The Experts below are selected from a list of 3195 Experts worldwide ranked by ideXlab platform
Pengjie Ren - One of the best experts on this subject based on the ideXlab platform.
-
sentence relations for extractive summarization with deep neural networks
ACM Transactions on Information Systems, 2018Co-Authors: Pengjie Ren, Furu Wei, Zhumin Chen, Zhaochun Ren, Liqiang Nie, Maarten De RijkeAbstract:Sentence regression is a type of extractive summarization that achieves state-of-the-art performance and is commonly used in practical systems. The most challenging task within the sentence regression framework is to identify discriminative features to represent each sentence. In this article, we study the use of sentence relations, e.g., Contextual Sentence Relations (CSR), Title Sentence Relations (TSR), and Query Sentence Relations (QSR), so as to improve the performance of sentence regression. CSR, TSR, and QSR refer to the relations between a main body sentence and its local context, its document title, and a given query, respectively.We propose a deep neural network model, Sentence Relation-based Summarization (SRSum), that consists of five sub-models, PriorSum, CSRSum, TSRSum, QSRSum, and SFSum. PriorSum encodes the latent semantic meaning of a sentence using a bi-gram convolutional neural network. SFSum encodes the surface information of a sentence, e.g., sentence length, sentence position, and so on. CSRSum, TSRSum, and QSRSum are three sentence relation sub-models corresponding to CSR, TSR, and QSR, respectively. CSRSum evaluates the ability of each sentence to summarize its local contexts. Specifically, CSRSum applies a CSR-based word-level and sentence-level attention mechanism to simulate the context-aware reading of a human reader, where words and sentences that have anaphoric relations or local summarization abilities are easily remembered and paid attention to. TSRSum evaluates the semantic closeness of each sentence with respect to its title, which usually reflects the main ideas of a document. TSRSum applies a TSR-based attention mechanism to simulate people’s reading ability with the main idea (title) in mind. QSRSum evaluates the relevance of each sentence with given queries for the query-focused summarization. QSRSum applies a QSR-based attention mechanism to simulate the attentive reading of a human reader with some queries in mind. The mechanism can recognize which parts of the given queries are more likely answered by a sentence under consideration. Finally as a whole, SRSum automatically learns useful latent features by jointly learning representations of query sentences, content sentences, and title sentences as well as their relations.We conduct extensive experiments on six benchmark datasets, including generic multi-document summarization and query-focused multi-document summarization. On both tasks, SRSum achieves comparable or superior performance compared with state-of-the-art approaches in terms of multiple ROUGE metrics.
-
leveraging contextual sentence relations for extractive summarization using a neural attention model
International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017Co-Authors: Pengjie Ren, Furu Wei, Zhumin Chen, Zhaochun Ren, Maarten De RijkeAbstract:As a framework for extractive summarization, sentence regression has achieved state-of-the-art performance in several widely-used practical systems. The most challenging task within the sentence regression framework is to identify discriminative features to encode a sentence into a feature vector. So far, sentence regression approaches have neglected to use features that capture contextual relations among sentences. We propose a neural network model, Contextual Relation-based Summarization (CRSum), to take advantage of contextual relations among sentences so as to improve the performance of sentence regression. Specifically, we first use sentence relations with a word-level attentive pooling convolutional neural network to construct sentence representations. Then, we use contextual relations with a sentence-level attentive pooling recurrent neural network to construct context representations. Finally, CRSum automatically learns useful contextual features by jointly learning representations of sentences and similarity scores between a sentence and sentences in its context. Using a two-level attention mechanism, CRSum is able to pay attention to important content, i.e., words and sentences, in the surrounding context of a given sentence. We carry out extensive experiments on six benchmark datasets. CRSum alone can achieve comparable performance with state-of-the-art approaches; when combined with a few basic surface features, it significantly outperforms the state-of-the-art in terms of multiple ROUGE metrics.
-
a redundancy aware sentence regression framework for extractive summarization
International Conference on Computational Linguistics, 2016Co-Authors: Pengjie Ren, Furu Wei, Zhumin Chen, Ming ZhouAbstract:Existing sentence regression methods for extractive summarization usually model sentence importance and redundancy in two separate processes. They first evaluate the importance f(s) of each sentence s and then select sentences to generate a summary based on both the importance scores and redundancy among sentences. In this paper, we propose to model importance and redundancy simultaneously by directly evaluating the relative importance f(s|S) of a sentence s given a set of selected sentences S. Specifically, we present a new framework to conduct regression with respect to the relative gain of s given S calculated by the ROUGE metric. Besides the single sentence features, additional features derived from the sentence relations are incorporated. Experiments on the DUC 2001, 2002 and 2004 multi-document summarization datasets show that the proposed method outperforms state-of-the-art extractive summarization approaches.
