Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence

Relation extraction is a type of information extraction task that recognizes semantic relationships between entities in a sentence. Many previous studies have focused on extracting only one semantic relation between two entities in a single sentence. However, multiple entities in a sentence are associated through various relations. To address this issue, we proposed a relation extraction model based on a dual pointer network with a multi-head attention mechanism. The proposed model finds n-to-1 subject–object relations using a forward object decoder. Then, it finds 1-to-n subject–object relations using a backward subject decoder. Our experiments confirmed that the proposed model outperformed previous models, with an F1-score of 80.8% for the ACE (automatic content extraction) 2005 corpus and an F1-score of 78.3% for the NYT (New York Times) corpus.

Download Full-text

Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extraction

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6374 ◽

2020 ◽

Vol 34 (05) ◽

pp. 8528-8535

Author(s):

Tapas Nayak ◽

Hwee Tou Ng

Keyword(s):

New York ◽

Machine Translation ◽

New York Times ◽

Relation Extraction ◽

Prior Work ◽

Time Step ◽

Unstructured Text ◽

Decoder Architecture ◽

Multiple Relation ◽

Representation Scheme

A relation tuple consists of two entities and the relation between them, and often such tuples are found in unstructured text. There may be multiple relation tuples present in a text and they may share one or both entities among them. Extracting such relation tuples from a sentence is a difficult task and sharing of entities or overlapping entities among the tuples makes it more challenging. Most prior work adopted a pipeline approach where entities were identified first followed by finding the relations among them, thus missing the interaction among the relation tuples in a sentence. In this paper, we propose two approaches to use encoder-decoder architecture for jointly extracting entities and relations. In the first approach, we propose a representation scheme for relation tuples which enables the decoder to generate one word at a time like machine translation models and still finds all the tuples present in a sentence with full entity names of different length and with overlapping entities. Next, we propose a pointer network-based decoding approach where an entire tuple is generated at every time step. Experiments on the publicly available New York Times corpus show that our proposed approaches outperform previous work and achieve significantly higher F1 scores.

Download Full-text

Semantic Enhanced Distantly Supervised Relation Extraction via Graph Attention Network

Information ◽

10.3390/info11110528 ◽

2020 ◽

Vol 11 (11) ◽

pp. 528

Author(s):

Xiaoye Ouyang ◽

Shudong Chen ◽

Rong Wang

Keyword(s):

New York ◽

New York Times ◽

Relation Extraction ◽

Extraction Methods ◽

Semantic Features ◽

Attention Networks ◽

Word Position ◽

Supervised Methods ◽

Dependency Trees ◽

Type Information

Distantly Supervised relation extraction methods can automatically extract the relation between entity pairs, which are essential for the construction of a knowledge graph. However, the automatically constructed datasets comprise amounts of low-quality sentences and noisy words, and the current Distantly Supervised methods ignore these noisy data, resulting in unacceptable accuracy. To mitigate this problem, we present a novel Distantly Supervised approach SEGRE (Semantic Enhanced Graph attention networks Relation Extraction) for improved relation extraction. Our model first uses word position and entity type information to provide abundant local features and background knowledge. Then it builds the dependency trees to remove noisy words that are irrelevant to relations and employs Graph Attention Networks (GATs) to encode syntactic information, which also captures the important semantic features of relational words in each instance. Furthermore, to make our model more robust against noisy words, the intra-bag attention module is used to weight the bag representation and mitigate noise in the bag. Through extensive experiments on Riedel New York Times (NYT) and Google IISc Distantly Supervised (GIDS) datasets, we demonstrate SEGRE’s effectiveness.

Download Full-text

A Topical Category-Aware Neural Text Summarizer

Applied Sciences ◽

10.3390/app10165422 ◽

2020 ◽

Vol 10 (16) ◽

pp. 5422 ◽

Cited By ~ 1

Author(s):

So-Eon Kim ◽

Nazira Kaibalina ◽

Seong-Bae Park

Keyword(s):

New York ◽

New York Times ◽

Attention Mechanism ◽

Text Summarization ◽

Original Text ◽

Automatic Summarization ◽

Specific Category ◽

Proposed Model ◽

Latent Topic ◽

Content Information

The advent of the sequence-to-sequence model and the attention mechanism has increased the comprehension and readability of automatically generated summaries. However, most previous studies on text summarization have focused on generating or extracting sentences only from an original text, even though every text has a latent topic category. That is, even if a topic category helps improve the summarization quality, there have been no efforts to utilize such information in text summarization. Therefore, this paper proposes a novel topical category-aware neural text summarizer which is differentiated from legacy neural summarizers in that it reflects the topic category of an original text into generating a summary. The proposed summarizer adopts the class activation map (CAM) as topical influence of the words in the original text. Since the CAM excerpts the words relevant to a specific category from the text, it allows the attention mechanism to be influenced by the topic category. As a result, the proposed neural summarizer reflects the topical information of a text as well as the content information into a summary by combining the attention mechanism and CAM. The experiments on The New York Times Annotated Corpus show that the proposed model outperforms the legacy attention-based sequence-to-sequence model, which proves that it is effective at reflecting a topic category into automatic summarization.

Download Full-text

Inhaltsanalyse elektronisch gespeicherter Massendaten der internationalen Presse

Zeitschrift für Medienpsychologie ◽

10.1026//1617-6383.15.3.98 ◽

2003 ◽

Vol 15 (3) ◽

pp. 98-105 ◽

Cited By ~ 1

Author(s):

Mark Galliker ◽

Jan Herman

Keyword(s):

New York ◽

New York Times

Zusammenfassung. Am Beispiel der Repräsentation von Mann und Frau in der Times und in der New York Times wird ein inhaltsanalytisches Verfahren vorgestellt, das sich besonders für die Untersuchung elektronisch gespeicherter Printmedien eignet. Unter Co-Occurrence-Analyse wird die systematische Untersuchung verbaler Kombinationen pro Zähleinheit verstanden. Diskutiert wird das Problem der Auswahl der bei der Auswertung und Darstellung der Ergebnisse berücksichtigten semantischen Einheiten.

Download Full-text