Abstract | This is the problem of domain adaptation . |
Abstract | The empirical evaluation on ACE 2005 domains shows that a suitable combination of syntax and lexical generalization is very promising for domain adaptation . |
Introduction | This is the problem of domain adaptation (DA) or transfer learning (TL). |
Introduction | Technically, domain adaptation addresses the problem of leam-ing when the assumption of independent and identically distributed (i.i.d.) |
Introduction | Domain adaptation has been studied extensively during the last couple of years for various NLP tasks, e.g. |
Conclusions and Future Work | Many other domain adaptations techniques exist and may produce language models with better performance. |
Language Model Evaluation: Perplexity | This approach has the benefit of simplicity, however, better performance for combining related corpora has been seen by domain adaptation techniques which combine the data in more structured ways (Bacchiani and Roark, 2003). |
Language Model Evaluation: Perplexity | Our goal for this paper is not to explore domain adaptation techniques, but to determine if normal data is useful for the simple language modeling task. |
Language Model Evaluation: Perplexity | if domain adaptation techniques may be useful, we also investigated a linearly interpolated language model. |
Related Work | If we view the normal data as out-of-domain data, then the problem of combining simple and normal data is similar to the language model domain adaption problem (Suzuki and Gao, 2005), in particular cross-domain adaptation (Bellegarda, 2004) where a domain-specific model is improved by incorporating additional general data. |
Related Work | guage model domain adaptation problem for text simplification. |
Related Work | Pan and Yang (2010) provide a survey on the related problem of domain adaptation for machine learning (also referred to as “transfer learning”), which utilizes similar techniques. |
Abstract | While domain adaptation techniques for SMT have proven to be effective at improving translation quality, their practicality for a multi-domain environment is often limited because of the computational and human costs of developing and maintaining multiple systems adapted to different domains. |
Introduction | The effectiveness of domain adaptation approaches such as mixture-modeling (Foster and Kuhn, 2007) has been established, and has led to research on a wide array of adaptation techniques in SMT, for instance (Matsoukas et al., 2009; Shah et al., 2012). |
Introduction | Therefore, when working with multiple and/or unlabelled domains, domain adaptation is often impractical for a number of reasons. |
Introduction | Secondly, domain adaptation bears a risk of performance loss. |
Translation Model Architecture | Our immediate purpose for this paper is domain adaptation in a multi-domain environment, but the delay of the feature computation has other potential applications, e.g. |
Translation Model Architecture | The goal is to perform domain adaptation without requiring domain labels or user input, neither for development nor decoding. |
Translation Model Architecture | Our theoretical expectation is that domain adaptation will fail to perform well if the test data is from |
Experiment | Even the performance of the pialign-linear is better than the Baseline GIZA-linear’s, which means that phrase pair extraction with hierarchical phrasal ITGs and sampling is more suitable for domain adaptation tasks than the combination GIZA++ and a heuristic method. |
Hierarchical Phrase Table Combination | In traditional domain adaptation approaches, phrase pairs are extracted together with their probabilities and/or frequencies so that the extracted phrase pairs are merged uniformly or after scaling. |
Introduction | Traditional domain adaption methods for SMT are also not adequate in this scenario. |
Related Work | A number of approaches have been proposed to make use of the full potential of the available parallel sentences from various domains, such as domain adaptation and incremental learning for SMT. |
Related Work | In the case of the previous work on translation modeling, mixed methods have been investigated for domain adaptation in SMT by adding domain information as additional labels to the original phrase table (Foster and Kuhn, 2007). |
Related Work | As a way to choose the right domain for the domain adaption , a classifier-based method and a feature-based method have been proposed. |
Abstract | We apply our method for the domain adaptation task and the extensive experiments show that our proposed method can substantially improve the translation quality. |
Conclusion and Future Work | Extensive experiments on domain adaptation have shown that our method can significantly outperform previous methods which also focus on exploring the in-domain lexicon and monolingual data. |
Experiments | Our purpose is to induce phrase pairs to improve translation quality for domain adaptation . |
Introduction | Finally, they used the learned translation model directly to translate unseen data (Ravi and Knight, 2011; Nuhn et al., 2012) or incorporated the learned bilingual lexicon as a new in-domain translation resource into the phrase-based model which is trained with out-of-domain data to improve the domain adaptation performance in machine translation (Dou and Knight, 2012). |
Introduction | The induced phrase-based model will be used to help domain adaptation for machine translation. |
Introduction | Section 6 will show the detailed experiments for the task of domain adaptation . |
Probabilistic Bilingual Lexicon Acquisition | In order to induce the phrase pairs from the in-domain monolingual data for domain adaptation , the probabilistic bilingual lexicon is essential. |
Abstract | This paper proposes a new approach to domain adaptation in statistical machine translation (SMT) based on a vector space model (VSM). |
Introduction | Domain adaptation is an active topic in the natural language processing (NLP) research community. |
Introduction | The 2012 JHU workshop on Domain Adaptation for MT 1 proposed phrase sense disambiguation (PSD) for translation model adaptation. |
Introduction | In this paper, we propose a new instance weighting approach to domain adaptation based on a vector space model (VSM). |
Experiments | This causes data-mismatch issues and hence provides a perfect testbed for a domain adaptation task. |
Experiments | To evaluate the domain adaptation (DA) approach and to compare with results reported by (Subramanya et al., 2010), we use the first and second half of QuestionBank (Judge et al., 2006) as our development and test sets (target). |
Experiments | 5.3.2 Experiment 2: Domain Adaptation Task. |
Conclusion and Future Work | Our strategy, therefore, enables us to build a classifier more domain adaptive and up to date. |
Experiments | The classifier performs much worse on the domains of chemistry, physics and machinery, it indicates the importance of domain adaptation for word segmentation (Gao et al., 2004; Ma and Way, 2009; Gao et al., 2010). |
Experiments | What is more, since the text on Internet is wide-coveraged and real-time updated, our strategy also helps a word segmenter be more domain adaptive and up to date. |
Learning with Natural Annotations | It probably provides a simple and effective domain adaptation strategy for already trained models. |
Abstract | Additionally, we design a cus-tomizable framework to address the often overlooked concept of domain adaptability , and illustrate that the system allows for transfer to new domains with a minimal amount of data and effort. |
Conclusions | This work presents a framework for normalization with an eye towards domain adaptation . |
Evaluation | The goal is to evaluate the framework in two aspects: (1) usefulness for downstream applications (specifically dependency parsing), and (2) domain adaptability . |
Related Work | Similarly, our work is the first to prioritize domain adaptation during the new wave of text message normalization. |
Analysis | 5.2 Domain Adaptation Analysis |
Analysis | To understand the domain adaptation issue we compared the nonzero weights in the discriminative phrase table (PT) for Ar—En models tuned on bitext5k and MT05/6/ 8. |
Introduction | Second, large bitexts often comprise many text genres (Haddow and Koehn, 2012), a virtue for classical dense MT models but a curse for high dimensional models: bitext tuning can lead to a significant domain adaptation problem when evaluating on standard test sets. |
Introduction | ), we also make initial tries for domain adaptation so that our summarization method does not need human-written abstracts for each new meeting domain (e.g. |
Results | Domain Adaptation Evaluation. |
Results | We further examine our system in domain adaptation scenarios for decision and problem summarization, where we train the system on AMI for use on ICSI, and vice versa. |