Filters








7 Hits in 1.9 sec

Maxprob and categorization of queries based on linguistic features

Desire Kompaore, Josiane Mothe
2007 Proceedings of the ACM first Ph.D. workshop in CIKM on - PIKM '07  
Our fusing technique is based on queries that are classified using some automatically extracted linguistic features [11] .  ...  The rank list of relevant documents provided by the systems are divided into segments and used in a training/testing process to detect the systems to fuse.  ...  The selection is based on clusters of queries that take into account variability and homogeneity in query features.  ... 
doi:10.1145/1316874.1316885 dblp:conf/cikm/KompaoreM07 fatcat:puzats57hrhzpmwxkgoznjr2wy

TFW, DamnGina, Juvie, and Hotsie-Totsie: On the Linguistic and Social Aspects of Internet Slang [article]

Vivek Kulkarni, William Yang Wang
2017 arXiv   pre-print
In this work, we use UrbanDictionary to conduct the first large-scale linguistic analysis of slang and its social aspects on the Internet to yield insights into this variety of language that is increasingly  ...  Analyzing tens of thousands of such slang words reveals that the majority of slang on the Internet belongs to two major categories: sex and drugs.  ...  Furthermore the model using character-ngram features significantly outperforms the morpheme based model.  ... 
arXiv:1712.08291v1 fatcat:d5atsrawsrczpdgtmgwice5esu

Type- and Content-Driven Synthesis of SQL Queries from Natural Language [article]

Navid Yaghmazadeh, Yuepeng Wang, Isil Dillig, Thomas Dillig
2017 arXiv   pre-print
We have implemented the proposed technique in a tool called Sqlizer and evaluate it on three different databases.  ...  Our experiments show that the desired query is ranked within the top 5 candidates in close to 90% of the cases.  ...  well across multiple databases and outperforms a state-of-the-art NLIDB system.  ... 
arXiv:1702.01168v1 fatcat:r6i3h7f3enaz7javsf7754kblm

SQLizer: query synthesis from natural language

Navid Yaghmazadeh, Yuepeng Wang, Isil Dillig, Thomas Dillig
2017 Proceedings of the ACM on Programming Languages  
We evaluate our approach on over 450 natural language queries concerning three different databases, namely MAS, IMDB, and YELP.  ...  At the core of our technique is a new NL-based program synthesis methodology that combines semantic parsing techniques from the NLP community with type-directed program synthesis and automated program  ...  This material is based on research sponsored by DARPA under agreement number #8750-14-2-0270. The U.S.  ... 
doi:10.1145/3133887 dblp:journals/pacmpl/Yaghmazadeh0DD17 fatcat:vlqlptvygbbijhvcibq5j5tlk4

Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering [article]

Siddhant Garg, Alessandro Moschitti
2021 arXiv   pre-print
Our experiments on three popular QA datasets and one industrial QA benchmark demonstrate the ability of our question models to approximate the Precision/Recall curves of the target QA system well.  ...  This is based on an interesting new finding: the answer confidence scores of state-of-the-art QA systems can be approximated well by models solely using the input question text.  ...  Acknowledgements We thank the anonymous reviewers and metareviewer for their valuable suggestions. We thank Thuy Vu for developing and sharing the human annotated data used in the AQAD dataset.  ... 
arXiv:2109.07009v1 fatcat:a2tg34evkrdnjjjdakvqng2q3i

Automated synthesis of data extraction and transformation programs [article]

Navid Yaghmazadeh
2017
This score is calculated based on a set of pre-defined features.  ...  To assess how Sqlizer performs on different classes of queries, we manually categorize the benchmarks into four groups based on the characteristics of their corresponding SQL query.  ...  For example, we experiments on 455 queries from three different databases shows that Sqlizer ranks the desired query as top one in 78% of the cases and among top 5 in ∼ 90% of the time.  ... 
doi:10.15781/t2zk56545 fatcat:guknbbfyfnacnmgfxvs2gqcamu

Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering

Siddhant Garg, Alessandro Moschitti
2021 Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing   unpublished
Our experiments on three popular QA datasets and one industrial QA benchmark demonstrate the ability of our question models to approximate the Precision/Recall curves of the target QA system well.  ...  This is based on an interesting new finding: the answer confidence scores of state-of-the-art QA systems can be approximated well by models solely using the input question text.  ...  Acknowledgements We thank the anonymous reviewers and metareviewer for their valuable suggestions. We thank Thuy Vu for developing and sharing the human annotated data used in the AQAD dataset.  ... 
doi:10.18653/v1/2021.emnlp-main.583 fatcat:ltajh5krtbfybjnntyerlvqpsy