Results 11 to 20 of about 6,834,762 (337)
SgSum:Transforming Multi-document Summarization into Sub-graph Selection [PDF]
Conference on Empirical Methods in Natural Language Processing, 2021 Most of existing extractive multi-document summarization (MDS) methods score each sentence individually and extract salient sentences one by one to compose a summary, which have two main drawbacks: (1) neglecting both the intra and cross-document ...
Moye Chen +5 more
openalex +3 more sources
Automatic Document Selection for Efficient Encoder Pretraining [PDF]
Conference on Empirical Methods in Natural Language Processing, 2022 Building pretrained language models is considered expensive and data-intensive, but must we increase dataset size to achieve better performance?
Yukun Feng +3 more
openalex +3 more sources
Applied Computational Intelligence and Soft Computing, 2018 Sentiment analysis in a movie review is the needs of today lifestyle. Unfortunately, enormous features make the sentiment of analysis slow and less sensitive. Finding the optimum feature selection and classification is still a challenge.
Asriyanti Indah Pratiwi, Adiwijaya
doaj +2 more sources
Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs [PDF]
North American Chapter of the Association for Computational Linguistics, 2022 Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification problem where each sentence is handled ...
Sha Li +6 more
semanticscholar +1 more source
IEEE Access, 2021 Sentiment classification is increasingly used to automatically identify a positive or negative sentiment in a text review. In classification, feature selection had always been a critical and challenging problem.
Nur Syafiqah Mohd Nafis, Suryanti Awang
semanticscholar +1 more source
Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning [PDF]
Conference on Empirical Methods in Natural Language Processing, 2020 Document-level neural machine translation has yielded attractive improvements. However, majority of existing methods roughly use all context sentences in a fixed scope. They neglect the fact that different source sentences need different sizes of context.
Xiaomian Kang +3 more
semanticscholar +1 more source
A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots [PDF]
International Joint Conference on Artificial Intelligence, 2019 We present a document-grounded matching network (DGMN) for response selection that can power a knowledge-aware retrieval-based chatbot system. The challenges of building such a model lie in how to ground conversation contexts with background documents ...
Xueliang Zhao +5 more
openalex +3 more sources
Data-driven Feature Selection Methods for Text Classification: an Empirical Evaluation [PDF]
Journal of Universal Computer Science, 2019 Dimensionality reduction is a crucial task in text classification. The most adopted strategy is feature selection using filter methods. This approach presents a difficulty in determining the best size for the final feature vector.
Rogerio C. P. Fragoso +2 more
doaj +3 more sources
Experiments with document archive size detection [PDF]
, 2003 The size of a document archive is a very important parameter for resource selection in distributed information retrieval systems. In this paper, we present a method for automatically detecting the size (ie the number of documents) of a document archive ...
Crestani, F., Gibb, F., Wu, S.
core +1 more source
The role of domain knowledge in document selection from search results
J. Assoc. Inf. Sci. Technol., 2019 It is a frequently seen scenario that when people are not familiar with their search topics, they use a simple keyword search, which leads to a large amount of search results in multiple pages. This makes it difficult for users to pick relevant documents,
Jingjing Liu, Xiangmin Zhang
semanticscholar +1 more source