Dependency-based Word Embeddings Research Articles

Task-specific dependency-based word embedding methods

While most traditional word embedding methods target generic tasks, two task-specific dependency-based word embedding methods are proposed for better performance in text classification tasks in this work. First, we exploit the dependency parsing tree structure to capture the structural information of a sentence, and develop a method called dependency-based word embedding (DWE). It finds keywords and neighbor words of a target word as contexts via dependency parsing. Next, we leverage the word-class co-occurrence statistics to model the class distributional information and incorporate it into the embedding learning process. This leads to the class-enhanced dependency-based word embedding (CEDWE) method. Task-specific corpora and the matrix-factorization-based framework are used to train DWE and CEDWE. Seven text classification datasets are used to evaluate the performance of DWE and CEDWE, and experimental results show that they outperform several state-of-the-art word embedding methods.

Context-aware sequence labeling for condition information extraction from historical bridge inspection reports

Effective upkeep of aging infrastructure systems with limited funding and resources calls for efficient bridge management systems. Although data-driven models have been extensively studied in the last decade for extracting knowledge from past experience to guide future maintenance decision making, their performance and usefulness have been limited by the level of detail and accuracy of currently available bridge condition databases. This paper leverages an untapped resource for bridge condition data and proposes a new method to extract condition information from it at a high level of detail. To that end, a natural language processing approach was developed to formalize structural condition knowledge by formulating a sequence labeling task and modeling inspection narratives as a combination of words representing defects, their severity and location, while accounting for the context of each word. The proposed framework employs a deep-learning-based approach and incorporates context-aware components including a bi-directional Long Short Term Memory (LSTM) neural network architecture and a Conditional Random Field (CRF) classifier to account for the context of words when assigning labels. A dependency-based word embedding model was also used to represent the raw text while incorporating both semantic and contextual information. The sequence labeling model was trained using bridge inspection reports collected from the Virginia Department of Transportation bridge inspection database and achieved an F1 score of 94.12% during testing. The proposed model also demonstrated improvements compared with baseline sequence labeling models, and was further used to demonstrate the capability of detecting condition changes with respect to previous inspection records. Results of this study show that the proposed method can be used to extract and create a condition information database that can further assist in developing data-driven bridge management and condition forecasting models, as well as automated bridge inspection systems.

Towards syntax-aware token embeddings

AbstractDistributional semantic word representations are at the basis of most modern NLP systems. Their usefulness has been proven across various tasks, particularly as inputs to deep learning models. Beyond that, much work investigated fine-tuning the generic word embeddings to leverage linguistic knowledge from large lexical resources. Some work investigated context-dependent word token embeddings motivated by word sense disambiguation, using sequential context and large lexical resources. More recently, acknowledging the need for an in-context representation of words, some work leveraged information derived from language modelling and large amounts of data to induce contextualised representations. In this paper, we investigate Syntax-Aware word Token Embeddings (SATokE) as a way to explicitly encode specific information derived from the linguistic analysis of a sentence in vectors which are input to a deep learning model. We propose an efficient unsupervised learning algorithm based on tensor factorisation for computing these token embeddings given an arbitrary graph of linguistic structure. Applying this method to syntactic dependency structures, we investigate the usefulness of such token representations as part of deep learning models of text understanding. We encode a sentence either by learning embeddings for its tokens and the relations between them from scratch or by leveraging pre-trained relation embeddings to infer token representations. Given sufficient data, the former is slightly more accurate than the latter, yet both provide more informative token embeddings than standard word representations, even when the word representations have been learned on the same type of context from larger corpora (namely pre-trained dependency-based word embeddings). We use a large set of supervised tasks and two major deep learning families of models for sentence understanding to evaluate our proposal. We empirically demonstrate the superiority of the token representations compared to popular distributional representations of words for various sentence and sentence pair classification tasks.

Dual embeddings and metrics for word and relational similarity

Word embedding models excel in measuring word similarity and completing analogies. Word embeddings based on different notions of context trade off strengths in one area for weaknesses in another. Linear bag-of-words contexts, such as in word2vec, can capture topical similarity better, while dependency-based word embeddings better encode functional similarity. By combining these two word embeddings using different metrics, we show how the best aspects of both approaches can be captured. We show state-of-the-art performance on standard word and relational similarity benchmarks.

Contextual label sensitive gated network for biomedical event trigger extraction.

