白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Generation of sentence representation

專利號
US11176333B2
公開日期
2021-11-16
申請人
International Business Machines Corporation(US NY Armonk)
發(fā)明人
Bang An; HongLei Guo; Shiwan Zhao; Zhong Su
IPC分類
G06F40/56; G06F40/30; G06F40/289; G06F40/58
技術領域
sentence,graph,word,nodes,node,syntactic,in,neighbor,may,cloud
地域: NY NY Armonk

摘要

Embodiments of the present disclosure relate to generation of sentence representation. In an embodiment, a method is disclosed. According to the method, a sentence graph is generated from a sentence containing words, the sentence graph comprising nodes representing the words and edges connecting the nodes to indicate relationships between the words. Word representations for the plurality of words are determined based on the sentence graph by applying a graph convolution operation on respective sets of neighbor nodes for respective ones of the nodes, a set of neighbor nodes for a node having edges connected with the node. A sentence representation for the sentence is determined based on the word representations for use in a natural language processing task related to the sentence. In other embodiments, a system and a computer program product are disclosed.

說明書

appos appositional modifier advcl adverbial clause modifier det Determiner modifier ndet Numeric-determiner modifier

It would be appreciated that only some examples of dependency relationships are provided above, and more, less, or different dependency relationships may be used to represent the syntactic relationships between the words in the sentence 402.

In some embodiments, when considering the dependency relationships as the syntactic relationships, opposite dependency relationships may also be added into the sentence graph 512. An opposite dependency relationship is a different type of syntactic relationship from the corresponding dependency relationship. The opposite dependency relationships may be indicated by the edges when generating a directed sentence graph 512. For example, if the graph generation module 510 determines that there is a dependency relationship from a first word to a second word in the sentence 402, there might be an opposite relationship dependency relationship from the second word to the first word. As such, a directed edge may be constructed from a first node representing the first word to a second node representing the second word to indicate the dependency relationship, and a further directed edge may be constructed from the second node to the first node to indicate the opposite dependency relationship.

權利要求

1
微信群二維碼
意見反饋