1 |
Analysis and Insights from the PARSEME Shared Task dataset ; Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Semantic reranking of CRF label sequences for verbal multiword expression identification ; Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop
|
|
|
|
BASE
|
|
Show details
|
|
3 |
An empirical study of segment prioritization for incrementally retrained post-editing-based SMT
|
|
|
|
In: Du, Jinhua orcid:0000-0002-3267-4881 , Ankit, Srivastava, Way, Andy orcid:0000-0001-5736-5930 , Maldonado Guerra, Alfredo orcid:0000-0001-8426-5249 and Lewis, David orcid:0000-0002-3503-4644 (2015) An empirical study of segment prioritization for incrementally retrained post-editing-based SMT. In: The Fifteenth MT Summit Conference, 30 Oct-3 Nov 2015, Miami, FL, USA. (2015)
|
|
BASE
|
|
Show details
|
|
4 |
Linear transformations of semantic spaces for word-sense discrimination and collocation compositionality grading
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Multi-word expression-sensitive word alignment
|
|
|
|
In: Okita, Tsuyoshi, Maldonado Guerra, Alfredo orcid:0000-0001-8426-5249 , Graham, Yvette and Way, Andy orcid:0000-0001-5736-5930 (2010) Multi-word expression-sensitive word alignment. In: CLIA 2010 - Fourth International Workshop On Cross Lingual Information Access: Computational Linguistics and the Information Need of Multilingual Societies, 28 Augt 2010, Beijing, China. (2010)
|
|
Abstract:
This paper presents a new word alignment method which incorporates knowledge about Bilingual Multi-Word Expressions (BMWEs). Our method of word alignment first extracts such BMWEs in a bidirectional way for a given corpus and then starts conventional word alignment, considering the properties of BMWEs in their grouping as well as their alignment links. We give partial annotation of alignment links as prior knowledge to the word alignment process; by replacing the maximum likelihood estimate in the M-step of the IBM Models with the Maximum A Posteriori (MAP) estimate, prior knowledge about BMWEs is embedded in the prior in this MAP estimate. In our experiments, we saw an improvement of 0.77 Bleu points absolute in JP–EN. Except for one case, our method gave better results than the method using only BMWEs grouping. Even though this paper does not directly address the issues in Cross-Lingual Information Retrieval (CLIR), it discusses an approach of direct relevance to the field. This approach could be viewed as the opposite of current trends in CLIR on semantic space that incorporate a notion of order in the bag-of-words model (e.g. co-occurences).
|
|
Keyword:
Machine translating
|
|
URL: http://doras.dcu.ie/15801/
|
|
BASE
|
|
Hide details
|
|
|
|