Let's do it "again": A First Computational Approach to Detecting Adverbial Presupposition Triggers
This work addresses a specific linguistic challenge for natural language processing applications such as summarization and dialogue systems, representing an incremental advancement in the field.
The paper tackles the problem of detecting adverbial presupposition triggers like 'also' and 'again' in text, which involves identifying recurring or similar events in discourse, and introduces a novel attention mechanism that statistically outperforms baselines, including an LSTM-based language model, on two new datasets derived from the Penn Treebank and Annotated English Gigaword corpora.
We introduce the task of predicting adverbial presupposition triggers such as also and again. Solving such a task requires detecting recurring or similar events in the discourse context, and has applications in natural language generation tasks such as summarization and dialogue systems. We create two new datasets for the task, derived from the Penn Treebank and the Annotated English Gigaword corpora, as well as a novel attention mechanism tailored to this task. Our attention mechanism augments a baseline recurrent neural network without the need for additional trainable parameters, minimizing the added computational cost of our mechanism. We demonstrate that our model statistically outperforms a number of baselines, including an LSTM-based language model.