Abstract | ||
---|---|---|
Word prediction helps to increase communication rate when using Augmentative and Alternative Communication devices. Basic prediction systems offer topically inappropriate predictions for the context, thus we adapt the predictions to the topic of discourse. However, previous work has relied on texts that are grouped into topics by humans. In contrast, we avoid this restriction by treating each document as a topic. The results are comparable to human-labeled topics and also the method is applicable to unlabeled text. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1145/1414471.1414556 | ASSETS |
Keywords | Field | DocType |
human-labeled topic,alternative communication device,topic-labeled data,unlabeled text,previous work,basic prediction system,adapting word prediction,word prediction,communication rate,topically inappropriate prediction,subject matter,topic modeling,language modeling,language model | Computer science,Human–computer interaction,Natural language processing,Artificial intelligence,Topic model,Labeled data,Language model,Augmentative and alternative communication | Conference |
Citations | PageRank | References |
1 | 0.36 | 5 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Keith Trnka | 1 | 97 | 7.51 |