Panelist: Marie-Catherine de Marneffe
Title: Uphill battle: Drawing inferences

Extracting information that is expressed without actually being said remains an uphill battle for NLP. The problem is complex, as illustrated in (1) and (2). We want to derive that people will generally take that it is war from (1), but will take that relocating species threatened by climate is not a panacea from (2), even though both events are embedded under (s)he doesn’t believe.
(1) The problem, I’m afraid, with my colleague here, he really doesn’t believe that it’s war.

(2)  Transplanting an ecosystem can be risky, as history shows. Hellmann doesn’t believe that relocating species threatened by climate change is a panacea. 

Automatically extracting systematic inferences of that kind is fundamental to a range of NLP tasks, including information extraction, opinion detection, and textual entailment. But surprisingly, at present the vast majority of information extraction systems work at the clause level and regard any event they find as true without taking into account the context in which the event appears in the sentence.

Echoing Martin Kay’s invited talk at Coling 2014 “Does a Computational Linguist have to be a Linguist?” where he argued that the long-term development of automatic language processing requires linguistic theory on top of sophisticated statistical manipulation of big data, my talk aims at illustrating how linguistically-motivated features, conjoined with surface-level ones, can enable progress in achieving robust text understanding. What changed from the early age of NLP is access to much more data and annotations from which we can learn models that incorporate both types of features.