English
Related papers

Related papers: Unsupervised Deep Keyphrase Generation

200 papers

Aiming to generate a set of keyphrases, Keyphrase Generation (KG) is a classical task for capturing the central idea from a given document. Based on Seq2Seq models, the previous reinforcement learning framework on KG tasks utilizes the…

Computation and Language · Computer Science 2021-09-13 Yichao Luo , Yige Xu , Jiacheng Ye , Xipeng Qiu , Qi Zhang

Abstractive summarization typically relies on large collections of paired articles and summaries. However, in many cases, parallel data is scarce and costly to obtain. We develop an abstractive summarization system that relies only on large…

Computation and Language · Computer Science 2020-03-04 Nikola I. Nikolov , Richard H. R. Hahnloser

This paper presents a new method for inferring the semantic properties of documents by leveraging free-text keyphrase annotations. Such annotations are becoming increasingly abundant due to the recent dramatic growth in semi-structured,…

Computation and Language · Computer Science 2014-01-16 S. R. K. Branavan , Harr Chen , Jacob Eisenstein , Regina Barzilay

Despite the remarkable generative capabilities of language models in producing naturalistic language, their effectiveness on explicit manipulation and generation of linguistic structures remain understudied. In this paper, we investigate…

Computation and Language · Computer Science 2024-06-26 Xinyue Cui , Swabha Swayamdipta

The premise of manual keyphrase annotation is to read the corresponding content of an annotated object. Intuitively, when we read, more important words will occupy a longer reading time. Hence, by leveraging human reading time, we can find…

Computation and Language · Computer Science 2020-10-27 Yingyi Zhang , Chengzhi Zhang

We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and constructing comprehensive background knowledge graphs (KGs);…

Computation and Language · Computer Science 2020-11-03 Qingyun Wang , Lifu Huang , Zhiying Jiang , Kevin Knight , Heng Ji , Mohit Bansal , Yi Luan

The goal of automated feature generation is to liberate machine learning experts from the laborious task of manual feature generation, which is crucial for improving the learning performance of tabular data. The major challenge in automated…

Machine Learning · Computer Science 2023-06-06 Tianping Zhang , Zheyu Zhang , Zhiyuan Fan , Haoyan Luo , Fengyuan Liu , Qian Liu , Wei Cao , Jian Li

Current research in automatic single document summarization is dominated by two effective, yet naive approaches: summarization by sentence extraction, and headline generation via bag-of-words models. While successful in some tasks, neither…

Computation and Language · Computer Science 2009-07-07 Hal Daumé , Daniel Marcu

Keyphrase generation aims to automatically generate short phrases summarizing an input document. The recently emerged ONE2SET paradigm (Ye et al., 2021) generates keyphrases as a set and has achieved competitive performance. Nevertheless,…

Computation and Language · Computer Science 2023-02-17 Binbin Xie , Xiangpeng Wei , Baosong Yang , Huan Lin , Jun Xie , Xiaoli Wang , Min Zhang , Jinsong Su

Search typically relies on keyword queries, but these are often semantically ambiguous. We propose to overcome this by offering users natural language questions, based on their keyword queries, to disambiguate their intent. This…

Information Retrieval · Computer Science 2018-07-18 Heng Ding , Krisztian Balog

Due to the recent boom in artificial intelligence (AI) research, including computer vision (CV), it has become impossible for researchers in these fields to keep up with the exponentially increasing number of manuscripts. In response to…

Computer Vision and Pattern Recognition · Computer Science 2018-11-19 Shintaro Yamamoto , Yoshihiro Fukuhara , Ryota Suzuki , Shigeo Morishima , Hirokatsu Kataoka

High quality arguments are essential elements for human reasoning and decision-making processes. However, effective argument construction is a challenging task for both human and machines. In this work, we study a novel task on…

Computation and Language · Computer Science 2018-05-28 Xinyu Hua , Lu Wang

The dominant text generation models compose the output by sequentially selecting words from a fixed vocabulary. In this paper, we formulate text generation as progressively copying text segments (e.g., words or phrases) from an existing…

Computation and Language · Computer Science 2023-07-17 Tian Lan , Deng Cai , Yan Wang , Heyan Huang , Xian-Ling Mao

Synthetic data is a standard component in training large language models, yet systematic comparisons across design dimensions, including rephrasing strategy, generator model, and source data, remain absent. We conduct extensive controlled…

In the majority of the existing Visual Question Answering (VQA) research, the answers consist of short, often single words, as per instructions given to the annotators during dataset construction. This study envisions a VQA task for natural…

Computer Vision and Pattern Recognition · Computer Science 2020-10-13 Kohei Uehara , Tatsuya Harada

Query routing for retrieval-augmented generation aims to assign an input query to the most suitable search engine. Existing works rely heavily on supervised datasets that require extensive manual annotation, resulting in high costs and…

Information Retrieval · Computer Science 2025-01-15 Feiteng Mu , Liwen Zhang , Yong Jiang , Wenjie Li , Zhen Zhang , Pengjun Xie , Fei Huang

Automatic question generation can benefit many applications ranging from dialogue systems to reading comprehension. While questions are often asked with respect to long documents, there are many challenges with modeling such long documents.…

Computation and Language · Computer Science 2019-10-24 Luu Anh Tuan , Darsh J Shah , Regina Barzilay

A popular tool for unsupervised modelling and mining multi-aspect data is tensor decomposition. In an exploratory setting, where and no labels or ground truth are available how can we automatically decide how many components to extract? How…

Machine Learning · Statistics 2015-03-12 Evangelos E. Papalexakis

This paper explores zero-label learning in Natural Language Processing (NLP), whereby no human-annotated data is used anywhere during training and models are trained purely on synthetic data. At the core of our framework is a novel approach…

Computation and Language · Computer Science 2021-09-21 Zirui Wang , Adams Wei Yu , Orhan Firat , Yuan Cao

Transformer-based architectures in natural language processing force input size limits that can be problematic when long documents need to be processed. This paper overcomes this issue for keyphrase extraction by chunking the long documents…

Computation and Language · Computer Science 2022-05-12 Martin Docekal , Pavel Smrz