Conjunct Resolution in the Face of Verbal Omissions
This work addresses the challenge of verbal omissions in natural language processing, which is crucial for accurate sentence interpretation, though it is incremental as it builds on prior limited datasets and methods.
The paper tackles the problem of recovering omitted verbs and arguments in VP coordination structures, a task where state-of-the-art models struggle, by proposing a conjunct resolution task and curating a large dataset of over 10K naturally-occurring examples with crowd-sourced annotations, showing that their best method achieves decent performance but leaves room for improvement.
Verbal omissions are complex syntactic phenomena in VP coordination structures. They occur when verbs and (some of) their arguments are omitted from subsequent clauses after being explicitly stated in an initial clause. Recovering these omitted elements is necessary for accurate interpretation of the sentence, and while humans easily and intuitively fill in the missing information, state-of-the-art models continue to struggle with this task. Previous work is limited to small-scale datasets, synthetic data creation methods, and to resolution methods in the dependency-graph level. In this work we propose a conjunct resolution task that operates directly on the text and makes use of a split-and-rephrase paradigm in order to recover the missing elements in the coordination structure. To this end, we first formulate a pragmatic framework of verbal omissions which describes the different types of omissions, and develop an automatic scalable collection method. Based on this method, we curate a large dataset, containing over 10K examples of naturally-occurring verbal omissions with crowd-sourced annotations of the resolved conjuncts. We train various neural baselines for this task, and show that while our best method obtains decent performance, it leaves ample space for improvement. We propose our dataset, metrics and models as a starting point for future research on this topic.