Index of papers in Proc. ACL 2013 that mention
  • labeled data
Lucas, Michael and Downey, Doug
Abstract
SSL techniques are often effective in text classification, where labeled data is scarce but large unlabeled corpora are readily available.
Introduction
Semi-supervised Learning (SSL) is a Machine Learning (ML) approach that utilizes large amounts of unlabeled data, combined with a smaller amount of labeled data , to learn a target function (Zhu, 2006; Chapelle et al., 2006).
Introduction
Then, for a given target class and labeled data set, we utilize the statistics to improve a classifier.
Introduction
The marginal statistics are used as a constraint to improve the class-conditional probability estimates P (w | +) and P (w | —) for the positive and negative classes, which are often noisy when estimated over sparse labeled data sets.
Problem Definition
In particular, SFE uses the equality P(+|w) = P(+, and estimates the rhs using P computed over all the unlabeled data, rather than using only labeled data as in standard MNB.
Problem Definition
Further, it can be shown that as P(w) of a word 21) in the unlabeled data becomes larger than that in the labeled data , SFE’s estimate of the ratio P(w|+) /P(w|—) approaches one.
Problem Definition
Depending on the labeled data , such an estimate can be arbitrarily inaccurate.
labeled data is mentioned in 10 sentences in this paper.
Topics mentioned in this paper:
Celikyilmaz, Asli and Hakkani-Tur, Dilek and Tur, Gokhan and Sarikaya, Ruhi
Abstract
Finding concepts in natural language utterances is a challenging task, especially given the scarcity of labeled data for learning semantic ambiguity.
Experiments
First a supervised learning algorithm is used to build a CRF model based on the labeled data .
Introduction
Thus, each latent semantic class corresponds to one of the semantic tags found in labeled data .
Markov Topic Regression - MTR
We assume a fixed K topics corresponding to semantic tags of labeled data .
Markov Topic Regression - MTR
K latent topics to the K semantic tags of our labeled data .
Markov Topic Regression - MTR
labeled data , 712?, based on the log-linear model in Eq.
Semi-Supervised Semantic Labeling
(5) is the loss on the labeled data and £2 regularization on parameters, Ag), from nth iteration, same as standard CRF.
Semi-Supervised Semantic Labeling
The labeled rows ml of the vocabulary matrix, m={wl,m“}, contain only {0,1} values, indicating the word’s observed semantic tags in the labeled data .
labeled data is mentioned in 8 sentences in this paper.
Topics mentioned in this paper:
Lan, Man and Xu, Yu and Niu, Zhengyu
Abstract
To overcome the shortage of labeled data for implicit discourse relation recognition, previous works attempted to automatically generate training data by removing explicit discourse connectives from sentences and then built models on these synthetic implicit examples.
Implementation Details of Multitask Learning Method
nectives and relations in PDTB and generate synthetic labeled data by removing the connectives.
Implementation Details of Multitask Learning Method
BLLIP North American News Text (Complete) is used as unlabeled data source to generate synthetic labeled data .
Implementation Details of Multitask Learning Method
In comparison with the synthetic labeled data generated from the explicit relations in PDTB, the synthetic labeled data from BLLIP contains more noise.
Multitask Learning for Discourse Relation Prediction
Following these two principles, we create the auxiliary tasks by generating automatically labeled data as follows.
Multitask Learning for Discourse Relation Prediction
Previous work (Marcu and Echihabi, 2002) and (Sporleder and Lascarides, 2008) adopted predefined pattern-based approach to generate synthetic labeled data , where each predefined pattern has one discourse relation label.
Multitask Learning for Discourse Relation Prediction
In contrast, we adopt an automatic approach to generate synthetic labeled data , where each discourse connective between two texts serves as their relation label.
labeled data is mentioned in 8 sentences in this paper.
Topics mentioned in this paper:
Zeng, Xiaodong and Wong, Derek F. and Chao, Lidia S. and Trancoso, Isabel
Introduction
In the past years, several proposed supervised joint models (Ng and Low, 2004; Zhang and Clark, 2008; Jiang et al., 2009; Zhang and Clark, 2010) achieved reasonably accurate results, but the outstanding problem among these models is that they rely heavily on a large amount of labeled data , i.e., segmented texts with POS tags.
Introduction
However, the production of such labeled data is extremely time-consuming and expensive (Jiao et al., 2006; J iang et al., 2009).
Introduction
Motivated by the works in (Subramanya et al., 2010; Das and Smith, 2011), for structured problems, graph-based label propagation can be employed to infer valuable syntactic information (n-gram-level label distributions) from labeled data to unlabeled data.
Method
It is especially helpful for the graph to make connections with trigrams that may not have been seen in labeled data but have similar label information.
Method
The first term in Equation (5) is the same as Equation (2), which is the traditional CRFs leam-ing objective function on the labeled data .
Method
To satisfy the characteristic of the semi-supervised learning problem, the train set, i.e., the labeled data , is formed by a relatively small amount of annotated texts sampled from CTB-7.
labeled data is mentioned in 7 sentences in this paper.
