Amazon's Mechanical Turk (MTurk) service is becoming increasingly popular in naturallanguageprocessing (NLP) research. In this paper, we report our findings in using MTurk to annotate medical text extracted from...
详细信息
We present a human computation online game for enabling users to contribute to the creation of a corpus of question-resource pairs for harvesting web-based question answering. Our idea was motivated by the popular ...
详细信息
The present article describes fsm2, a software program which can be used interactively or as a script interpreter to manipulate weighted finite-state automata with around 100 different commands. fsm2 is based on FSM ...
详细信息
ISBN:
(纸本)9783642146831
The present article describes fsm2, a software program which can be used interactively or as a script interpreter to manipulate weighted finite-state automata with around 100 different commands. fsm2 is based on FSM < 2.0 > an efficient C++ template library to create and algebraically manipulate weighted automata.
The proceedings contain 125 papers. The topics discussed include: on dual decomposition and linear programming relaxations for naturallanguageprocessing;turbo parsers: dependency parsing by approximate variational i...
ISBN:
(纸本)1932432868
The proceedings contain 125 papers. The topics discussed include: on dual decomposition and linear programming relaxations for naturallanguageprocessing;turbo parsers: dependency parsing by approximate variational inference;jointly modeling aspects and opinions with a MaxEnt-LDA hybrid;handling noisy queries in cross language FAQ retrieval;soft syntactic constraints for hierarchical phrase-based translation using latent syntactic distributions;a hybrid morpheme-word representation for machine translation of morphologically rich languages;joint training and decoding using virtual nodes for cascaded segmentation and tagging tasks;crouching Dirichlet, hidden Markov model: unsupervised POS tagging with context local tag generation;storing the web in memory: space efficient language models with constant time retrieval;automatic discovery of manner relations and its applications;and exploiting conversation structure in unsupervised topic segmentation for emails.
Current markerless 3D registration methods usually utilize a single specified category of natural features. However, the richness of various natural features is ignored. They cannot meet users' diversified registr...
详细信息
There is considerable interest in interdisciplinary combinations of automatic speech recognition (ASR), machine learning, naturallanguageprocessing, text classification and information retrieval. Many of these boxes...
详细信息
This paper proposes a method to model confirmations for example-based dialog management. To enable the system to provide a confirmation to the user in an appropriate time, we employed a multiple dialog state represent...
详细信息
While many visualization tools exist that offer sophisticated functions for charting complex data, they still expect users to possess a high degree of expertise in wielding the tools to create an effective visualizati...
详细信息
ISBN:
(纸本)9783642135439
While many visualization tools exist that offer sophisticated functions for charting complex data, they still expect users to possess a high degree of expertise in wielding the tools to create an effective visualization. This paper presents Articulate, an attempt at a semi-automated visual analytic model that is guided by a conversational user interface to allow users to verbally describe and then manipulate what they want to see. We use naturallanguageprocessing and machine learning methods to translate the imprecise sentences into explicit expressions, and then apply a heuristic graph generation algorithm to create a suitable visualization. The goal is to relieve the user of the burden of having to learn a complex user-interface in order to craft a visualization.
This paper proposes an unsupervised word sense disambiguation method for the biomedical domain. In this paper, a network representation of co-occurrence data is first defined to represent both word senses and word con...
详细信息
In this paper we present algorithms for analysis and generation in a human-machine dialog context. The originality of our approach is to base these two algorithms on the same knowledge. The latter combines both semant...
详细信息
ISBN:
(纸本)9789898425133
In this paper we present algorithms for analysis and generation in a human-machine dialog context. The originality of our approach is to base these two algorithms on the same knowledge. The latter combines both semantic and syntactic aspects. The algorithms are based on a double principle: the correspondence between offers and expectations, and the calculation of a heuristic score. We present also some results obtained by performing an evaluation based on the MEDIA French corpus.
暂无评论