Filters








134,703 Hits in 6.2 sec

A study of statistical models for query translation

Jianfeng Gao, Jian-Yun Nie
2006 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '06  
We begin with a review of a word-based translation model that uses cooccurrence statistics for resolving translation ambiguities.  ...  This paper presents a study of three statistical query translation models that use different units of translation.  ...  Reranking Approach This section describes the reranking approach which is the fundamental modeling framework for both NP and dependency translation models.  ... 
doi:10.1145/1148170.1148207 dblp:conf/sigir/GaoN06 fatcat:lemb54h7ybeuncuwz5ibb5uyi4

Statistical query translation models for cross-language information retrieval

Jianfeng Gao, Jian-Yun Nie, Ming Zhou
2006 ACM Transactions on Asian Language Information Processing  
words and weights for a query.  ...  The co-occurrence model treats a query as a bag of words, and use all the other terms in the query as the context for translation disambiguation.  ...  Huang for useful discussions.  ... 
doi:10.1145/1236181.1236184 fatcat:wyvllatw3bbgfjvdws3ep7gi4i

KenLM: Faster and Smaller Language Model Queries

Kenneth Heafield
2011 Conference on Machine Translation  
We present KenLM, a library that implements two data structures for efficient language model queries, reducing both time and memory costs.  ...  The TRIE data structure is a trie with bit-level packing, sorted records, interpolation search, and optional quantization aimed at lower memory consumption.  ...  Adam Pauls provided a pre-release comparison to BerkeleyLM and an initial Java interface. Nicola Bertoldi and Marcello Federico assisted with IRSTLM. Chris Dyer integrated the code into cdec.  ... 
dblp:conf/wmt/Heafield11 fatcat:gskdwespmbcpvdru6mgzdghhbq

On-the-Fly Translation and Execution of OCL-Like Queries on Simulink Models

Beatriz Sanchez, Athanasios Zolotas, Horacio Hoyos Rodriguez, Dimitris Kolovos, Richard Paige
2019 2019 ACM/IEEE 22nd International Conference on Model Driven Engineering Languages and Systems (MODELS)  
MATLAB/Simulink is a tool for dynamic system modelling.  ...  This approach is expensive as the cost of the transformation can be crippling for large models, it requires the synchronisation of the native Simulink model and its EMF counterpart, and the EMF-representation  ...  In contrast, our approach uses the modelling technology API to translate high-level CRUD operations at model type level on-demand in a similar fashion to other Epsilon bridges such as [20, 35] .  ... 
doi:10.1109/models.2019.000-1 dblp:conf/models/SanchezZRKP19 fatcat:tppdrwecgfgvxoizhu5fp2ym7u

MQT, an Approach for Run-Time Query Translation: From EOL to SQL

Xabier De Carlos, Goiuria Sagardui, Salvador Trujillo
2014 ACM/IEEE International Conference on Model Driven Engineering Languages and Systems  
This paper presents MQT, an approach that translates EOL (model-level queries) to SQL (persistence-level queries) at runtime.  ...  Both are complementary but while model-level queries are closer to modelling engineers, persistence-level queries are specific to the persistence technology and leverage its capabilities.  ...  Dimitris Kolovos for his help on this work. This work is partially supported by the EC, through the Scalable Modelling and Model Management on the Cloud (MONDO) FP7 STREP project (#611125).  ... 
dblp:conf/models/CarlosST14a fatcat:ryy4py5c4za4nita6f6zznmj3a

Text-to-SQL Generation for Question Answering on Electronic Medical Records [article]

Ping Wang, Tian Shi, Chandan K. Reddy
2020 arXiv   pre-print
In this paper, we tackle these challenges by developing a deep learning based TRanslate-Edit Model for Question-to-SQL (TREQS) generation, which adapts the widely used sequence-to-sequence model to directly  ...  However, most of the existing approaches have not been adapted to the healthcare domain due to a lack of healthcare Question-to-SQL dataset for learning models specific to this domain.  ...  large-scale dataset for Question-to-SQL task in healthcare domain.  ... 
arXiv:1908.01839v2 fatcat:7cwr33tcdbd5xhup7jdnsixvxe

Scalable Model Edition, Query and Version Control Through Embedded Database Persistence

Xabier De Carlos, Goiuria Sagardui, Salvador Trujillo
2014 ACM/IEEE International Conference on Model Driven Engineering Languages and Systems  
This approach aims to provide scalability through model edition, querying and versioning mechanisms that leverage database capabilities.  ...  However, to the best of our knowledge there is less coverage of approaches on models persistence which include model querying, versioning and edition capabilities leveraging persistence capabilities.  ...  Fig. 1 : 1 Fig. 1: Model-Level Query Layer, run-time translation from model-level to persistence-level. Fig. 2 : 2 Fig. 2: VCS Integration Layer, differencing and merging for large-scale models.  ... 
dblp:conf/models/CarlosST14 fatcat:yxtpn5old5d63nrkozkvyunnfa

Efficiently querying large-scale heterogeneous models

Qurat ul ain Ali, Dimitris Kolovos, Konstantinos Barmpis
2020 Proceedings of the 23rd ACM/IEEE International Conference on Model Driven Engineering Languages and Systems: Companion Proceedings  
This paper contributes to tackling the challenge of scalable querying of large-scale heterogeneous models for low-code platforms.  ...  In [20] , the authors discuss the challenges of running OCL based queries on relational database-backed models and propose an approach for translating queries written in higher-level query languages (  ...  It is essential to have a query optimization strategy for this scenario so that large-scale models can be queried efficiently.  ... 
doi:10.1145/3417990.3420207 dblp:conf/models/AliKB20 fatcat:rrcbc5drk5fgfg7lrhrpur2fqa

