skip to main content

Explore Research Products in the NSF-PAR

Title: Improving Cross-Domain Performance for Relation Extraction via Dependency Prediction and Information Flow Control

Relation Extraction (RE) is one of the fundamental tasks in Information Extraction and Natural Language Processing. Dependency trees have been shown to be a very useful source of information for this task. The current deep learning models for relation extraction has mainly exploited this dependency information by guiding their computation along the structures of the dependency trees. One potential problem with this approach is it might prevent the models from capturing important context information beyond syntactic structures and cause the poor cross-domain generalization. This paper introduces a novel method to use dependency trees in RE for deep learning models that jointly predicts dependency and semantics relations. We also propose a new mechanism to control the information flow in the model based on the input entity mentions. Our extensive experiments on benchmark datasets show that the proposed model outperforms the existing methods for RE significantly.

  more » « less
Award ID(s):
1747798
NSF-PAR ID:
10131139
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Page Range / eLocation ID:
5153 to 5159
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ( , Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics)
    null (Ed.)
    This paper studies the task of Relation Extraction (RE) that aims to identify the semantic relations between two entity mentions in text. In the deep learning models for RE, it has been beneficial to incorporate the syntactic structures from the dependency trees of the input sentences. In such models, the dependency trees are often used to directly structure the network architectures or to obtain the dependency relations between the word pairs to inject the syntactic information into the models via multi-task learning. The major problem with these approaches is the lack of generalization beyond the syntactic structures in the training data or the failure to capture the syntactic importance of the words for RE. In order to overcome these issues, we propose a novel deep learning model for RE that uses the dependency trees to extract the syntax-based importance scores for the words, serving as a tree representation to introduce syntactic information into the models with greater generalization. In particular, we leverage Ordered-Neuron Long-Short Term Memory Networks (ON-LSTM) to infer the model-based importance scores for RE for every word in the sentences that are then regulated to be consistent with the syntax-based scores to enable syntactic information injection. We perform extensive experiments to demonstrate the effectiveness of the proposed method, leading to the state-of-the-art performance on three RE benchmark datasets. 
    more » « less
  2. ; ; ; ; ( , Proceedings of the AAAI Conference on Artificial Intelligence)
    null (Ed.)
    Relation Extraction (RE) is one of the fundamental tasks in Information Extraction. The goal of this task is to find the semantic relations between entity mentions in text. It has been shown in many previous work that the structure of the sentences (i.e., dependency trees) can provide important information/features for the RE models. However, the common limitation of the previous work on RE is the reliance on some external parsers to obtain the syntactic trees for the sentence structures. On the one hand, it is not guaranteed that the independent external parsers can offer the optimal sentence structures for RE and the customized structures for RE might help to further improve the performance. On the other hand, the quality of the external parsers might suffer when applied to different domains, thus also affecting the performance of the RE models on such domains. In order to overcome this issue, we introduce a novel method for RE that simultaneously induces the structures and predicts the relations for the input sentences, thus avoiding the external parsers and potentially leading to better sentence structures for RE. Our general strategy to learn the RE-specific structures is to apply two different methods to infer the structures for the input sentences (i.e., two views). We then introduce several mechanisms to encourage the structure and semantic consistencies between these two views so the effective structure and semantic representations for RE can emerge. We perform extensive experiments on the ACE 2005 and SemEval 2010 datasets to demonstrate the advantages of the proposed method, leading to the state-of-the-art performance on such datasets. 
    more » « less
  3. ; ; ; ( , Proceedings of the AAAI Conference on Artificial Intelligence)
    null (Ed.)
