists of adding the dictionary entries directly to the parallel corpus. In addition to the obvious increase in lexical coverage, Schwenk et al (2009) state that the quality of the alignments obtained is also improved when the words in the bilingual dictionary appear in other sentences of the parallel corpus. However, it is not guaranteed that, following this strategy, multi-word expressions from the bilingual dictionary that appear in the SL sentences are translated as such because they may be split into smaller units by the phrase-extraction algorithm.…”

Section: Hybrid and Rule-based Mt Systemsmentioning

confidence: 99%

Getting Past the Language Gap: Innovations in Machine Translation

Delmonte

2012

Mobile Speech and Advanced Natural Language Solutions

View full text Add to dashboard Cite

In this chapter, we will be reviewing state of the art machine translation systems, and will discuss innovative methods for machine translation, highlighting the most promising techniques and applications. Machine translation (MT) has benefited from a revitalization in the last 10 years or so, after a period of relatively slow activity. In 2005 the field received a jumpstart when a powerful complete experimental package for building MT systems from scratch became freely available as a result of the unified efforts of the MOSES international consortium. Around the same time, hierarchical methods had been introduced by Chinese researchers, which allowed the introduction and use of syntactic information in translation modeling. Furthermore, the advances in the related field of computational linguistics, making off-the-shelf taggers and parsers readily available, helped give MT an additional boost. Yet there is still more progress to be made. For example, MT will be enhanced greatly when both syntax and semantics are on board: this still presents a major challenge though many advanced research groups are currently pursuing ways to meet this challenge head-on. The next generation of MT will consist of a collection of hybrid systems. It also augurs well for the mobile environment, as we look forward to more advanced and improved technologies that enable the working of Speech-To-Speech machine translation on hand-held devices, i.e. speech recognition and speech synthesis. We review all of these developments and point out in the final section some of the most promising research avenues for the future of MT.

show abstract

“…We selected TextTiling for its robustness and simplicity, although more advanced techniques such as TopicTiling [24] (same core algorithm but with LDA topic modeling) are also available and could be tested in the future. Table 1 shows the total number of segments, the average segment size (in seconds) and the standard deviation STD (in seconds) for each of the three alternative transcript types of the BBC TV shows available for segmentation: subtitles vs. ASR from LIMSI [11] vs. ASR from LIUM [27]. The longer size of the LIUM-based segments and the larger variability of subtitle-based segments should be noted.…”

Section: Topic Segmentationmentioning

confidence: 99%

“…We generate the data units, namely topic-based segments, from the human-made subtitles provided by the BBC or from the ASR transcripts. We experimented with transcripts from LIMSI [11] and from LIUM [27], both kindly provided to the MediaEval participants. The topic segmentation was performed over the words using the TextTiling algorithm implemented in NLTK.…”

Section: System Overviewmentioning

confidence: 99%

Multimodal Reranking of Content-based Recommendations for Hyperlinking Video Snippets

Bhatt

Pappas

Habibi

et al. 2014

Proceedings of International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

In this paper, we present an approach for topic-level search and hyperlinking of video snippets, which relies on contentbased recommendation and multimodal re-ranking techniques. We identify topic-level segments using transcripts or subtitles and enrich them with other metadata. Segments are indexed in a word vector space. Given a text query or an anchor, the most similar segments are retrieved using cosine similarity scores, which are then combined with visual similarity scores, computed as the distance from the anchor's visual concept vector. This approach has performed well on the MediaEval 2013 Search and Hyperlinking task, evaluated over 1260 hours of BBC TV broadcast, in terms of overall mean average precision. Experiments showed that topic-segments based on transcripts from automatic speech recognition level systems (ASR) led to better performance than the ones based on subtitles for both search and hyperlinking. Moreover, by analyzing the effect of multimodal re-ranking on hyperlinking performance, we emphasize the merits of rich visual information available in the anchors for the hyperlinking task, and the merits of ASR for large-scale search and hyperlinking.

show abstract

SMT and SPE machine translation systems for WMT'09

Cited by 12 publications

References 15 publications

Experiments with Segmentation Strategies for Passage Retrieval in Audio-Visual Documents

Experiments with Segmentation Strategies for Passage Retrieval in Audio-Visual Documents

Getting Past the Language Gap: Innovations in Machine Translation

Multimodal Reranking of Content-based Recommendations for Hyperlinking Video Snippets

Contact Info

Product

Resources

About