Semantic Role Labeling Performance Research Articles

Syntax Role for Neural Semantic Role Labeling

Semantic role labeling (SRL) is dedicated to recognizing the semantic predicate-argument structure of a sentence. Previous studies in terms of traditional models have shown syntactic information can make remarkable contributions to SRL performance; however, the necessity of syntactic information was challenged by a few recent neural SRL studies that demonstrate impressive performance without syntactic backbones and suggest that syntax information becomes much less important for neural semantic role labeling, especially when paired with recent deep neural network and large-scale pre-trained language models. Despite this notion, the neural SRL field still lacks a systematic and full investigation on the relevance of syntactic information in SRL, for both dependency and both monolingual and multilingual settings. This paper intends to quantify the importance of syntactic information for neural SRL in the deep learning framework. We introduce three typical SRL frameworks (baselines), sequence-based, tree-based, and graph-based, which are accompanied by two categories of exploiting syntactic information: syntax pruning-based and syntax feature-based. Experiments are conducted on the CoNLL-2005, -2009, and -2012 benchmarks for all languages available, and results show that neural SRL models can still benefit from syntactic information under certain conditions. Furthermore, we show the quantitative significance of syntax to neural SRL models together with a thorough empirical survey using existing models.

Adaptive Convolution for Semantic Role Labeling

Semantic role labeling (SRL) aims at elaborating the meaning of a sentence by forming a predicate-argument structure. Recent researches depicted that the effective use of syntax can improve SRL performance. However, syntax is a complicated linguistic clue and is hard to be effectively applied in a downstream task like SRL. This work effectively encodes syntax using adaptive convolution which endows strong flexibility to existing convolutional networks. The existing CNNs may help in encoding a complicated structure like syntax for SRL, but it still has shortcomings. Contrary to traditional convolutional networks that use same filters for different inputs, adaptive convolution uses adaptively generated filters conditioned on syntactically-informed inputs. We achieve this with the integration of a filter generation network which generates the input specific filters. This helps the model to focus on important syntactic features present inside the input, thus enlarging the gap between syntax-aware and syntax-agnostic SRL systems. We further study a hashing technique to compress the size of the filter generation network for SRL in terms of trainable parameters. Experiments on CoNLL-2009 dataset confirm that the proposed model substantially outperforms most previous SRL systems for both English and Chinese languages.

Improving Chinese Semantic Role Labeling using High-quality Surface and Deep Case Frames

This paper presents a method for applying automatically acquired knowledge to semantic role labeling (SRL). We use a large amount of automatically extracted knowledge to improve the performance of SRL. We present two varieties of knowledge, which we call surface case frames and deep case frames. Although the surface case frames are compiled from syntactic parses and can be used as rich syntactic knowledge, they have limited capability for resolving semantic ambiguity. To compensate the deficiency of the surface case frames, we compile deep case frames from automatic semantic roles. We also consider quality management for both types of knowledge in order to get rid of the noise brought from the automatic analyses. The experimental results show that Chinese SRL can be improved using automatically acquired knowledge and the quality management shows a positive effect on this task.

Automatic Extraction of Access Control Policies from Natural Language Documents

A fundamental management responsibility is securing information systems. Almost all applications that deal with safety, privacy, or defense include some form of access control. There are a plethora of access control models in the information security realm such as role-based access control and attribute-based access control. However, the initial development of access control policies (ACPs) can be very challenging. Most organizations have high-level requirement specifications that include a set of ACPs, which describe allowable operations of the system. It is time consuming and error-prone to manually sift through these documents and extract ACPs. In this paper, we propose a new framework towards extracting ACPs from unrestricted natural language documents using semantic role labeling (SRL). We were able to correctly identify ACP elements with an average $F_1$ F 1 score of 75 percent, which bested the previous work by 15 percent. Furthermore, as SRL tools are often trained on publicly available corpora such as Wall Street Journal, we investigated the idea of improving SRL performance using domain-related knowledge. We utilized domain adaptation and semi-supervised learning techniques and were able to improve the SRL performance by 2 percent using only a small amount of access control data.

Learning Generalized Features for Semantic Role Labeling

This article makes an effort to improve Semantic Role Labeling (SRL) through learning generalized features. The SRL task is usually treated as a supervised problem. Therefore, a huge set of features are crucial to the performance of SRL systems. But these features often lack generalization powers when predicting an unseen argument. This article proposes a simple approach to relieve the issue. A strong intuition is that arguments occurring in similar syntactic positions are likely to bear the same semantic role, and, analogously, arguments that are lexically similar are likely to represent the same semantic role. Therefore, it will be informative to SRL if syntactic or lexical similar arguments can activate the same feature. Inspired by this, we embed the information of lexicalization and syntax into a feature vector for each argument and then use K -means to make clustering for all feature vectors of training set. For an unseen argument to be predicted, it will belong to the same cluster as its similar arguments of training set. Therefore, the clusters can be thought of as a kind of generalized feature. We evaluate our method on several benchmarks. The experimental results show that our approach can significantly improve the SRL performance.

Domain adaptation for semantic role labeling of clinical text.

Semantic role labeling (SRL), which extracts a shallow semantic relation representation from different surface textual forms of free text sentences, is important for understanding natural language. Few studies in SRL have been conducted in the medical domain, primarily due to lack of annotated clinical SRL corpora, which are time-consuming and costly to build. The goal of this study is to investigate domain adaptation techniques for clinical SRL leveraging resources built from newswire and biomedical literature to improve performance and save annotation costs. Multisource Integrated Platform for Answering Clinical Questions (MiPACQ), a manually annotated SRL clinical corpus, was used as the target domain dataset. PropBank and NomBank from newswire and BioProp from biomedical literature were used as source domain datasets. Three state-of-the-art domain adaptation algorithms were employed: instance pruning, transfer self-training, and feature augmentation. The SRL performance using different domain adaptation algorithms was evaluated by using 10-fold cross-validation on the MiPACQ corpus. Learning curves for the different methods were generated to assess the effect of sample size. When all three source domain corpora were used, the feature augmentation algorithm achieved statistically significant higher F-measure (83.18%), compared to the baseline with MiPACQ dataset alone (F-measure, 81.53%), indicating that domain adaptation algorithms may improve SRL performance on clinical text. To achieve a comparable performance to the baseline method that used 90% of MiPACQ training samples, the feature augmentation algorithm required <50% of training samples in MiPACQ, demonstrating that annotation costs of clinical SRL can be reduced significantly by leveraging existing SRL resources from other domains.