China 
Africa 
Explore chapters and articles related to this topic
Natural Language Processing
Published in Vishal Jain, Akash Tayal, Jaspreet Singh, Arun Solanki, Cognitive Computing Systems, 2021
V. Vishnuprabha, Lino Murali, Daleesha M. Viswanathan
Semantic role labeling is to identify a verb or a predicate and its arguments in a sentence [1]. Each argument identified is labeled based on its semantic relation with the predicate. Semantic role labeling within the sentence makes the meaning representation independent of syntactic arrangement. Both supervised and unsupervised methods are used in semantic role labeling. The semantic roles can come variously from resources such as PropBank, FrameNet, or VerbNet. It can also be extended to similar semantic roles that are introduced by other POS, such as nominal or adjectival elements [2]. Semantic role labeling is also called as thematic role labeling, case role assignment, or even shallow semantic parsing [1].
A survey on non-factoid question answering systems
Published in International Journal of Computers and Applications, 2022
Manvi Breja, Sanjay Kumar Jain
Question Analysis module analyzes and retrieves important information from the question to determine the focus and intent of the user. It consists of three sub-modules (1) Question Preprocessing, (2) Question Classification, and (3) Question Reformulation. Question Preprocessing removes stopwords and retrieves keywords of question. Question classification processes question lexically, syntactically, and semantically to find its intent and label it with its type and expected answer type. Lexical analysis breaks the questions into tokens and recognizes the role of each term in a question. Syntactic analysis employs a dependency parser to find the relation between lexical terms extracted from question. Semantic analysis determines the meaning of terms using semantic role labeling and labels phrases in a sentence with semantic roles. Question Reformulation reformulates the question to gain an insight into the user’s intent from question.
Automated Identification of Causal Relationships in Nuclear Power Plant Event Reports
Published in Nuclear Technology, 2019
Yunfei Zhao, Xiaoxu Diao, Jonathon Huang, Carol Smidts
Parts of speech denote word classes or categories, for instance, noun or verb. The parts of speech are useful because of the large amount of information they can provide about the words and their neighbors.14 A number of lists of parts of speech have been defined by different researchers. The most widely used list is the 45-tag Penn Treebank tagset.15 Dependency parsing is used to identify the semantic relations between words in a sentence. Examples of dependencies include nominal subject (nsubj), direct object (dobj), determiner (det), etc.14 For instance, in the sentence “She looks very beautiful.”, She is the nominal subject (nsubj) of looks. Further details on dependency relations can be found in the literature.16–18 Both parts of speech and dependencies have been used as features in more complex natural language processing tasks, such as semantic role labeling.19
Semantic Role Labeling Based on Valence Structure and Deep Neural Network
Published in IETE Journal of Research, 2023
With the introduction of theories such as valence grammar and case grammar, scholars engaged in language research have begun to pay more and more attention to the issue of semantic roles. They have applied these theories to language research and proposed many semantic role labeling systems. At present, most of the semantic role labeling research is based on PropBank, NomBank and the semantic role labeling system based on these benchmark corpuses.