Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Hou Pong Chan"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 1213-1232 (2021)
AbstractWe study controllable text summarization, which allows users to gain control on a particular attribute (e.g., length limit) of the generated summaries. In this work, we propose a novel training framework based on Constrained Markov Decision P
Externí odkaz:
https://doaj.org/article/cbd0abc00b03485ca14e6196cba18c8d
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 31:188-199
Controllable text generation is an appealing but challenging task, which allows users to specify particular attributes of the generated outputs. In this paper, we propose a controllable dialogue generation model to steer response generation under mul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1502c151912e48d4d940f371542f12c8
https://doi.org/10.1109/taslp.2022.3221002
https://doi.org/10.1109/taslp.2022.3221002
Summarizing text-rich documents has been long studied in the literature, but most of the existing efforts have been made to summarize a static and predefined multi-document set. With the rapid development of online platforms for generating and distri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b35c796bc491eb550886498b966f3fe0
Autor:
Irwin King, Hou Pong Chan
Select-then-compress is a popular hybrid, framework for text summarization due to its high efficiency. This framework first selects salient sentences and then independently condenses each of the selected sentences into a concise version. However, com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c05acc20acd4f56cfb36e13ce788666d
Publikováno v:
SIGIR
Acquiring accurate summarization and sentiment from user reviews is an essential component of modern e-commerce platforms. Review summarization aims at generating a concise summary that describes the key opinions and sentiment of a review, while sent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::033b100d5835b7f9325c0763dd761faa
Publikováno v:
Scopus-Elsevier
ACL
ACL
Keyphrase generation (KG) aims to summarize the main ideas of a document into a set of keyphrases. A new setting is recently introduced into this problem, in which, given a document, the model needs to predict a set of keyphrases and simultaneously d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1bfc686ae0b942687f8abc6894be8987
Publikováno v:
Knowledge-Based Systems. 229:107328
Dialogue summarization aims to generate a summary that indicates the key points of a given dialogue. In this work, we propose an end-to-end neural model for dialogue summarization with two novel modules, namely, the supporting utterance flow modellin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a1685edf341ea7727e7a84ddf941310c
https://doi.org/10.1016/j.knosys.2021.107328
https://doi.org/10.1016/j.knosys.2021.107328
Autor:
Irwin King, Hou Pong Chan
Publikováno v:
EMNLP
The task of thread popularity prediction and tracking aims to recommend a few popular comments to subscribed users when a batch of new comments arrive in a discussion thread. This task has been formulated as a reinforcement learning problem, in which
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4ce754a601a2eef6a0b598dddd73ffe1
https://doi.org/10.18653/v1/d18-1376
https://doi.org/10.18653/v1/d18-1376
Autor:
Irwin King, Hou Pong Chan
Publikováno v:
WWW (Companion Volume)
With the advent of Massive Open Online Courses (MOOCs), students from all over the world can access to quality courses via a web browser. Due to their great convenience, a popular MOOC can easily attract tens of thousands of students to enroll. Hence
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::21540c195cf34a34e839680b5794eae2
https://doi.org/10.1145/3041021.3054165
https://doi.org/10.1145/3041021.3054165
Publikováno v:
WWW (Companion Volume)
Massive Open Online Coursers (MOOCs) offer a convenient way for people to access quality courses via the internet. However, the problem of grading open-ended assignments at such a large scale still remains challenging. Although peer assessment have b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2d0bc0c82d71fc2d123bfbba216ea90c
https://doi.org/10.1145/2872518.2891080
https://doi.org/10.1145/2872518.2891080