Recognizing semantic frames using neural networks and distributional word representations

This paper reports the results of a series of experiments into recognizing semantic frames and frame elements using neural networks and measuring the added benefit of embedding large-scale co-occurrence information about words during the process. Frame recognition is carried out using Elman-type recurrent neural networks to give the system short-term memory of previous words within the sentence. Long-term memory is implemented in the system of weighted links between neurons. We test 9 wordrepresentation methods including predict- and count-type distributional representations. We show that distributional word representations, which provide the frame recognizer with access to unlabelled co-occurrence information about every word, perform noticeably better than nondistributional techniques. Frame recognition F-score increased from 0.76 to 0.89, and frame element recognition - a considerably more difficult task - also benefited from the added information: we see an F-score increase from 0.46 to 0.53. We also show that this task is less sensitive to the particularities of collecting word distribution information than the known benchmark experiments.