Search

Current information retrieval (IR) approaches do not formally capture the explicit meaning of a keyword query but provide a comfortable way for the user to specify information needs on the basis of keywords. Ontology-based approaches allow for sophisticated semantic search but impose a query syntax more difficult to handle. In this paper, we present an approach for translating keyword queries to DL conjunctive queries using background knowledge available in ontologies. We present an implementation which shows that this interpretation of keywords can then be used for both exploration of asserted knowledge and for a semantics-based declarative query answering process. We also present an evaluation of our system and a discussion of the limitations of the approach with respect to our underlying assumptions which directly points to issues for future work.

En este artículo se consideran los problemas de la transferncia lexical de pronombres y la resolución anafórica en la traducción automática (TA), sobretodo desde el punto de vista de la traducción inglés-coreano. Después de introducir el problema general de la transferencia léxica, los autores argumentan la necesidad de la resolución anafórica en la traducción inglés-coreano, describen brevemente su sistema de TA y proponen reglas prácticas para la transferencia lexical de pronombres. Finalmente, se presenta un modelo de resolución anafórica que se realizará en el sistema de traducción automática. There have been various results in English-to-Korean Machine Translation reported, but so far no attention has been paid to the problems of lexical transfer of pronominal anaphors and/or resolving pronominal reference and a default pronoun translation has been considered instead. In this paper we argue that pronouns cannot be handled trivially in English-to-Korean translation and one cannot bypass the task of resolving anaphoric reference if aiming at good and natural translation. In addition, we propose practical transfer rules for English-to-Korean anaphora translation and outline an anaphora resolution model for an English-to-Korean MT system in operation.

This paper seeks to improve the performance of automatic speech recognition (ASR) systems operating on code-switched speech. Code-switching refers to the alternation of languages within a conversation, a phenomenon that is of increasing importance considering the rapid rise in the number of bilingual speakers in the world. It is particularly challenging for ASR owing to the relative scarcity of code-switching speech and text data, even when the individual languages are themselves well-resourced. This paper proposes to overcome this challenge by applying linguistic theories in order to generate more realistic code-switching text, necessary for language modelling in ASR. Working with English-Spanish code-switching, we find that Equivalence Constraint theory and part-of-speech labelling are particularly helpful for text generation, and bring 2% improvement to ASR performance.

Graph embedding models produce embedding vectors for entities and relations in Knowledge Graphs, often without taking literal properties into account. We show an initial idea based on the combination of global graph structure with additional information provided by textual information in properties. Our initial experiment shows that this approach might be useful, but does not clearly outperform earlier approaches when evaluated on machine learning tasks., Comment: Presented at the 4th Workshop on Semantic Deep Learning (SemDeep-4)

This paper presents ProphetMT, a monolingual Controlled Language (CL) authoring tool which allows users to easily compose an in-domain sentence with the help of tree-based SMT-driven auto-suggestions. The interface also visualizes target-language sentences as they are built by the SMT system. When the user is finished composing, the final translation(s) are generated by a tree-based SMT system using the text and structural information provided by the user. With this domain-specific controlled language, ProphetMT will produce highly reliable translations. The contributions of this work are: 1) we develop a user-friendly auto-completion-based editor which guarantees that the vocabulary and grammar chosen by a user are compatible with a tree-based SMT model; 2) by applying a shift-reduce-like parsing feature, this editor allows users to write from left-to-right and generates the parsing results on the fly. Accordingly, with this in-domain composing restriction as well as the gold-standard parsing result, a highly reliable translation can be generated.