scholarly journals Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions

2013 ◽  
Vol 1 ◽  
pp. 49-62 ◽  
Author(s):  
Yoav Artzi ◽  
Luke Zettlemoyer
Keyword(s):  
Natural Language ◽  
Supervised Learning ◽  
State Of The Art ◽  
Semantic Parsing ◽  
Weak Supervision ◽  
Instruction Sets ◽  
Strong Signal ◽  
Previous State ◽  
Strong Performance ◽  
Weakly Supervised

The context in which language is used provides a strong signal for learning to recover its meaning. In this paper, we show it can be used within a grounded CCG semantic parsing approach that learns a joint model of meaning and context for interpreting and executing natural language instructions, using various types of weak supervision. The joint nature provides crucial benefits by allowing situated cues, such as the set of visible objects, to directly influence learning. It also enables algorithms that learn while executing instructions, for example by trying to replicate human actions. Experiments on a benchmark navigational dataset demonstrate strong performance under differing forms of supervision, including correctly executing 60% more instruction sets relative to the previous state of the art.

scholarly journals Large-scale Semantic Parsing without Question-Answer Pairs

2014 ◽  
Vol 2 ◽  
pp. 377-392 ◽  
Author(s):  
Siva Reddy ◽  
Mirella Lapata ◽  
Mark Steedman
Keyword(s):  
Natural Language ◽  
Large Scale ◽  
Graph Matching ◽  
State Of The Art ◽  
The State ◽  
Semantic Parsing ◽  
Matching Problem ◽  
Weak Supervision ◽  
Benchmark Datasets

In this paper we introduce a novel semantic parsing approach to query Freebase in natural language without requiring manual annotations or question-answer pairs. Our key insight is to represent natural language via semantic graphs whose topology shares many commonalities with Freebase. Given this representation, we conceptualize semantic parsing as a graph matching problem. Our model converts sentences to semantic graphs using CCG and subsequently grounds them to Freebase guided by denotations as a form of weak supervision. Evaluation experiments on a subset of the Free917 and WebQuestions benchmark datasets show our semantic parser improves over the state of the art.

scholarly journals Merging Weak and Active Supervision for Semantic Parsing

2020 ◽  
Vol 34 (05) ◽  
pp. 8536-8543
Author(s):  
Ansong Ni ◽  
Pengcheng Yin ◽  
Graham Neubig
Keyword(s):  
Active Learning ◽  
State Of The Art ◽  
Semantic Parsing ◽  
Large Space ◽  
Performance Gap ◽  
Weak Supervision ◽  
Domain Experts ◽  
Supervised Training ◽  
Weakly Supervised ◽  
Learning Heuristics

A semantic parser maps natural language commands (NLs) from the users to executable meaning representations (MRs), which are later executed in certain environment to obtain user-desired results. The fully-supervised training of such parser requires NL/MR pairs, annotated by domain experts, which makes them expensive to collect. However, weakly-supervised semantic parsers are learnt only from pairs of NL and expected execution results, leaving the MRs latent. While weak supervision is cheaper to acquire, learning from this input poses difficulties. It demands that parsers search a large space with a very weak learning signal and it is hard to avoid spurious MRs that achieve the correct answer in the wrong way. These factors lead to a performance gap between parsers trained in weakly- and fully-supervised setting. To bridge this gap, we examine the intersection between weak supervision and active learning, which allows the learner to actively select examples and query for manual annotations as extra supervision to improve the model trained under weak supervision. We study different active learning heuristics for selecting examples to query, and various forms of extra supervision for such queries. We evaluate the effectiveness of our method on two different datasets. Experiments on the WikiSQL show that by annotating only 1.8% of examples, we improve over a state-of-the-art weakly-supervised baseline by 6.4%, achieving an accuracy of 79.0%, which is only 1.3% away from the model trained with full supervision. Experiments on WikiTableQuestions with human annotators show that our method can improve the performance with only 100 active queries, especially for weakly-supervised parsers learnt from a cold start. 1

scholarly journals From Characters to Time Intervals: New Paradigms for Evaluation and Neural Parsing of Time Normalizations