Maarten De Rijke - One of the best experts on this subject based on the ideXlab platform.
-
sentence relations for extractive summarization with deep neural networks
ACM Transactions on Information Systems, 2018Co-Authors: Pengjie Ren, Furu Wei, Zhumin Chen, Zhaochun Ren, Liqiang Nie, Maarten De RijkeAbstract:Sentence regression is a type of extractive summarization that achieves state-of-the-art performance and is commonly used in practical systems. The most challenging task within the sentence regression framework is to identify discriminative features to represent each sentence. In this article, we study the use of sentence relations, e.g., Contextual Sentence Relations (CSR), Title Sentence Relations (TSR), and Query Sentence Relations (QSR), so as to improve the performance of sentence regression. CSR, TSR, and QSR refer to the relations between a main body sentence and its local context, its document title, and a given query, respectively.We propose a deep neural network model, Sentence Relation-based Summarization (SRSum), that consists of five sub-models, PriorSum, CSRSum, TSRSum, QSRSum, and SFSum. PriorSum encodes the latent semantic meaning of a sentence using a bi-gram convolutional neural network. SFSum encodes the surface information of a sentence, e.g., sentence length, sentence position, and so on. CSRSum, TSRSum, and QSRSum are three sentence relation sub-models corresponding to CSR, TSR, and QSR, respectively. CSRSum evaluates the ability of each sentence to summarize its local contexts. Specifically, CSRSum applies a CSR-based word-level and sentence-level attention mechanism to simulate the context-aware reading of a human reader, where words and sentences that have anaphoric relations or local summarization abilities are easily remembered and paid attention to. TSRSum evaluates the semantic closeness of each sentence with respect to its title, which usually reflects the main ideas of a document. TSRSum applies a TSR-based attention mechanism to simulate people’s reading ability with the main idea (title) in mind. QSRSum evaluates the relevance of each sentence with given queries for the query-focused summarization. QSRSum applies a QSR-based attention mechanism to simulate the attentive reading of a human reader with some queries in mind. The mechanism can recognize which parts of the given queries are more likely answered by a sentence under consideration. Finally as a whole, SRSum automatically learns useful latent features by jointly learning representations of query sentences, content sentences, and title sentences as well as their relations.We conduct extensive experiments on six benchmark datasets, including generic multi-document summarization and query-focused multi-document summarization. On both tasks, SRSum achieves comparable or superior performance compared with state-of-the-art approaches in terms of multiple ROUGE metrics.
-
leveraging contextual sentence relations for extractive summarization using a neural attention model
International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017Co-Authors: Pengjie Ren, Furu Wei, Zhumin Chen, Zhaochun Ren, Maarten De RijkeAbstract:As a framework for extractive summarization, sentence regression has achieved state-of-the-art performance in several widely-used practical systems. The most challenging task within the sentence regression framework is to identify discriminative features to encode a sentence into a feature vector. So far, sentence regression approaches have neglected to use features that capture contextual relations among sentences. We propose a neural network model, Contextual Relation-based Summarization (CRSum), to take advantage of contextual relations among sentences so as to improve the performance of sentence regression. Specifically, we first use sentence relations with a word-level attentive pooling convolutional neural network to construct sentence representations. Then, we use contextual relations with a sentence-level attentive pooling recurrent neural network to construct context representations. Finally, CRSum automatically learns useful contextual features by jointly learning representations of sentences and similarity scores between a sentence and sentences in its context. Using a two-level attention mechanism, CRSum is able to pay attention to important content, i.e., words and sentences, in the surrounding context of a given sentence. We carry out extensive experiments on six benchmark datasets. CRSum alone can achieve comparable performance with state-of-the-art approaches; when combined with a few basic surface features, it significantly outperforms the state-of-the-art in terms of multiple ROUGE metrics.
Zhumin Chen - One of the best experts on this subject based on the ideXlab platform.
