Event-Driven Headline Generation

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pages 462–472, Beijing, China, July 26-31, 2015. c⃝2015 Association for Computational Linguistics Event-Driven Headline Generation Rui Sun†, Yue Zhang‡, Meishan Zhang‡ and Donghong Ji† † Computer School, Wuhan University, China ‡ Singapore University of Technology and Design {ruisun, dhji}@whu.edu.cn {yue zhang, meishan zhang}@sutd.edu.sg Abstract We propose an event-driven model for headline generation. Given an input document, the system identifies a key event chain by extracting a set of structural events that describe them. Then a novel multi-sentence compression algorithm is used to fuse the extracted events, generating a headline for the document. Our model can be viewed as a novel combination of extractive and abstractive headline generation, combining the advantages of both methods using event structures. Standard evaluation shows that our model achieves the best performance compared with previous state-of-the-art systems. 1 Introduction Headline generation (HG) is a text summarization task, which aims to describe an article (or a set of related paragraphs) using a single short sentence. The task is useful in a number of practical scenarios, such as compressing text for mobile device users (Corston-Oliver, 2001), generating table of contents (Erbs et al., 2013), and email summarization (Wan and McKeown, 2004). This task is challenging in not only informativeness and readability, which are challenges to common summarization tasks, but also the length reduction, which is unique for headline generation. Previous headline generation models fall into two main categories, namely extractive HG and abstractive HG (Woodsend et al., 2010; Alfonseca et al., 2013). Both consist of two steps: candidate extraction and headline generation. Extractive models choose a set of salient sentences in candidate extraction, and then exploit sentence compression techniques to achieve headline generation (Dorr et al., 2003; Texts Phrases Events Sentences Candidate Ranking Candidate #1 ... Candidate #i ... Candidate #K Multi-Sentence Compression Headline Candidate Extraction Headline Generation Figure 1: System framework. Zajic et al., 2005). Abstractive models choose a set of informative phrases for candidate extraction, and then exploit sentence synthesis techniques for headline generation (Soricut and Marcu, 2007; Woodsend et al., 2010; Xu et al., 2010). Extractive HG and abstractive HG have their respective advantages and disadvantages. Extractive models can generate more readable headlines, because the final title is derived by tailoring human-written sentences. However, extractive models give less informative titles (Alfonseca et al., 2013), because sentences are very sparse, making high-recall candidate extraction difficult. In contrast, abstractive models use phrases as the basic processing units, which are much less sparse. However, it is more difficult for abstractive HG to ensure the grammaticality of the generated titles, given that sentence synthesis is still very inaccurate based on a set of phrases with little grammatical information (Zhang, 2013). In this paper, we propose an event-driven model for headline generation, which alleviates the 462 disadvantages of both extractive and abstractive HG. The framework of the proposed model is shown in Figure 1. In particular, we use …

Content truncated to 500 words