This paper presents a method to develop a class of variable memory Markov models that have higher memory capacity than traditional (uniform memory) Markov models. The structure of...
Ordering information is a critical task for natural language generation applications. In this paper we propose an approach to information ordering that is particularly suited for ...
Kernel-based learning (e.g., Support Vector Machines) has been successfully applied to many hard problems in Natural Language Processing (NLP). In NLP, although feature combinatio...
It is well known that occurrence counts of words in documents are often modeled poorly by standard distributions like the binomial or Poisson. Observed counts vary more than simpl...
When rules of transfer-based machine translation (MT) are automatically acquired from bilingual corpora, incorrect/redundant rules are generated due to acquisition errors or trans...
The model used by the CCG parser of Hockenmaier and Steedman (2002b) would fail to capture the correct bilexical dependencies in a language with freer word order, such as Dutch. T...
This paper concerns the discourse understanding process in spoken dialogue systems. This process enables the system to understand user utterances based on the context of a dialogu...
Many applications of natural language processing technologies involve analyzing texts that concern the psychological states and processes of people, including their beliefs, goals...
Andrew Gordon, Abe Kazemzadeh, Anish Nair, Milena ...
We augment a model of translation based on re-ordering nodes in syntactic trees in order to allow alignments not conforming to the original tree structure, while keeping computati...
This paper presents a dependency language model (DLM) that captures linguistic constraints via a dependency structure, i.e., a set of probabilistic dependencies that express the r...