| LDR | | 03344nmm uu200457 4500 |
| 001 | | 000000332271 |
| 005 | | 20240805170509 |
| 008 | | 181129s2018 |||||||||||||||||c||eng d |
| 020 | |
▼a 9780438149212 |
| 035 | |
▼a (MiAaPQ)AAI10751591 |
| 035 | |
▼a (MiAaPQ)umd:18819 |
| 040 | |
▼a MiAaPQ
▼c MiAaPQ
▼d 248032 |
| 082 | 0 |
▼a 004 |
| 100 | 1 |
▼a He, Hua.
▼0 (orcid)0000-0002-5294-8261 |
| 245 | 10 |
▼a Architecture, Models, and Algorithms for Textual Similarity. |
| 260 | |
▼a [S.l.] :
▼b University of Maryland, College Park.,
▼c 2018 |
| 260 | 1 |
▼a Ann Arbor :
▼b ProQuest Dissertations & Theses,
▼c 2018 |
| 300 | |
▼a 212 p. |
| 500 | |
▼a Source: Dissertation Abstracts International, Volume: 79-11(E), Section: B. |
| 500 | |
▼a Adviser: Jimmy Lin. |
| 502 | 1 |
▼a Thesis (Ph.D.)--University of Maryland, College Park, 2018. |
| 520 | |
▼a Identifying similar pieces of texts remains one of the fundamental problems in computational linguistics. This dissertation focuses on the textual similarity measurement and identification problem by studying a variety of major tasks that share |
| 520 | |
▼a We investigate how to make textual similarity measurement more accurate with deep neural networks. Traditional approaches are either based on feature engineering which leads to disconnected solutions, or the Siamese architecture which treats inp |
| 520 | |
▼a Our multi-perspective convolutional neural networks (MPCNN) uses a multiplicity of perspectives to process input sentences with multiple parallel convolutional neural networks, is able to extract salient sentence-level features automatically at |
| 520 | |
▼a We also provide an attention-based input interaction layer on top of the MPCNN model. The input interaction layer models a closer relationship of input words by converting two separate sentences into an inter-related sentence pair. This layer ut |
| 520 | |
▼a We then provide our pairwise word interaction model with very deep neural networks (PWI). This model directly encodes input word interactions with novel pairwise word interaction modeling and a novel similarity focus layer. The use of very deep |
| 520 | |
▼a We also focus on the question answering task with a pairwise ranking approach. Unlike traditional pointwise approach of the task, our pairwise ranking approach with the use of negative sampling focuses on modeling interactions between two pairs |
| 520 | |
▼a For the insight extraction on biomedical literature task, we develop neural networks with similarity modeling for better causality/correlation relation extraction, as we convert the extraction task into a similarity measurement task. Our approac |
| 520 | |
▼a Lastly, we explore how to exploit massive parallelism offered by modern GPUs for high-efficiency pattern matching. We take advantage of GPU hardware advances and develop a massive parallelism approach. We firstly work on phrase-based SMT, where |
| 590 | |
▼a School code: 0117. |
| 650 | 4 |
▼a Computer science. |
| 690 | |
▼a 0984 |
| 710 | 20 |
▼a University of Maryland, College Park.
▼b Computer Science. |
| 773 | 0 |
▼t Dissertation Abstracts International
▼g 79-11B(E). |
| 773 | |
▼t Dissertation Abstract International |
| 790 | |
▼a 0117 |
| 791 | |
▼a Ph.D. |
| 792 | |
▼a 2018 |
| 793 | |
▼a English |
| 856 | 40 |
▼u http://www.riss.kr/pdu/ddodLink.do?id=T14997178
▼n KERIS |
| 980 | |
▼a 201812
▼f 2019 |
| 990 | |
▼a 관리자 |