-
sentence relations for extractive summarization with deep neural networks
ACM Transactions on Information Systems, 2018Co-Authors: Pengjie Ren, Furu Wei, Zhumin Chen, Zhaochun Ren, Liqiang Nie, Maarten De RijkeAbstract:Sentence regression is a type of extractive summarization that achieves state-of-the-art performance and is commonly used in practical systems. The most challenging task within the sentence regression framework is to identify discriminative features to represent each sentence. In this article, we study the use of sentence relations, e.g., Contextual Sentence Relations (CSR), Title Sentence Relations (TSR), and Query Sentence Relations (QSR), so as to improve the performance of sentence regression. CSR, TSR, and QSR refer to the relations between a main body sentence and its local context, its document title, and a given query, respectively.We propose a deep neural network model, Sentence Relation-based Summarization (SRSum), that consists of five sub-models, PriorSum, CSRSum, TSRSum, QSRSum, and SFSum. PriorSum encodes the latent semantic meaning of a sentence using a bi-gram convolutional neural network. SFSum encodes the surface information of a sentence, e.g., sentence length, sentence position, and so on. CSRSum, TSRSum, and QSRSum are three sentence relation sub-models corresponding to CSR, TSR, and QSR, respectively. CSRSum evaluates the ability of each sentence to summarize its local contexts. Specifically, CSRSum applies a CSR-based word-level and sentence-level attention mechanism to simulate the context-aware reading of a human reader, where words and sentences that have anaphoric relations or local summarization abilities are easily remembered and paid attention to. TSRSum evaluates the semantic closeness of each sentence with respect to its title, which usually reflects the main ideas of a document. TSRSum applies a TSR-based attention mechanism to simulate people’s reading ability with the main idea (title) in mind. QSRSum evaluates the relevance of each sentence with given queries for the query-focused summarization. QSRSum applies a QSR-based attention mechanism to simulate the attentive reading of a human reader with some queries in mind. The mechanism can recognize which parts of the given queries are more likely answered by a sentence under consideration. Finally as a whole, SRSum automatically learns useful latent features by jointly learning representations of query sentences, content sentences, and title sentences as well as their relations.We conduct extensive experiments on six benchmark datasets, including generic multi-document summarization and query-focused multi-document summarization. On both tasks, SRSum achieves comparable or superior performance compared with state-of-the-art approaches in terms of multiple ROUGE metrics.
-
leveraging contextual sentence relations for extractive summarization using a neural attention model
International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017Co-Authors: Pengjie Ren, Furu Wei, Zhumin Chen, Zhaochun Ren, Maarten De RijkeAbstract:As a framework for extractive summarization, sentence regression has achieved state-of-the-art performance in several widely-used practical systems. The most challenging task within the sentence regression framework is to identify discriminative features to encode a sentence into a feature vector. So far, sentence regression approaches have neglected to use features that capture contextual relations among sentences. We propose a neural network model, Contextual Relation-based Summarization (CRSum), to take advantage of contextual relations among sentences so as to improve the performance of sentence regression. Specifically, we first use sentence relations with a word-level attentive pooling convolutional neural network to construct sentence representations. Then, we use contextual relations with a sentence-level attentive pooling recurrent neural network to construct context representations. Finally, CRSum automatically learns useful contextual features by jointly learning representations of sentences and similarity scores between a sentence and sentences in its context. Using a two-level attention mechanism, CRSum is able to pay attention to important content, i.e., words and sentences, in the surrounding context of a given sentence. We carry out extensive experiments on six benchmark datasets. CRSum alone can achieve comparable performance with state-of-the-art approaches; when combined with a few basic surface features, it significantly outperforms the state-of-the-art in terms of multiple ROUGE metrics.
-
a redundancy aware sentence regression framework for extractive summarization
International Conference on Computational Linguistics, 2016Co-Authors: Pengjie Ren, Furu Wei, Zhumin Chen, Ming ZhouAbstract:Existing sentence regression methods for extractive summarization usually model sentence importance and redundancy in two separate processes. They first evaluate the importance f(s) of each sentence s and then select sentences to generate a summary based on both the importance scores and redundancy among sentences. In this paper, we propose to model importance and redundancy simultaneously by directly evaluating the relative importance f(s|S) of a sentence s given a set of selected sentences S. Specifically, we present a new framework to conduct regression with respect to the relative gain of s given S calculated by the ROUGE metric. Besides the single sentence features, additional features derived from the sentence relations are incorporated. Experiments on the DUC 2001, 2002 and 2004 multi-document summarization datasets show that the proposed method outperforms state-of-the-art extractive summarization approaches.
Furu Wei - One of the best experts on this subject based on the ideXlab platform.
