arXiv subjects

Hai Zhao

Publications and source records attributed to Hai Zhao.

250 records · Page 14Linked to original sources

arXiv2018

SJTU-NLP at SemEval-2018 Task 9: Neural Hypernym Discovery with Term Embeddings

This paper describes a hypernym discovery system for our participation in the SemEval-2018 Task 9, which aims to discover the best (set of) candidate hypernyms for input concepts or entities, given the search space of a pre-defined vocabulary. We introduce a neural network architecture for the concerned task and empirically study various neural network models to build the representations in latent space for words and phrases. The evaluated models include convolutional neural network, long-short term memory network, gated recurrent unit and recurrent convolutional neural network. We also explore different embedding methods, including word embedding and sense embedding for better performance.

cs.CL↗

arXiv2018

Automatic Article Commenting: the Task and Dataset

Comments of online articles provide extended views and improve user engagement. Automatically making comments thus become a valuable functionality for online forums, intelligent chatbots, etc. This paper proposes the new task of automatic article commenting, and introduces a large-scale Chinese dataset with millions of real comments and a human-annotated subset characterizing the comments' varying quality. Incorporating the human bias of comment quality, we further develop automatic metrics that generalize a broad set of popular reference-based metrics and exhibit greatly improved correlations with human evaluations.

cs.CL↗

arXiv2017

Tracing a Loose Wordhood for Chinese Input Method Engine

Chinese input methods are used to convert pinyin sequence or other Latin encoding systems into Chinese character sentences. For more effective pinyin-to-character conversion, typical Input Method Engines (IMEs) rely on a predefined vocabulary that demands manually maintenance on schedule. For the purpose of removing the inconvenient vocabulary setting, this work focuses on automatic wordhood acquisition by fully considering that Chinese inputting is a free human-computer interaction procedure. Instead of strictly defining words, a loose word likelihood is introduced for measuring how likely a character sequence can be a user-recognized word with respect to using IME. Then an online algorithm is proposed to adjust the word likelihood or generate new words by comparing user true choice for inputting and the algorithm prediction. The experimental results show that the proposed solution can agilely adapt to diverse typings and demonstrate performance approaching highly-optimized IME with fixed vocabulary.

cs.CL↗

arXiv2017

Internet Anomaly Detection based on Complex Network Path

Detecting the anomaly behaviors such as network failure or Internet intentional attack in the large-scale Internet is a vital but challenging task. While numerous techniques have been developed based on Internet traffic in past years, anomaly detection for structured datasets by complex network have just been of focus recently. In this paper, a anomaly detection method for large-scale Internet topology is proposed by considering the changes of network crashes. In order to quantify the dynamic changes of Internet topology, the network path changes coefficient(NPCC) is put forward which will highlight the Internet abnormal state after it is attacked continuously. Furthermore we proposed the decision function which is inspired by Fibonacci Sequence to determine whether the Internet is abnormal or not. That is the current Internet is abnormal if its NPCC is beyond the normal domain which structured by the previous k NPCCs of Internet topology. Finally the new Internet anomaly detection method was tested over the topology data of three Internet anomaly events. The results show that the detection accuracy of all events are over 97%, the detection precision of each event are 90.24%, 83.33% and 66.67%, when k = 36. According to the experimental values of the index F_1, we found the the better the detection performance is, the bigger the k is, and our method has better performance for the anomaly behaviors caused by network failure than that caused by intentional attack. Compared with traditional anomaly detection, our work may be more simple and powerful for the government or organization in items of detecting large-scale abnormal events.

cs.NI↗

arXiv2017

Structural Stability of Lexical Semantic Spaces: Nouns in Chinese and French

Many studies in the neurosciences have dealt with the semantic processing of words or categories, but few have looked into the semantic organization of the lexicon thought as a system. The present study was designed to try to move towards this goal, using both electrophysiological and corpus-based data, and to compare two languages from different families: French and Mandarin Chinese. We conducted an EEG-based semantic-decision experiment using 240 words from eight categories (clothing, parts of a house, tools, vehicles, fruits/vegetables, animals, body parts, and people) as the material. A data-analysis method (correspondence analysis) commonly used in computational linguistics was applied to the electrophysiological signals. The present cross-language comparison indicated stability for the following aspects of the languages' lexical semantic organizations: (1) the living/nonliving distinction, which showed up as a main factor for both languages; (2) greater dispersion of the living categories as compared to the nonliving ones; (3) prototypicality of the \emph{animals} category within the living categories, and with respect to the living/nonliving distinction; and (4) the existence of a person-centered reference gradient. Our electrophysiological analysis indicated stability of the networks at play in each of these processes. Stability was also observed in the data taken from word usage in the languages (synonyms and associated words obtained from textual corpora).

