Alicia Tribble

Domain portability in speech-to-speech translation

Speech-to-speech translation has made significant advances over the past decade, with several high-visibility projects (C-STAR, Verb-mobil, the Spoken Language Translator, and others) significantly advancing the state-of-the-art. While speech recognition can currently effectively deal with very large vocabularies and is fairly speaker independent, speech translation is currently still effective only in limited, albeit large, domains. The issue of domain portability is thus of significant importance, with several current research efforts designed to develop speech-translation systems that can be ported to new domains with significantly less time and effort than is currently possible.

Improvements in non-verbal cue identification using multilingual phone strings

Todays state-of-the-art front-ends for multilingual speech-to-speech translation systems apply monolingual speech recognizers trained for a single language and/or accent. The monolingual speech engine is usually adaptable to an unknown speaker over time using unsupervised training methods; however, if the speaker was seen during training, their specialized acoustic model will be applied, since it achieves better performance. In order to make full use of specialized acoustic models in this proposed scenario, it is necessary to automatically identify the speaker with high accuracy. Furthermore, monolingual speech recognizers currently rely on the fact that language and/or accent will be selected beforehand by the user. This requires the users cooperation and an interface which easily allows for such selection. Both requirements are awkward and error-prone, especially when translation services are provided for many languages using small devices like PDAs or telephones. For these scenarios, front-ends are desired which automatically identify the spoken language or accent. We believe that the automatic identification of an utterances non-verbal cues, such as language, accent and speaker, are necessary to the successful deployment of speech-to-speech translation systems.

Overlapping phrase-level translation rules in an SMT engine

We explore a technique for adding longer phrase translation pairs to a statistical machine translation (SMT) system. Merging existing phrase-level alignments that have overlapping words on both the source and target sides generates new phrases. The effect on translation quality is reported for an Arabic-English system in the news domain.

CMU-AT: Semantic Distance and Background Knowledge for Identifying Semantic Relations

This system uses a background knowledge base to identify semantic relations between base noun phrases in English text, as evaluated in SemEval 2007, Task 4. Training data for each relation is converted to statements in the Scone Knowledge Representation Language. At testing time a new Scone statement is created for the sentence under scrutiny, and presence or absence of a relation is calculated by comparing the total semantic distance between the new statement and all positive examples to the total distance between the new statement and all negative examples.

Usable browsers for ontological knowledge acquisition

In this paper we compare the usability of several presentation formats for ontological knowledge of events. The goal is to support further work in knowledge acquisition from informants who are not necessarily experienced with knowledge representations. This work investigates the question: How can we present detailed ontological information to such informants, in a format that is easy to understand, modify, and augment? We compare three formats: two commonly-used diagram styles and one lisp-like list of knowledge axioms. Ongoing work on this topic will expand the investigation into a study of the role of natural language in knowledge acquisition.

SconeEdit: A Text-guided Domain Knowledge Editor

We will demonstrate SconeEdit, a new tool for exploring and editing knowledge bases (KBs) that leverages interaction with domain texts. The tool provides an annotated view of user-selected text, allowing a user to see which concepts from the text are in the KB and to edit the KB directly from this Text View. Alongside the Text View, SconeEdit provides a navigable KB View of the knowledge base, centered on concepts that appear in the text. This unified tool gives the user a text-driven way to explore a KB and add new knowledge.