-
sentence relations for extractive summarization with deep neural networks
ACM Transactions on Information Systems, 2018Co-Authors: Pengjie Ren, Furu Wei, Zhumin Chen, Zhaochun Ren, Liqiang Nie, Maarten De RijkeAbstract:Sentence regression is a type of extractive summarization that achieves state-of-the-art performance and is commonly used in practical systems. The most challenging task within the sentence regression framework is to identify discriminative features to represent each sentence. In this article, we study the use of sentence relations, e.g., Contextual Sentence Relations (CSR), Title Sentence Relations (TSR), and Query Sentence Relations (QSR), so as to improve the performance of sentence regression. CSR, TSR, and QSR refer to the relations between a main body sentence and its local context, its document title, and a given query, respectively.We propose a deep neural network model, Sentence Relation-based Summarization (SRSum), that consists of five sub-models, PriorSum, CSRSum, TSRSum, QSRSum, and SFSum. PriorSum encodes the latent semantic meaning of a sentence using a bi-gram convolutional neural network. SFSum encodes the surface information of a sentence, e.g., sentence length, sentence position, and so on. CSRSum, TSRSum, and QSRSum are three sentence relation sub-models corresponding to CSR, TSR, and QSR, respectively. CSRSum evaluates the ability of each sentence to summarize its local contexts. Specifically, CSRSum applies a CSR-based word-level and sentence-level attention mechanism to simulate the context-aware reading of a human reader, where words and sentences that have anaphoric relations or local summarization abilities are easily remembered and paid attention to. TSRSum evaluates the semantic closeness of each sentence with respect to its title, which usually reflects the main ideas of a document. TSRSum applies a TSR-based attention mechanism to simulate people’s reading ability with the main idea (title) in mind. QSRSum evaluates the relevance of each sentence with given queries for the query-focused summarization. QSRSum applies a QSR-based attention mechanism to simulate the attentive reading of a human reader with some queries in mind. The mechanism can recognize which parts of the given queries are more likely answered by a sentence under consideration. Finally as a whole, SRSum automatically learns useful latent features by jointly learning representations of query sentences, content sentences, and title sentences as well as their relations.We conduct extensive experiments on six benchmark datasets, including generic multi-document summarization and query-focused multi-document summarization. On both tasks, SRSum achieves comparable or superior performance compared with state-of-the-art approaches in terms of multiple ROUGE metrics.
-
leveraging contextual sentence relations for extractive summarization using a neural attention model
International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017Co-Authors: Pengjie Ren, Furu Wei, Zhumin Chen, Zhaochun Ren, Maarten De RijkeAbstract:As a framework for extractive summarization, sentence regression has achieved state-of-the-art performance in several widely-used practical systems. The most challenging task within the sentence regression framework is to identify discriminative features to encode a sentence into a feature vector. So far, sentence regression approaches have neglected to use features that capture contextual relations among sentences. We propose a neural network model, Contextual Relation-based Summarization (CRSum), to take advantage of contextual relations among sentences so as to improve the performance of sentence regression. Specifically, we first use sentence relations with a word-level attentive pooling convolutional neural network to construct sentence representations. Then, we use contextual relations with a sentence-level attentive pooling recurrent neural network to construct context representations. Finally, CRSum automatically learns useful contextual features by jointly learning representations of sentences and similarity scores between a sentence and sentences in its context. Using a two-level attention mechanism, CRSum is able to pay attention to important content, i.e., words and sentences, in the surrounding context of a given sentence. We carry out extensive experiments on six benchmark datasets. CRSum alone can achieve comparable performance with state-of-the-art approaches; when combined with a few basic surface features, it significantly outperforms the state-of-the-art in terms of multiple ROUGE metrics.
-
a redundancy aware sentence regression framework for extractive summarization
International Conference on Computational Linguistics, 2016Co-Authors: Pengjie Ren, Furu Wei, Zhumin Chen, Ming ZhouAbstract:Existing sentence regression methods for extractive summarization usually model sentence importance and redundancy in two separate processes. They first evaluate the importance f(s) of each sentence s and then select sentences to generate a summary based on both the importance scores and redundancy among sentences. In this paper, we propose to model importance and redundancy simultaneously by directly evaluating the relative importance f(s|S) of a sentence s given a set of selected sentences S. Specifically, we present a new framework to conduct regression with respect to the relative gain of s given S calculated by the ROUGE metric. Besides the single sentence features, additional features derived from the sentence relations are incorporated. Experiments on the DUC 2001, 2002 and 2004 multi-document summarization datasets show that the proposed method outperforms state-of-the-art extractive summarization approaches.
Darko Stipanicev - One of the best experts on this subject based on the ideXlab platform.
-
a recursive tf isf based sentence retrieval method with local context
International Journal of Machine Learning and Computing, 2013Co-Authors: Alen Doko, Maja Stula, Darko StipanicevAbstract:Sentence retrieval consists of retrieving relevant sentences from a document base in response to a query. Question answering, novelty detection, summarization, opinion mining and information provenance make use of sentence retrieval. Most of the sentence retrieval methods are trivial adaptations of document retrieval methods. However some newer sentence retrieval methods based on the language modeling framework successfully use some kind of context of sentences. Unlike that there is no successful improvement of the TF-ISF method that takes into account the context of sentences. In this paper we propose a recursive TF-ISF based method that takes into account the local context of a sentence. The context is considered the previous and next sentence of current sentence. We compared the new method to the TF-ISF baseline and to an earlier unsuccessful method that also incorporates a similar context into TF-ISF. We got statistically significant improvements of the results in comparison to both of the methods. Additional benefit of our method is the clear explicit model of the context that will allow us to automatically generate a document representation with context suitable for sentence retrieval which is important for our future work.