Biomedical events play a key role in improving biomedical research. Event trigger identification, extracting the words describing the event types, is a crucial and prerequisite step in the pipeline process of biomedical event extraction. There exist two main problems in previous methods: (1) The association among contextual trigger labels which can provide significant clues is ignored. (2)The weight between word embeddings and contextual features needs to be adjusted dynamically according to the trigger candidate. In this paper, we propose a novel contextual label sensitive gated network for biomedical event trigger extraction to solve the above two problems, which can mix the two parts dynamically and capture the contextual label clues automatically. Furthermore, we also introduce the dependency-based word embeddings to represent dependency-based semantic information as well as attention mechanism to get more focused representations. Experimental results show that our approach advances state-of-the-arts and achieves the best F1-score on the commonly used Multi-Level Event Extraction (MLEE) corpus.

Evaluating semantic relations in neural word embeddings with biomedical and general domain knowledge bases

BackgroundIn the past few years, neural word embeddings have been widely used in text mining. However, the vector representations of word embeddings mostly act as a black box in downstream applications using them, thereby limiting their interpretability. Even though word embeddings are able to capture semantic regularities in free text documents, it is not clear how different kinds of semantic relations are represented by word embeddings and how semantically-related terms can be retrieved from word embeddings.MethodsTo improve the transparency of word embeddings and the interpretability of the applications using them, in this study, we propose a novel approach for evaluating the semantic relations in word embeddings using external knowledge bases: Wikipedia, WordNet and Unified Medical Language System (UMLS). We trained multiple word embeddings using health-related articles in Wikipedia and then evaluated their performance in the analogy and semantic relation term retrieval tasks. We also assessed if the evaluation results depend on the domain of the textual corpora by comparing the embeddings of health-related Wikipedia articles with those of general Wikipedia articles.ResultsRegarding the retrieval of semantic relations, we were able to retrieve semanti. Meanwhile, the two popular word embedding approaches, Word2vec and GloVe, obtained comparable results on both the analogy retrieval task and the semantic relation retrieval task, while dependency-based word embeddings had much worse performance in both tasks. We also found that the word embeddings trained with health-related Wikipedia articles obtained better performance in the health-related relation retrieval tasks than those trained with general Wikipedia articles.ConclusionIt is evident from this study that word embeddings can group terms with diverse semantic relations together. The domain of the training corpus does have impact on the semantic relations represented by word embeddings. We thus recommend using domain-specific corpus to train word embeddings for domain-specific text mining tasks.

Training and Evaluating Improved Dependency-Based Word Embeddings

Word embedding has been widely used in many natural language processing tasks. In this paper, we focus on learning word embeddings through selective higher-order relationships in sentences to improve the embeddings to be less sensitive to local context and more accurate in capturing semantic compositionality. We present a novel multi-order dependency-based strategy to composite and represent the context under several essential constraints. In order to realize selective learning from the word contexts, we automatically assign the strengths of different dependencies between co-occurred words in the stochastic gradient descent process. We evaluate and analyze our proposed approach using several direct and indirect tasks for word embeddings. Experimental results demonstrate that our embeddings are competitive to or better than state-of-the-art methods and significantly outperform other methods in terms of context stability. The output weights and representations of dependencies obtained in our embedding model conform to most of the linguistic characteristics and are valuable for many downstream tasks.

A multiple distributed representation method based on neural network for biomedical event extraction

BackgroundBiomedical event extraction is one of the most frontier domains in biomedical research. The two main subtasks of biomedical event extraction are trigger identification and arguments detection which can both be considered as classification problems. However, traditional state-of-the-art methods are based on support vector machine (SVM) with massive manually designed one-hot represented features, which require enormous work but lack semantic relation among words.MethodsIn this paper, we propose a multiple distributed representation method for biomedical event extraction. The method combines context consisting of dependency-based word embedding, and task-based features represented in a distributed way as the input of deep learning models to train deep learning models. Finally, we used softmax classifier to label the example candidates.ResultsThe experimental results on Multi-Level Event Extraction (MLEE) corpus show higher F-scores of 77.97% in trigger identification and 58.31% in overall compared to the state-of-the-art SVM method.ConclusionsOur distributed representation method for biomedical event extraction avoids the problems of semantic gap and dimension disaster from traditional one-hot representation methods. The promising results demonstrate that our proposed method is effective for biomedical event extraction.