We have developed SummaryBIFF, a new e-mail delivery system for mobile phones that sends a summary of each newly arrived message and the URL connected to the HTML file converted from the message. The summary is generated by our sentence extraction method that takes the features of e-mail messages for business use into consideration. Our method uses the features as cue phrases and modalities tha...

This paper describes our approach to the 2016 QATS quality assessment shared task. We trained three independent Random Forest classifiers in order to assess the quality of the simplified texts in terms of grammaticality, meaning preservation and simplicity. We used the language model of Google-Ngram as feature to predict the grammaticality. Meaning preservation is predicted using two complement...

Humans produce speech incrementally and on-line as the dialogue progresses using information from several different sources in parallel. A dialogue system that generates output in a stepwise manner and not in preplanned syntactically correct sentences needs to signal how new dialogue contributions relate to previous discourse. This paper describes a data collection which is the foundation for a...

The TNO system for multi-document summarisation is based on an extraction approach. For headline generation, we chose to extend our system to extract the most informative topical noun phrase. The cluster topic is defined as the most frequent term occurring in the most salient document sentences. The core of our system is a probabilistic model, which estimates the log-odds of salience based on a...

We present recent work in the area of Cross-Domain Dialogue Act (DA) tagging. We have previously reported on the use of a simple dialogue act classifier based on purely intra-utterance features — principally involving word n-gram cue phrases automatically generated from a training corpus. Such a classifier performs surprisingly well, rivalling scores obtained using far more sophisticated langua...

This paper presents a system for automatically generating discourse structures from written text. The system is divided into two levels: sentence-level and text-level. The sentence-level discourse parser uses syntactic information and cue phrases to segment sentences into elementary discourse units and to generate discourse structures of sentences. At the text-level, constraints about textual a...

We present recent work in the area of Dialogue Act (DA) tagging. Identifying the dialogue acts of utterances is recognised as an important step towards understanding the content and nature of what speakers say. Our experiments investigate the use of a simple dialogue act classifier based on purely intra-utterance features — principally involving word n-gram cue phrases. Such a classifier perfor...

Using the RST annotated corpus (Carlson et al., 2003), we use simple statistics on the distribution of discourse markers or cue phrases as evidence of the three-way distinction of Contrast relations, Contrast, Antithesis and Concession, recognized in standard Rhetorical Structure Theory (RST, Mann & Thompson 1987). We also show that however, an intuitive marker of Contrast, is not actually used...

We here explore a “fully” lexicalized Tree-Adjoining Grammar for discourse that takes the basic elements of a (monologic) discourse to be not simply clauses, but larger structures that are anchored on variously realized discourse cues. This link with intra-sentential grammar suggests an account for different patterns of discourse cues, while the different structures and operations suggest three...