Towards Automatic Dialogue Understanding

In this paper we will present work carried out to scale up the system for text understanding called GETARUNS, and port it to be used in dialogue understanding. The current goal is that of extracting automatically argumentative information in order to build argumentative structure. The long term goal is using argumentative structure to produce automatic summarization of spoken dialogues. Very much like other deep linguistic processing systems (see Allen et al, 2007), our system is a generic text/dialogue understanding system that can be used in connection with an ontology – WordNet – and other similar repositories of commonsense knowledge. Word sense disambiguation takes place at the level of semantic interpretation and is represented in the Discourse Model. We will present the adjustments we made in order to cope with transcribed spoken dialogues like those produced in the ICSI Berkely project. The low level component is organized according to LFG theory; at this level, the system does pronominal binding, quantifier raising and temporal interpretation. The high level component is where the Discourse Model is created from the Logical Form. For longer sentences the system switches from the top-down to the bottom-up system. In case of failure it will back off to the partial system which produces a very lean and shallow semantics with no inference rules. In a final section, we present preliminary evaluation of the system on two tasks: the task of automatic argumentative labelling and another frequently addressed task: referential vs. non-referential pronominal detection. Results obtained fair much higher than those reported in similar experiments with machine learning approaches.