    Definition Extraction (DE) is one of the well-known topics in Information Extraction that aims to identify terms and their corresponding definitions in unstructured texts. This task can be formalized either as a sentence classification task (i.e., containing term-definition pairs or not) or a sequential labeling task (i.e., identifying the boundaries of the terms and definitions). The previous works for DE have only focused on one of the two approaches, failing to model the inter-dependencies between the two tasks. In this work, we propose a novel model for DE that simultaneously performs the two tasks in a single framework to benefit from their inter-dependencies. Our model features deep learning architectures to exploit the global structures of the input sentences as well as the semantic consistencies between the terms and the definitions, thereby improving the quality of the representation vectors for DE. Besides the joint inference between sentence classification and sequential labeling, the proposed model is fundamentally different from the prior work for DE in that the prior work has only employed the local structures of the input sentences (i.e., word-to-word relations), and not yet considered the semantic consistencies between terms and definitions. In order to implement these novel ideas, our model presents a multi-task learning framework that employs graph convolutional neural networks and predicts the dependency paths between the terms and the definitions. We also seek to enforce the consistency between the representations of the terms and definitions both globally (i.e., increasing semantic consistency between the representations of the entire sentences and the terms/definitions) and locally (i.e., promoting the similarity between the representations of the terms and the definitions). The extensive experiments on three benchmark datasets demonstrate the effectiveness of our approach.1 
    more » « less
  4. ; ; ; ; ; ( , CGO 2020: Proceedings of the 18th ACM/IEEE International Symposium on Code Generation and Optimization)
    null (Ed.)
    One of the key challenges arising when compilers vectorize loops for today’s SIMD-compatible architectures is to decide if vectorization or interleaving is beneficial. Then, the compiler has to determine the number of instructions to pack together and the interleaving level (stride). Compilers are designed today to use fixed-cost models that are based on heuristics to make vectorization decisions on loops. However, these models are unable to capture the data dependency, the computation graph, or the organization of instructions. Alternatively, software engineers often hand-write the vectorization factors of every loop. This, however, places a huge burden on them, since it requires prior experience and significantly increases the development time. In this work, we explore a novel approach for handling loop vectorization and propose an end-to-end solution using deep reinforcement learning (RL). We conjecture that deep RL can capture different instructions, dependencies, and data structures to enable learning a sophisticated model that can better predict the actual performance cost and determine the optimal vectorization factors. We develop an end-to-end framework, from code to vectorization, that integrates deep RL in the LLVM compiler. Our proposed framework takes benchmark codes as input and extracts the loop codes. These loop codes are then fed to a loop embedding generator that learns an embedding for these loops. Finally, the learned embeddings are used as input to a Deep RL agent, which dynamically determines the vectorization factors for all the loops. We further extend our framework to support random search, decision trees, supervised neural networks, and nearest-neighbor search. We evaluate our approaches against the currently used LLVM vectorizer and loop polyhedral optimization techniques. Our experiments show 1.29×−4.73× performance speedup compared to baseline and only 3% worse than the brute-force search on a wide range of benchmarks. 
    more » « less
  5. ; ( , 2019 CSCE Annual Conference)
    Most of the existing automated code compliance checking (ACC) methods are unable to fully automatically convert complex building-code requirements into computer-processable forms. Such complex requirements usually have hierarchically complex clause and sentence structures. There is, thus, a need to decompose such complex requirements into hierarchies of much smaller, manageable requirement units that would be processable using most of the existing ACC methods. Rule-based methods have been used to deal with such complex requirements and have achieved high performance. However, they lack scalability, because the rules are developed manually and need to be updated and/or adapted when applied to a different type of building code. More research is, thus, needed to develop a scalable method to automatically convert the complex requirements into hierarchies of requirement units to facilitate the succeeding steps of ACC such as information extraction and compliance reasoning. To address this need, this paper proposes a new, machine learning-based method to automatically extract requirement hierarchies from building codes. The proposed method consists of five main steps: (1) data preparation and preprocessing; (2) data adaptation; (3) deep neural network model training for dependency parsing; (4) automated requirement segmentation and restriction interpretation based on the extracted dependencies; and (5) evaluation. The proposed method was trained using the English Treebank data; and was tested on sentences from the 2009 International Building Code (IBC) and the Champaign 2015 IBC Amendments. The preliminary results show that the proposed method achieved an average normalized edit distance of 0.32, a precision of 89%, a recall of 76%, and an F1-measure of 82%, which indicates good requirement hierarchy extraction performance. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email