Discriminative sentence compression with conditional random fields

Nomoto, Tadashi

doi:10.1016/j.ipm.2007.01.025

Cited by 26 publications

(23 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is completely different from the compression model for common news sentence, in which the syntactic features are the most necessary features [19], [28]. The reason for this fact is easily explained.…”

Section: B Sentiment Sentence Compression Resultsmentioning

confidence: 90%

See 1 more Smart Citation

Sentence Compression for Aspect-Based Sentiment Analysis

Che

Zhao

Guo

et al. 2015

IEEE/ACM Trans. Audio Speech Lang. Process.

110

View full text Add to dashboard Cite

Sentiment analysis, which addresses the computational treatment of opinion, sentiment, and subjectivity in text, has received considerable attention in recent years. In contrast to the traditional coarse-grained sentiment analysis tasks, such as document-level sentiment classification, we are interested in the fine-grained aspect-based sentiment analysis that aims to identify aspects that users comment on and these aspects' polarities. Aspect-based sentiment analysis relies heavily on syntactic features. However, the reviews that this task focuses on are natural and spontaneous, thus posing a challenge to syntactic parsers. In this paper, we address this problem by proposing a framework of adding a sentiment sentence compression (Sent Comp) step before performing the aspect-based sentiment analysis. Different from the previous sentence compression model for common news sentences, Sent Comp seeks to remove the sentiment-unnecessary information for sentiment analysis, thereby compressing a complicated sentiment sentence into one that is shorter and easier to parse. We apply a discriminative conditional random field model, with certain special features, to automatically compress sentiment sentences. Using the Chinese corpora of four product domains, Sent Comp significantly improves the performance of the aspect-based sentiment analysis. The features proposed for Sent Comp, especially the potential semantic features, are useful for sentiment sentence compression.Index Terms-sentiment analysis, aspect-based sentiment analysis, sentence compression, potential semantic features.1 In this paper, we focus on Chinese sentiment analysis task. The similar method can also be used into other languages. 2 A Chinese natural language processing toolkit, Language Technology Platform (LTP) [10], was used as our dependency parser. More information about the syntactic relations can be found from their paper. The state-of-the-art graph-based dependency parsing model, in the toolkit, was trained on Chinese Dependency Treebank 1.0 (LDC2012T05).

show abstract

Section: B Sentiment Sentence Compression Resultsmentioning

confidence: 90%

“…Similar to the work of Nomoto et al [19], in this paper we regard the sentiment sentence compression as a sequence labeling task, which can be solved using the Conditional Random Fields (CRF) model.…”

Section: B Task Definitionmentioning

confidence: 99%

Sentence Compression for Aspect-Based Sentiment Analysis

Che

Zhao

Guo

et al. 2015

IEEE/ACM Trans. Audio Speech Lang. Process.

110

View full text Add to dashboard Cite

show abstract

“…Clarke and Lapata (2008) improved the above discriminative model by using ILP in decoding, making it convenient to add constraints to preserve grammatical structure. Nomoto (2007) treated the compression task as a sequence labeling problem and used CRF for it. Thadani and McKeown (2013) presented an approach for discriminative sentence compression that jointly produces sequential and syntactic representations for output text.…”

Section: Related Workmentioning

confidence: 99%

Improving Multi-documents Summarization by Sentence Compression based on Expanded Constituent Parse Trees

Li¹,

Liu²,

Liu³

et al. 2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

In this paper, we focus on the problem of using sentence compression techniques to improve multi-document summarization. We propose an innovative sentence compression method by considering every node in the constituent parse tree and deciding its status -remove or retain. Integer liner programming with discriminative training is used to solve the problem. Under this model, we incorporate various constraints to improve the linguistic quality of the compressed sentences. Then we utilize a pipeline summarization framework where sentences are first compressed by our proposed compression model to obtain top-n candidates and then a sentence selection module is used to generate the final summary. Compared with state-ofthe-art algorithms, our model has similar ROUGE-2 scores but better linguistic quality on TAC data.

show abstract

“…There have also been studies on summarization [3], [4], which are related to emphasis because emphasizing also extracts the important parts from a document. Nomoto used CRF for sentence compression and also used syntactic information to improve the readability of the summarized docu- ments [3].…”

Section: Introductionmentioning

confidence: 99%

“…Nomoto used CRF for sentence compression and also used syntactic information to improve the readability of the summarized docu- ments [3]. Shen et al used CRF to extract the features used in machine learning for summarization [4].…”

Section: Introductionmentioning

confidence: 99%

Using Machine Learning for Automatic Estimation of Emphases in Japanese Documents

Murata

Abe

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWe propose a method for automatic emphasis estimation using conditional random fields. In our experiments, the value of Fmeasure obtained using our proposed method (0.31) was higher than that obtained using a random emphasis method (0.20), a method using TF-IDF (0.21), and a method based on LexRank (0.26). On the contrary, the value of F-measure of obtained using our proposed method (0.28) was slightly worse as compared with that obtained using manual estimation (0.26-0.40, with an average of 0.35).

show abstract

Discriminative sentence compression with conditional random fields

Cited by 26 publications

References 12 publications

Sentence Compression for Aspect-Based Sentiment Analysis

Sentence Compression for Aspect-Based Sentiment Analysis

Improving Multi-documents Summarization by Sentence Compression based on Expanded Constituent Parse Trees

Using Machine Learning for Automatic Estimation of Emphases in Japanese Documents

Contact Info

Product

Resources

About