2018 ◽  
Vol 6 ◽  
pp. 343-356 ◽  
Author(s):  
Egoitz Laparra ◽  
Dongfang Xu ◽  
Steven Bethard
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Comparative Analysis ◽  
State Of The Art ◽  
Learning Approaches ◽  
Semantic Parsing ◽  
Time Intervals ◽  
Semantic Composition ◽  
Previous State ◽  
New Scoring

This paper presents the first model for time normalization trained on the SCATE corpus. In the SCATE schema, time expressions are annotated as a semantic composition of time entities. This novel schema favors machine learning approaches, as it can be viewed as a semantic parsing task. In this work, we propose a character level multi-output neural network that outperforms previous state-of-the-art built on the TimeML schema. To compare predictions of systems that follow both SCATE and TimeML, we present a new scoring metric for time intervals. We also apply this new metric to carry out a comparative analysis of the annotations of both schemes in the same corpus.

scholarly journals Regularized Instance Embedding for Deep Multi-Instance Learning

2019 ◽  
Vol 10 (1) ◽  
pp. 64
Author(s):  
Yi Lin ◽  
Honggang Zhang
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Supervised Learning ◽  
Regularization Method ◽  
Gradient Descent ◽  
State Of The Art ◽  
Stochastic Gradient Descent ◽  
Learning Framework ◽  
Weakly Supervised ◽  
The Cost

In the era of Big Data, multi-instance learning, as a weakly supervised learning framework, has various applications since it is helpful to reduce the cost of the data-labeling process. Due to this weakly supervised setting, learning effective instance representation/embedding is challenging. To address this issue, we propose an instance-embedding regularizer that can boost the performance of both instance- and bag-embedding learning in a unified fashion. Specifically, the crux of the instance-embedding regularizer is to maximize correlation between instance-embedding and underlying instance-label similarities. The embedding-learning framework was implemented using a neural network and optimized in an end-to-end manner using stochastic gradient descent. In experiments, various applications were studied, and the results show that the proposed instance-embedding-regularization method is highly effective, having state-of-the-art performance.

scholarly journals Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels with Variational Auto-Encoder

2021 ◽  
Author(s):  
Weijia Zhang
Keyword(s):  
Medical Imaging ◽  
Supervised Learning ◽  
Real World ◽  
State Of The Art ◽  
Experimental Results ◽  
Weakly Supervised Learning ◽  
Variational Autoencoder ◽  
Label Prediction ◽  
Weakly Supervised ◽  
Better Than

Multi-instance learning is a type of weakly supervised learning. It deals with tasks where the data is a set of bags and each bag is a set of instances. Only the bag labels are observed whereas the labels for the instances are unknown. An important advantage of multi-instance learning is that by representing objects as a bag of instances, it is able to preserve the inherent dependencies among parts of the objects. Unfortunately, most existing algorithms assume all instances to be identically and independently distributed, which violates real-world scenarios since the instances within a bag are rarely independent. In this work, we propose the Multi-Instance Variational Autoencoder (MIVAE) algorithm which explicitly models the dependencies among the instances for predicting both bag labels and instance labels. Experimental results on several multi-instance benchmarks and end-to-end medical imaging datasets demonstrate that MIVAE performs better than state-of-the-art algorithms for both instance label and bag label prediction tasks.

scholarly journals Weakly Supervised Classification of Hyperspectral Image Based on Complementary Learning

2021 ◽  
Vol 13 (24) ◽  
pp. 5009
Author(s):  
Lingbo Huang ◽  
Yushi Chen ◽  
Xin He
Keyword(s):  
Supervised Classification ◽  
Data Augmentation ◽  
Hyperspectral Image ◽  
State Of The Art ◽  
The State ◽  
Weak Supervision ◽  
Training Samples ◽  
Weakly Supervised ◽  
Weakly Supervised Classification

