Lightly-Supervised Word Sense Translation Error Detection for an Interactive Conversational Spoken Language Translation System
نویسندگان
چکیده
Lexical ambiguity can lead to concept transfer failure in conversational spoken language translation (CSLT) systems. This paper presents a novel, classificationbased approach to accurately detecting word sense translation errors (WSTEs) of ambiguous source words. The approach requires minimal human annotation effort, and can be easily scaled to new language pairs and domains, with only a wordaligned parallel corpus and a small set of manual translation judgments. We show that this approach is highly precise in detecting WSTEs, even in highly skewed data, making it practical for use in an interactive CSLT system.
منابع مشابه
Semi-Supervised Word Sense Disambiguation for Mixed-Initiative Conversational Spoken Language Translation
Lexical ambiguity can cause critical failure in conversational spoken language translation (CSLT) systems due to the wrong sense being presented in the target language. In this paper, we present a framework for improving translation of ambiguous source words that (a) constrains statistical machine translation (SMT) decoding with phrase pair clusters to select a desired sense for translation; (b...
متن کاملSource-Error Aware Phrase-Based Decoding for Robust Conversational Spoken Language Translation
Spoken language translation (SLT) systems typically follow a pipeline architecture, in which the best automatic speech recognition (ASR) hypothesis of an input utterance is fed into a statistical machine translation (SMT) system. Conversational speech often generates unrecoverable ASR errors owing to its rich vocabulary (e.g. out-of-vocabulary (OOV) named entities). In this paper, we study the ...
متن کاملA language model for conversational speech recognition using information designed for speech translation
In this paper, a new language model is proposed for speech recognition in conversational speech translation. In conversation, speech strongly depends on the previous utterance of the other participant. Applying this dependency in language modeling, we can reduce the speech recognition error rate. To this end, we propose the following new language model where the content of the previous utteranc...
متن کاملتصحیح خودکار خطا در درخت بانک نحوی با استفاده از یادگیری ماشینی انتقال محور
The Treebank is one of the most useful resources for supervised or semi-supervised learning in many NLP tasks such as speech recognition, spoken language systems, parsing and machine translation. Treebank can be developded in different ways that could be, generally, categorized in manually and statistical approaches. While the resulted Treebank in each of these methods has the annotation error,...
متن کاملTowards A Hybrid Approach To Word-Sense Disambiguation In Machine Translation
The task of word sense disambiguation aims to select the correct sense of a polysemous word in a given context. When applied to machine translation, the correct translation in the target language must be selected for a polysemous lexical item in the source language. In this paper, we present work in progress on a supervised WSD system with a hybrid approach: on the one hand it relies on supervi...
متن کامل