Topics mentioned in this paper:
Zeng, Xiaodong and Wong, Derek F. and Chao, Lidia S. and Trancoso, Isabel
Abstract
The proposed approach trains a character-based and word-based model on labeled data , respectively, as the initial models.
Introduction
The proposed approach begins by training a character-based and word-based model on labeled data respectively, and then both models are regularized from each view by their segmentation agreements, i.e., the identical outputs, of unlabeled data.
Semi-supervised Learning via Co-regularizing Both Models
This study proposes a co-regularized CWS model based on character-based and word-based models, built on a small amount of segmented sentences ( labeled data ) and a large amount of raw sentences (unlabeled data).
Semi-supervised Learning via Co-regularizing Both Models
The model induction process is described in Algorithm 1: given labeled dataset D; and unlabeled dataset Du, the first two steps are training a CRFs (character-based) and Perceptrons (word-based) model on the labeled data D; , respectively.
labeled data is mentioned in 4 sentences in this paper.
Topics mentioned in this paper:
Goldwasser, Dan and Roth, Dan
Experimental Settings
The dataset was collected for the purpose of constructing semantic parsers from ambiguous supervision and consists of both “noisy” and gold labeled data .
Experimental Settings
The gold labeled labeled data consists of pairs (X, y).
Semantic Interpretation Model
Moreover, since learning this layer is a byproduct of the learning process (as it does not use any labeled data ) forcing the connection between the decisions is the mechanism that drives learning this model.
labeled data is mentioned in 3 sentences in this paper.
Topics mentioned in this paper:
Plank, Barbara and Moschitti, Alessandro
Abstract
The clear drawback of supervised methods is the need of training data: labeled data is expensive to obtain, and there is often a mismatch between the training data and the data the system will be applied to.
Introduction
However, the clear drawback of supervised methods is the need of training data, which can slow down the delivery of commercial applications in new domains: labeled data is expensive to obtain, and there is often a mismatch between the training data and the data the system will be applied to.
Related Work
These correspondences are then integrated as new features in the labeled data of the source domain.
labeled data is mentioned in 3 sentences in this paper.
Topics mentioned in this paper:
Popat, Kashyap and A.R, Balamurali and Bhattacharyya, Pushpak and Haffari, Gholamreza
Clustering for Cross Lingual Sentiment Analysis
Algorithm 1 Projection based on sense Input: Polarity labeled data in source language (S) and data in target language (T) to be labeled Output: Classified documents 1: Sense mark the polarity labeled data from S 2: Project the sense marked corpora from S to T using a Multidict 3: Model the sentiment classifier using the data obtained in step-2 4: Sense mark the unlabelled data from T 5: Test the sentiment classifier on data obtained in step-4 using model obtained in step-3
Introduction
Popular approaches for Cross-Lingual Sentiment Analysis (CLSA) (Wan, 2009; Duh et al., 2011) depend on Machine Translation (MT) for converting the labeled data from one language to the other (Hiroshi et al., 2004; Banea et al., 2008; Wan, 2009).
Related Work
In situations where labeled data is not present in a language, approaches based on cross-lingual sentiment analysis are used.
labeled data is mentioned in 3 sentences in this paper.
Topics mentioned in this paper:
Scheible, Christian and Schütze, Hinrich
Distant Supervision
To summarize, the results of our experiments using distant supervision show that a sentiment relevance classifier can be trained successfully by labeling data with a few simple feature rules, with
Methods
Supervised optimization is impossible as we do not have any labeled data .
Related Work
In general, it is not possible to know what the underlying concepts of a statistical classification are if no detailed annotation guidelines exist and no direct evaluation of manually labeled data is performed.
labeled data is mentioned in 3 sentences in this paper.
Topics mentioned in this paper:
Sogaard, Anders
Experiments
ting an antagonistic adversary corrupt our labeled data - somewhat surprisingly, maybe - leads to better cross-domain performance.
Introduction
The problem with out-of-vocabulary effects can be illustrated using a small labeled data set: {X1 = <1,<0,1,0>>,X2 I <1, <0,1,1>>,X3 = (0, <0,0,0>>,X4 = (1, (0,0, Say we train our model on X1_3 and evaluate it on the fourth data point.
Robust perceptron learning
Globerson and Roweis (2006) let an adversary corrupt labeled data during training to learn better models of test data with missing features.
labeled data is mentioned in 3 sentences in this paper.
Topics mentioned in this paper:
Zhang, Longkai and Li, Li and He, Zhengyan and Wang, Houfeng and Sun, Ni
Experiment
We use the benchmark datasets provided by the second International Chinese Word Segmentation Bakeoff2 as the labeled data .
Our method
We randomly reuse some characters labeling ’N’ from labeled data until ratio 77 is reached.
Our method
In summary our algorithm tackles the problem by duplicating labeled data in source domain.
labeled data is mentioned in 3 sentences in this paper.
Topics mentioned in this paper: