Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945448559> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2945448559 abstract "In this paper we present a new method for intent recognition for complex dialog management in low resource situations. Complex dialog management is required because our target domain is real world mixed initiative food ordering between agents and their customers, where individual customer utterances may contain multiple intents and refer to food items with complex structure. For example, a customer might say “Can I get a deluxe burger with large fries and oh put extra mayo on the burger would you?” We approach this task as a multi-level sequence labeling problem, with the constraint of limited real training data. Both traditional methods like HMM, MEMM, or CRF and newer methods like DNN or BiLSTM use only homogeneous feature sets. Newer methods perform better but also require considerably more data. Previous research has done pseudo-data synthesis to obtain the required amounts of training data. We propose to use a k-NN learner with heterogeneous feature set. We used windowed word n-grams, POS tag n-grams and pre-trained word embeddings as features. For the experiments we perform a comparison between using pseudo-data and real world data. We also perform semi-supervised self-training to obtain additional labeled data, in order to better model real world scenarios. Instead of using massive pseudo-data, we show that with only less than 1% of the data size, we can achieve better result than any of the methods above by annotating real world data. We achieve labeled bracketed F-scores of 75.46, 52.84 and 49.66 for the three levels of sequence labeling where each level has a longer word span than its previous level. Overall we achieve 60.71F. In comparison, two previous systems, MEMM and DNN-ELMO, achieved 52.32 and 45.25 respectively." @default.
- W2945448559 created "2019-05-29" @default.
- W2945448559 creator A5029240873 @default.
- W2945448559 creator A5037051254 @default.
- W2945448559 date "2019-01-01" @default.
- W2945448559 modified "2023-09-25" @default.
- W2945448559 title "A k-Nearest Neighbor Approach towards Multi-level Sequence Labeling" @default.
- W2945448559 cites W1632114991 @default.
- W2945448559 cites W1934019294 @default.
- W2945448559 cites W2068537423 @default.
- W2945448559 cites W2077302143 @default.
- W2945448559 cites W2094472029 @default.
- W2945448559 cites W2143017621 @default.
- W2945448559 cites W2250539671 @default.
- W2945448559 cites W2473329891 @default.
- W2945448559 cites W2604698497 @default.
- W2945448559 cites W2897650517 @default.
- W2945448559 cites W2912270430 @default.
- W2945448559 cites W2962739339 @default.
- W2945448559 doi "https://doi.org/10.18653/v1/n19-2019" @default.
- W2945448559 hasPublicationYear "2019" @default.
- W2945448559 type Work @default.
- W2945448559 sameAs 2945448559 @default.
- W2945448559 citedByCount "0" @default.
- W2945448559 crossrefType "proceedings-article" @default.
- W2945448559 hasAuthorship W2945448559A5029240873 @default.
- W2945448559 hasAuthorship W2945448559A5037051254 @default.
- W2945448559 hasConcept C119857082 @default.
- W2945448559 hasConcept C136764020 @default.
- W2945448559 hasConcept C138885662 @default.
- W2945448559 hasConcept C153180895 @default.
- W2945448559 hasConcept C154945302 @default.
- W2945448559 hasConcept C162324750 @default.
- W2945448559 hasConcept C173853756 @default.
- W2945448559 hasConcept C177264268 @default.
- W2945448559 hasConcept C187736073 @default.
- W2945448559 hasConcept C199360897 @default.
- W2945448559 hasConcept C204321447 @default.
- W2945448559 hasConcept C2524010 @default.
- W2945448559 hasConcept C2776036281 @default.
- W2945448559 hasConcept C2776401178 @default.
- W2945448559 hasConcept C2778112365 @default.
- W2945448559 hasConcept C2780451532 @default.
- W2945448559 hasConcept C33923547 @default.
- W2945448559 hasConcept C35639132 @default.
- W2945448559 hasConcept C41008148 @default.
- W2945448559 hasConcept C41895202 @default.
- W2945448559 hasConcept C54355233 @default.
- W2945448559 hasConcept C86803240 @default.
- W2945448559 hasConcept C90805587 @default.
- W2945448559 hasConceptScore W2945448559C119857082 @default.
- W2945448559 hasConceptScore W2945448559C136764020 @default.
- W2945448559 hasConceptScore W2945448559C138885662 @default.
- W2945448559 hasConceptScore W2945448559C153180895 @default.
- W2945448559 hasConceptScore W2945448559C154945302 @default.
- W2945448559 hasConceptScore W2945448559C162324750 @default.
- W2945448559 hasConceptScore W2945448559C173853756 @default.
- W2945448559 hasConceptScore W2945448559C177264268 @default.
- W2945448559 hasConceptScore W2945448559C187736073 @default.
- W2945448559 hasConceptScore W2945448559C199360897 @default.
- W2945448559 hasConceptScore W2945448559C204321447 @default.
- W2945448559 hasConceptScore W2945448559C2524010 @default.
- W2945448559 hasConceptScore W2945448559C2776036281 @default.
- W2945448559 hasConceptScore W2945448559C2776401178 @default.
- W2945448559 hasConceptScore W2945448559C2778112365 @default.
- W2945448559 hasConceptScore W2945448559C2780451532 @default.
- W2945448559 hasConceptScore W2945448559C33923547 @default.
- W2945448559 hasConceptScore W2945448559C35639132 @default.
- W2945448559 hasConceptScore W2945448559C41008148 @default.
- W2945448559 hasConceptScore W2945448559C41895202 @default.
- W2945448559 hasConceptScore W2945448559C54355233 @default.
- W2945448559 hasConceptScore W2945448559C86803240 @default.
- W2945448559 hasConceptScore W2945448559C90805587 @default.
- W2945448559 hasLocation W29454485591 @default.
- W2945448559 hasOpenAccess W2945448559 @default.
- W2945448559 hasPrimaryLocation W29454485591 @default.
- W2945448559 hasRelatedWork W112633934 @default.
- W2945448559 hasRelatedWork W1481149166 @default.
- W2945448559 hasRelatedWork W1999131133 @default.
- W2945448559 hasRelatedWork W2891299330 @default.
- W2945448559 hasRelatedWork W2894887961 @default.
- W2945448559 hasRelatedWork W2899286655 @default.
- W2945448559 hasRelatedWork W2922097976 @default.
- W2945448559 hasRelatedWork W2980598790 @default.
- W2945448559 hasRelatedWork W3080496452 @default.
- W2945448559 hasRelatedWork W3120418856 @default.
- W2945448559 isParatext "false" @default.
- W2945448559 isRetracted "false" @default.
- W2945448559 magId "2945448559" @default.
- W2945448559 workType "article" @default.