EXCITEMENT -- Exploring Customer Interactions with Textual Entailment
There are two interleaved high-level goals for this project. The first is to set up, for the first time, a generic architecture and a comprehensive implementation for a multilingual textual inference platform and to make it available to the scientific and technological communities. The second goal of the project is to develop a new generation of inference-based industrial text exploration applications for customer interactions, which will enable businesses to better analyze and make sense of their diverse and often unpredicted client content. These goals will be achieved for three languages – English, German and Italian, and for three customer interaction channels – speech (transcriptions), email and social media. This is a EC STREP project undertaken in collaboration with Bar Ilan University, DFKI, FBK, and the companies AlmaWave, NICE, and OMQ.
Linguistically plausible empirical representation of word meaning
This project is centered on a fundamental problem of lexical semantics, the development of linguistically adequate representations of word meaning. Methodically, it aims at interleaving linguistic, computational (corpus-based) and cognitive approaches to word meaning. Its overarching aim is to develop linguistically plausible feature-based representations for word meaning in context. This is a TransCoop collaboration project with Katrin Erk, UT Austin.
Lexical-semantic factors in event interpretation (Stuttgart, SFB 732)
This project is concerned with a particular phenomenon of incremental specification in context, namely the interpretation of verb-object pairs. While some verb-object pairs are interpreted compositionally ("simple composition", as in begin a holiday), the understanding of others involves covert events that are not realised on the surface ("enriched composition": for example, begin a song, in neutral context, implies begin singing a song).
Semantics beyond the sentence: Coherence in language processing
The goal of the doctoral program is to extend semantic analysis to the discourse level and to approximate coherence-based interpretation through three mutually supporting research directions: (a) analysing semantic phenomena at the discourse level and representing them as “semantic graphs”; (b) using these graphs to improve semantic analysis; (c) evaluating (a) and (b) in NLP applications. The proposed PhD topics are integrated into and linked by the three directions. Further ties are ensured by the joint use of text collections (corpora).