In recent years, supervised learning-based methods have achieved excellent performance for hyperspectral image (HSI) classification. However, the collection of training samples with labels is not only costly but also time-consuming. This fact usually causes the existence of weak supervision, including incorrect supervision where mislabeled samples exist and incomplete supervision where unlabeled samples exist. Focusing on the inaccurate supervision and incomplete supervision, the weakly supervised classification of HSI is investigated in this paper. For inaccurate supervision, complementary learning (CL) is firstly introduced for HSI classification. Then, a new method, which is based on selective CL and convolutional neural network (SeCL-CNN), is proposed for classification with noisy labels. For incomplete supervision, a data augmentation-based method, which combines mixup and Pseudo-Label (Mix-PL) is proposed. And then, a classification method, which combines Mix-PL and CL (Mix-PL-CL), is designed aiming at better semi-supervised classification capacity of HSI. The proposed weakly supervised methods are evaluated on three widely-used hyperspectral datasets (i.e., Indian Pines, Houston, and Salinas datasets). The obtained results reveal that the proposed methods provide competitive results compared to the state-of-the-art methods. For inaccurate supervision, the proposed SeCL-CNN has outperformed the state-of-the-art method (i.e., SSDP-CNN) by 0.92%, 1.84%, and 1.75% in terms of OA on the three datasets, when the noise ratio is 30%. And for incomplete supervision, the proposed Mix-PL-CL has outperformed the state-of-the-art method (i.e., AROC-DP) by 1.03%, 0.70%, and 0.82% in terms of OA on the three datasets, with 25 training samples per class.

scholarly journals Effective Search of Logical Forms for Weakly Supervised Knowledge-Based Question Answering

2020 ◽  
Author(s):  
Tao Shen ◽  
Xiubo Geng ◽  
Guodong Long ◽  
Jing Jiang ◽  
Chengqi Zhang ◽  
...  
Keyword(s):  
Question Answering ◽  
Logical Form ◽  
Computation Time ◽  
Search Space ◽  
Training Data ◽  
Semantic Parsing ◽  
Weak Supervision ◽  
Knowledge Based ◽  
Model Training ◽  
Weakly Supervised

Many algorithms for Knowledge-Based Question Answering (KBQA) depend on semantic parsing, which translates a question to its logical form. When only weak supervision is provided, it is usually necessary to search valid logical forms for model training. However, a complex question typically involves a huge search space, which creates two main problems: 1) the solutions limited by computation time and memory usually reduce the success rate of the search, and 2) spurious logical forms in the search results degrade the quality of training data. These two problems lead to a poorly-trained semantic parsing model. In this work, we propose an effective search method for weakly supervised KBQA based on operator prediction for questions. With search space constrained by predicted operators, sufficient search paths can be explored, more valid logical forms can be derived, and operators possibly causing spurious logical forms can be avoided. As a result, a larger proportion of questions in a weakly supervised training set are equipped with logical forms, and fewer spurious logical forms are generated. Such high-quality training data directly contributes to a better semantic parsing model. Experimental results on one of the largest KBQA datasets (i.e., CSQA) verify the effectiveness of our approach and deliver a new state-of-the-art performance.

TransBERT

2021 ◽  
Vol 20 (1) ◽  
pp. 1-20
Author(s):  
Zhongyang Li ◽  
Xiao Ding ◽  
Ting Liu
Keyword(s):  
Natural Language ◽  
Large Scale ◽  
State Of The Art ◽  
Language Model ◽  
Fine Tuning ◽  
Action Prediction ◽  
Target Task ◽  
Language Knowledge ◽  
Previous State ◽  
Transfer Tasks

