Matches in SemOpenAlex for { <https://semopenalex.org/work/W2993157032> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2993157032 abstract "Semantic parsing in Natural language processing (NLP) is a challenging task, which has been studied for many years. The main purpose is to model the language as a logical form like a machine translation task. Recently, an approach which uses a Neural network with Sequence to sequence model (Seq2seq) has achieved positive results. However, there are many challenges which have not been solved thoroughly yet, especially in the problem of rare words. Rare words in a natural sentence are usually the name of an object, a place or number, time, etc. Although these words are very various and difficult for the model to capture meaning, it holds a key information role in human communication (for example: name all the rivers in colorado ?). There are some methods to solve this problem such as using Attention or using Copy mechanism. However, these methods still difficult to copy phrase rare words, especially in case these phrases are variable in size. This paper proposes a novel approach to solve this problem, namely Marking mechanism in Seq2seq. The main idea is to label special words which are rare-words in a sentence by the encoder (marking step) and the decoder represents the logical form based on those labels (transforming step). Our experiments demonstrate that this approach works effectively, achieved a competitive result with old methods on all 3 datasets Geo, Atis, Jobs and special outperformed on our Artificial dataset." @default.
- W2993157032 created "2019-12-13" @default.
- W2993157032 creator A5040245741 @default.
- W2993157032 creator A5054854013 @default.
- W2993157032 creator A5060590567 @default.
- W2993157032 date "2019-10-01" @default.
- W2993157032 modified "2023-09-24" @default.
- W2993157032 title "Marking Mechanism in Sequence-to-sequence Model for Mapping Language to Logical Form" @default.
- W2993157032 cites W1902237438 @default.
- W2993157032 cites W2064675550 @default.
- W2993157032 cites W2103457851 @default.
- W2993157032 cites W2118434577 @default.
- W2993157032 cites W2161002933 @default.
- W2993157032 cites W2606974598 @default.
- W2993157032 cites W2897767292 @default.
- W2993157032 cites W2962902328 @default.
- W2993157032 cites W2963212250 @default.
- W2993157032 cites W2963655793 @default.
- W2993157032 cites W2963794306 @default.
- W2993157032 cites W2964165364 @default.
- W2993157032 cites W62369917 @default.
- W2993157032 doi "https://doi.org/10.1109/kse.2019.8919471" @default.
- W2993157032 hasPublicationYear "2019" @default.
- W2993157032 type Work @default.
- W2993157032 sameAs 2993157032 @default.
- W2993157032 citedByCount "1" @default.
- W2993157032 countsByYear W29931570322022 @default.
- W2993157032 crossrefType "proceedings-article" @default.
- W2993157032 hasAuthorship W2993157032A5040245741 @default.
- W2993157032 hasAuthorship W2993157032A5054854013 @default.
- W2993157032 hasAuthorship W2993157032A5060590567 @default.
- W2993157032 hasConcept C154945302 @default.
- W2993157032 hasConcept C162324750 @default.
- W2993157032 hasConcept C186644900 @default.
- W2993157032 hasConcept C187736073 @default.
- W2993157032 hasConcept C195324797 @default.
- W2993157032 hasConcept C203005215 @default.
- W2993157032 hasConcept C204321447 @default.
- W2993157032 hasConcept C2776224158 @default.
- W2993157032 hasConcept C2777530160 @default.
- W2993157032 hasConcept C2778112365 @default.
- W2993157032 hasConcept C2779439875 @default.
- W2993157032 hasConcept C2780451532 @default.
- W2993157032 hasConcept C2781238097 @default.
- W2993157032 hasConcept C41008148 @default.
- W2993157032 hasConcept C54355233 @default.
- W2993157032 hasConcept C86803240 @default.
- W2993157032 hasConceptScore W2993157032C154945302 @default.
- W2993157032 hasConceptScore W2993157032C162324750 @default.
- W2993157032 hasConceptScore W2993157032C186644900 @default.
- W2993157032 hasConceptScore W2993157032C187736073 @default.
- W2993157032 hasConceptScore W2993157032C195324797 @default.
- W2993157032 hasConceptScore W2993157032C203005215 @default.
- W2993157032 hasConceptScore W2993157032C204321447 @default.
- W2993157032 hasConceptScore W2993157032C2776224158 @default.
- W2993157032 hasConceptScore W2993157032C2777530160 @default.
- W2993157032 hasConceptScore W2993157032C2778112365 @default.
- W2993157032 hasConceptScore W2993157032C2779439875 @default.
- W2993157032 hasConceptScore W2993157032C2780451532 @default.
- W2993157032 hasConceptScore W2993157032C2781238097 @default.
- W2993157032 hasConceptScore W2993157032C41008148 @default.
- W2993157032 hasConceptScore W2993157032C54355233 @default.
- W2993157032 hasConceptScore W2993157032C86803240 @default.
- W2993157032 hasLocation W29931570321 @default.
- W2993157032 hasOpenAccess W2993157032 @default.
- W2993157032 hasPrimaryLocation W29931570321 @default.
- W2993157032 hasRelatedWork W1532058475 @default.
- W2993157032 hasRelatedWork W1652311832 @default.
- W2993157032 hasRelatedWork W2118300983 @default.
- W2993157032 hasRelatedWork W2135396778 @default.
- W2993157032 hasRelatedWork W2243428364 @default.
- W2993157032 hasRelatedWork W2462453872 @default.
- W2993157032 hasRelatedWork W3107474891 @default.
- W2993157032 hasRelatedWork W3207171446 @default.
- W2993157032 hasRelatedWork W4243252198 @default.
- W2993157032 hasRelatedWork W4245713008 @default.
- W2993157032 isParatext "false" @default.
- W2993157032 isRetracted "false" @default.
- W2993157032 magId "2993157032" @default.
- W2993157032 workType "article" @default.