LAUSR

Previous answer aggregation methods for sentence-level crowdsourcing tasks extract one sentence from a collection of redundant sentences. However, these extractive methods have a drawback in that they ignore the phenomenon of answer complementarity and the spammer dilemma in crowdsourcing. To alleviate this problem, in this paper, we generate new, comprehensive sentences that synthesize all redundant sentences. To achieve this goal, we design a sequence-to-sequence neural model composed of an encoder and decoder. Specifically, considering the complementarity phenomenon, the encoder synthesizes all the collected sentences into hidden states, which are then utilized by the decoder to generate the final sentence. Next, considering the spammer dilemma, we model the workers in the neural network to detect spammers. Furthermore, to train the neural model better, we construct pseudo-sentences to enrich the training data. The experimental results demonstrate that our method can efficiently aggregate redundant sentences and generate comprehensive sentences with increased quality.