Effective Approaches to Neural Query Language Identification

Xingzhang Ren, Baosong Yang, Dayiheng Liu, Haibo Zhang, Xiaoyu Lv, Liang Yao, Jun Xie
2022 Computational Linguistics  
In order to enhance the discrimination of queries, a variety of external features, e.g. character, word as well as script, are fed into the model and fused by a multi-scale attention mechanism.  ...  Moreover, to remedy the low resource challenge in this task, a novel machine translation based strategy is proposed to automatically generate synthetic query-style data for low-resource languages.  ...  Acknowledgments The authors thank the reviewers for their helpful comments in improving the quality of this work. This work is supported by National Key R&D Program of China (2018YFB1403202).  ... 
doi:10.1162/coli_a_00451 fatcat:tz3oxk6lujehtesnagnnzwpzqe

Cross-language spoken document retrieval using HMM-based retrieval model with multi-scale fusion

Wai-Kit Lo, Helen Meng, P. C. Ching
2003 ACM Transactions on Asian Language Information Processing  
In addition, this HMM-based CLIR retrieval model is also extended for retrieval at subword scales.  ...  The HMM-based retrieval model is a probabilistic formulation for the retrieval problem. Extensions to this retrieval model can be made by taking advantage of its probabilistic nature.  ...  One approach is to obtain maximum likelihood estimates from large corpora.  ... 
doi:10.1145/964161.964162 fatcat:meyid3zxrjglvpf3zm4nn3u2wu

Cross-lingual Information Retrieval with BERT [article]

Zhuolin Jiang, Amro El-Jaroudi, William Hartmann, Damianos Karakos, Lingjun Zhao
2020 arXiv   pre-print
Experimental results of the retrieval of Lithuanian documents against short English queries show that our model is effective and outperforms the competitive baseline approaches.  ...  A deep relevance matching model based on BERT is introduced and trained by finetuning a pretrained multilingual BERT model with weak supervision, using home-made CLIR training data derived from parallel  ...  After finetuning, this model produces a sentence-level relevance score for a pair of input query and foreign language sentence.  ... 
arXiv:2004.13005v1 fatcat:c4wlwr65abekrjljez3bvzipru

Statistical Machine Translation for Query Expansion in Answer Retrieval

Stefan Riezler, Alexander Vasserman, Ioannis Tsochantaridis, Vibhu O. Mittal, Yi Liu
2007 Annual Meeting of the Association for Computational Linguistics  
SMT-based query expansion is done by i) using a full-sentence paraphraser to introduce synonyms in context of the entire query, and ii) by translating query terms into answer terms using a full-sentence  ...  We present an approach to query expansion in answer retrieval that uses Statistical Machine Translation (SMT) techniques to bridge the lexical gap between questions and answers.  ...  Our method for question-answer translation uses a large corpus of question-answer pairs extracted from FAQ pages to learn a translation model from questions to answers.  ... 
dblp:conf/acl/RiezlerVTML07 fatcat:ixaktrrskfcqraia3fxl55aghi

Machine learning for query-document matching in search

Hang Li, Jun Xu
2012 Proceedings of the fifth ACM international conference on Web search and data mining - WSDM '12  
Sense level Topic level Structure level No Transformation Topic Model Dependency Model Latent Space Model Query Reformulation Translation Model Translation Model Translation Model  ...  Translation Model • Matching in Latent Space 33 Relation between Approaches 34 Phrase level Doc Trans.  ...  ., 2003) • Generation process -Word distribution given topic ~Dir -For each document:  ... 
doi:10.1145/2124295.2124393 dblp:conf/wsdm/LiX12 fatcat:ie2hyzulwvd6tayifniys5ih4y

Learning Translational and Knowledge-based Similarities from Relevance Rankings for Cross-Language Retrieval

Shigehiko Schamoni, Felix Hieber, Artem Sokolov, Stefan Riezler
2014 Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
In large-scale experiments for patent prior art search and cross-lingual retrieval in Wikipedia, our approach yields considerable improvements over learningto-rank with either only dense or only sparse  ...  We present an approach to cross-language retrieval that combines dense knowledgebased features and sparse word translations.  ...  Acknowledgments This research was supported in part by DFG grant RI-2221/1-1 "Cross-language Learning-to-Rank for Patent Retrieval".  ... 
doi:10.3115/v1/p14-2080 dblp:conf/acl/SchamoniHSR14 fatcat:fk42avwtpje2pmt76sw276vc7e

Cross-Lingual Learning-to-Rank with Shared Representations

Shota Sasaki, Shuo Sun, Shigehiko Schamoni, Kevin Duh, Kentaro Inui
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)  
We introduce a large-scale dataset derived from Wikipedia to support CLIR research in 25 languages.  ...  This is a challenging problem for data-driven approaches due to the general lack of labeled training data.  ...  Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.  ... 
doi:10.18653/v1/n18-2073 dblp:conf/naacl/SasakiSSDI18 fatcat:mrdjzvlqgnda5bu74vzlg4xwwi
« Previous Showing results 1 — 15 out of 134,703 results