Centroid-based Text Summarization through Compositionality of Word Embeddings

Rossiello, Gaetano; Basile, Pierpaolo; Semeraro, Giovanni

doi:10.18653/v1/w17-1003

Cited by 114 publications

(103 citation statements)

References 25 publications

Supporting

Mentioning

100

Contrasting

Unclassified

Order By: Relevance

“…We implement the selection of top-ranking features for both the original and modified models slightly differently to Rossiello et al (2017): all words in the vocabulary are ranked by their value in the centroid vector. On a development dataset, a parameter is tuned that defines the proportion of the ranked vocabulary that is represented in the centroid vector and the rest is set to zero.…”

Section: Original Centroid-based Methodsmentioning

confidence: 99%

“…Rossiello et al (2017) improved the centroidbased method by representing sentences as sums of word embeddings instead of TF-IDF vectors so that semantic relationships between sentences that have no words in common can be captured. Mackie et al (2016) also evaluated summaries from SumRepo and did experiments on improving baseline systems such as the centroid-based and the KL-divergence method with different antiredundancy filters.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Proceedings of the Workshop on New Frontiers in Summarization

2017

View full text Add to dashboard Cite

With the prevalence of video sharing, there are increasing demands for automatic video digestion such as highlight detection. Recently, platforms with crowdsourced time-sync video comments have emerged worldwide, providing a good opportunity for highlight detection. However, this task is non-trivial: (1) time-sync comments often lag behind their corresponding shot; (2) time-sync comments are semantically sparse and noisy; (3) to determine which shots are highlights is highly subjective. The present paper aims to tackle these challenges by proposing a framework that (1) uses concept-mapped lexical-chains for lagcalibration; (2) models video highlights based on comment intensity and combination of emotion and concept concentration of each shot; (3) summarize each detected highlight using improved SumBasic with emotion and concept mapping. Experiments on large real-world datasets show that our highlight detection method and summarization method both outperform other benchmarks with considerable margins. IntroductionEvery day, people watch billions of hours of videos on YouTube, with half of the views on mobile devices 1 . With the prevalence of video shar-1 https://www.youtube.com/yt/press/statistics.html ing, there is increasing demand for fast video digestion. Imagine a scenario where a user wants to quickly grasp a long video, without dragging the progress bar repeatedly to skip shots unappealing to the user. With automatically-generated highlights, users could digest the entire video in minutes, before deciding whether to watch the full video later. Moreover, automatic video highlight detection and summarization could benefit video indexing, video search and video recommendation. However, finding highlights from a video is not a trivial task. First, what is considered to be a "highlight" can be very subjective. Second, a highlight may not always be captured by analyzing low-level features in image, audio and motions. Lack of abstract semantic information has become a bottleneck of highlight detection in traditional video processing.Recently, crowdsourced time-sync video comments, or "bullet-screen comments" have emerged, where real-time generated comments will be flying over or besides the screen, synchronized with the video frame by frame. It has gained popularity worldwide, such as niconico in Japan, Bilibili and Acfun in China, YouTube Live and Twitch Live in USA. The popularity of the timesync comments has suggested new opportunities for video highlight detection based on natural language processing.Nevertheless, it is still a challenge to detect and label highlights using time-sync comments. First, there is almost inevitable lag for comments related to each shot. As in Figure 1, ongoing discussion about one shot may extend to next a few shots. Highlight detection and labeling without lagcalibration may cause inaccurate results. Second, 1 time-sync comments are sparse semantically, both in number of comments per shot and number of tokens per comment. Traditionally bag-of-words statistical model may...

show abstract

Section: Original Centroid-based Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Proceedings of the Workshop on New Frontiers in Summarization

2017

View full text Add to dashboard Cite

show abstract

“…For the comparisons, two unsupervised baseline models are employed. A graph-based unsupervised sentence extraction method, TextRank is employed (Mihalcea and Tarau, 2004), where sentence embeddings are used instead of bag-ofwords representations, based on (Rossiello et al, 2017). As an unsupervised word-level extractive approach, we employ Opinosis (Ganesan et al, 2010), which detects salient phrases in terms of their redundancy.…”

Section: Baselinementioning

confidence: 99%

Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking

Isonuma

Mori

Sakata

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

This paper focuses on the end-to-end abstractive summarization of a single product review without supervision. We assume that a review can be described as a discourse tree, in which the summary is the root, and the child sentences explain their parent in detail. By recursively estimating a parent from its children, our model learns the latent discourse tree without an external parser and generates a concise summary. We also introduce an architecture that ranks the importance of each sentence on the tree to support summary generation focusing on the main review point. The experimental results demonstrate that our model is competitive with or outperforms other unsupervised approaches. In particular, for relatively long reviews, it achieves a competitive or better performance than supervised models. The induced tree shows that the child sentences provide additional information about their parent, and the generated summary abstracts the entire review.

show abstract

“…We use the term concept to denote an arithmetic structure obtained by averaging a set of word vectors to encode a common concept. For example, a concept can represent the selectional preferences of a verb [BDK14], or phrases and sentences [RBS17]. The goal is to evaluate the similarity between a concept and a word (or another concept), e.g., to find nouns a verb prefers as objects.…”

Section: • Compare Conceptsmentioning

confidence: 99%

Interactive Analysis of Word Vector Embeddings

Heimerl

Gleicher

2018

Computer Graphics Forum

View full text Add to dashboard Cite

Word vector embeddings are an emerging tool for natural language processing. They have proven beneficial for a wide variety of language processing tasks. Their utility stems from the ability to encode word relationships within the vector space. Applications range from components in natural language processing systems to tools for linguistic analysis in the study of language and literature. In many of these applications, interpreting embeddings and understanding the encoded grammatical and semantic relations between words is useful, but challenging. Visualization can aid in such interpretation of embeddings. In this paper, we examine the role for visualization in working with word vector embeddings. We provide a literature survey to catalogue the range of tasks where the embeddings are employed across a broad range of applications. Based on this survey, we identify key tasks and their characteristics. Then, we present visual interactive designs that address many of these tasks. The designs integrate into an exploration and analysis environment for embeddings. Finally, we provide example use cases for them and discuss domain user feedback.

show abstract

Centroid-based Text Summarization through Compositionality of Word Embeddings

Cited by 114 publications

References 25 publications

Proceedings of the Workshop on New Frontiers in Summarization

Proceedings of the Workshop on New Frontiers in Summarization

Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking

Interactive Analysis of Word Vector Embeddings

Contact Info

Product

Resources

About