Recent advances, such as GPT, BERT, and RoBERTa, have shown success in incorporating a pre-trained transformer language model and fine-tuning operations to improve downstream NLP systems. However, this framework still has some fundamental problems in effectively incorporating supervised knowledge from other related tasks. In this study, we investigate a transferable BERT (TransBERT) training framework, which can transfer not only general language knowledge from large-scale unlabeled data but also specific kinds of knowledge from various semantically related supervised tasks, for a target task. Particularly, we propose utilizing three kinds of transfer tasks, including natural language inference, sentiment classification, and next action prediction, to further train BERT based on a pre-trained model. This enables the model to get a better initialization for the target task. We take story-ending prediction as the target task to conduct experiments. The final results of 96.0% and 95.0% accuracy on two versions of Story Cloze Test datasets dramatically outperform previous state-of-the-art baseline methods. Several comparative experiments give some helpful suggestions on how to select transfer tasks to improve BERT. Furthermore, experiments on six English and three Chinese datasets show that TransBERT generalizes well to other tasks, languages, and pre-trained models.

scholarly journals Weakly Supervised Learning for Evaluating Road Surface Condition from Wheelchair Driving Data

Information ◽  
2019 ◽  
Vol 11 (1) ◽  
pp. 2
Author(s):  
Takumi Watanabe ◽  
Hiroki Takahashi ◽  
Yusuke Iwasawa ◽  
Yutaka Matsuo ◽  
Ikuko Eguchi Yairi
Keyword(s):  
Supervised Learning ◽  
Surface Condition ◽  
Road Surface ◽  
Supervised Machine Learning ◽  
Accelerometer Data ◽  
Weakly Supervised Learning ◽  
Weak Supervision ◽  
Surface Conditions ◽  
Feature Representations ◽  
Weakly Supervised

Providing accessibility information about sidewalks for people with difficulties with moving is an important social issue. We previously proposed a fully supervised machine learning approach for providing accessibility information by estimating road surface conditions using wheelchair accelerometer data with manually annotated road surface condition labels. However, manually annotating road surface condition labels is expensive and impractical for extensive data. This paper proposes and evaluates a novel method for estimating road surface conditions without human annotation by applying weakly supervised learning. The proposed method only relies on positional information while driving for weak supervision to learn road surface conditions. Our results demonstrate that the proposed method learns detailed and subtle features of road surface conditions, such as the difference in ascending and descending of a slope, the angle of slopes, the exact locations of curbs, and the slight differences of similar pavements. The results demonstrate that the proposed method learns feature representations that are discriminative for a road surface classification task. When the amount of labeled data is 10% or less in a semi-supervised setting, the proposed method outperforms a fully supervised method that uses manually annotated labels to learn feature representations of road surface conditions.

scholarly journals Learning to Map Frequent Phrases to Sub-Structures of Meaning Representation for Neural Semantic Parsing

2020 ◽  
Vol 34 (05) ◽  
pp. 7546-7553
Author(s):  
Bo Chen ◽  
Xianpei Han ◽  
Ben He ◽  
Le Sun
Keyword(s):  
Natural Language ◽  
Performance Improvement ◽  
Search Space ◽  
Great Benefit ◽  
Semantic Parsing ◽  
Mismatch Problem ◽  
Weakly Supervised ◽  
Meaning Representation

Neural semantic parsers usually generate meaning representation tokens from natural language tokens via an encoder-decoder model. However, there is often a vocabulary-mismatch problem between natural language utterances and logical forms. That is, one word maps to several atomic logical tokens, which need to be handled as a whole, rather than individual logical tokens at multiple steps. In this paper, we propose that the vocabulary-mismatch problem can be effectively resolved by leveraging appropriate logical tokens. Specifically, we exploit macro actions, which are of the same granularity of words/phrases, and allow the model to learn mappings from frequent phrases to corresponding sub-structures of meaning representation. Furthermore, macro actions are compact, and therefore utilizing them can significantly reduce the search space, which brings a great benefit to weakly supervised semantic parsing. Experiments show that our method leads to substantial performance improvement on three benchmarks, in both supervised and weakly supervised settings.

Sign in / Sign up

Export Citation Format

Share Document