q-bio.NC↗

arXiv2017

Fast and Accurate Neural Word Segmentation for Chinese

Neural models with minimal feature engineering have achieved competitive performance against traditional methods for the task of Chinese word segmentation. However, both training and working procedures of the current neural models are computationally inefficient. This paper presents a greedy neural word segmenter with balanced word and character embedding inputs to alleviate the existing drawbacks. Our segmenter is truly end-to-end, capable of performing segmentation much faster and even more accurate than state-of-the-art neural models on Chinese benchmark datasets.

cs.CL↗

arXiv2017

Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classification

Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another neural network with access to connectives, and thus encouraged to extract similarly salient features for accurate classification. We develop an adversarial model to enable an adaptive imitation scheme through competition between the implicit network and a rival feature discriminator. Our method effectively transfers discriminability of connectives to the implicit features, and achieves state-of-the-art performance on the PDTB benchmark.

cs.CL↗

arXiv2016

Neural Word Segmentation Learning for Chinese

Most previous approaches to Chinese word segmentation formalize this problem as a character-based sequence labeling task where only contextual information within fixed sized local windows and simple interactions between adjacent tags can be captured. In this paper, we propose a novel neural framework which thoroughly eliminates context windows and can utilize complete segmentation history. Our model employs a gated combination neural network over characters to produce distributed representations of word candidates, which are then given to a long short-term memory (LSTM) language scoring model. Experiments on the benchmark datasets show that without the help of feature engineering as most existing approaches, our models achieve competitive or better performances with previous state-of-the-art methods.

cs.CL↗

arXiv2016

Research on Life Characteristics of Internet Based on Network Motifs

From biosystem to complex system,the study of life is always an important area. Inspired by hyper-cycle theory about the evolution of non-life system, we study the metabolism, self-replication and mutation behavior in the Internet based on node entity, connection relationship and function subgraph--motif--of network topology. Firstly a framework of complex network evolution is proposed to analyze the birth and death phenomena of Internet topology from January 1998 to August 2013. Then we find the Internet metabolism behavior from angle of node, motif to global topology, i.e. one born node is only added into Internet, subsequently takes part in the local reconstruction activities. Meanwhile there are nodes' and motifs' death. In process of the local reconstruction, although the Internet system replicates motifs repeatedly by adding or removing actions, the system characteristics and global structure are not destroyed. Statistics about the motif M3 which is a full connectivity subgraph shows that the process of its metabolism is fluctuation that causes mutation of Internet. Furthermore we find that mutation is instinctive reaction of Internet when it's influenced from inside or outside environment, such as Internet bubble, social network rising and finance crisis. The behaviors of metabolism, self-replication and mutation of Internet indicate its life characteristic as a complex artificial life. And our work will inspire people to study the life-like phenomena of other complex systems from angle of topology structure.

cs.NI↗

arXiv2016

A Novel Bilingual Word Embedding Method for Lexical Translation Using Bilingual Sense Clique

Most of the existing methods for bilingual word embedding only consider shallow context or simple co-occurrence information. In this paper, we propose a latent bilingual sense unit (Bilingual Sense Clique, BSC), which is derived from a maximum complete sub-graph of pointwise mutual information based graph over bilingual corpus. In this way, we treat source and target words equally and a separated bilingual projection processing that have to be used in most existing works is not necessary any more. Several dimension reduction methods are evaluated to summarize the BSC-word relationship. The proposed method is evaluated on bilingual lexicon translation tasks and empirical results show that bilingual sense embedding methods outperform existing bilingual word embedding methods.

cs.CL↗

arXiv2016

Connecting Phrase based Statistical Machine Translation Adaptation

Although more additional corpora are now available for Statistical Machine Translation (SMT), only the ones which belong to the same or similar domains with the original corpus can indeed enhance SMT performance directly. Most of the existing adaptation methods focus on sentence selection. In comparison, phrase is a smaller and more fine grained unit for data selection, therefore we propose a straightforward and efficient connecting phrase based adaptation method, which is applied to both bilingual phrase pair and monolingual n-gram adaptation. The proposed method is evaluated on IWSLT/NIST data sets, and the results show that phrase based SMT performance are significantly improved (up to +1.6 in comparison with phrase based SMT baseline system and +0.9 in comparison with existing methods).

cs.CL↗

arXiv2015

A Unified Tagging Solution: Bidirectional LSTM Recurrent Neural Network with Word Embedding

Bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN) has been shown to be very effective for modeling and predicting sequential data, e.g. speech utterances or handwritten documents. In this study, we propose to use BLSTM-RNN for a unified tagging solution that can be applied to various tagging tasks including part-of-speech tagging, chunking and named entity recognition. Instead of exploiting specific features carefully optimized for each task, our solution only uses one set of task-independent features and internal representations learnt from unlabeled text for all tasks.Requiring no task specific knowledge or sophisticated feature engineering, our approach gets nearly state-of-the-art performance in all these three tagging tasks.

cs.CL↗

arXiv2015

Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network

Bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN) has been shown to be very effective for tagging sequential data, e.g. speech utterances or handwritten documents. While word embedding has been demoed as a powerful representation for characterizing the statistical properties of natural language. In this study, we propose to use BLSTM-RNN with word embedding for part-of-speech (POS) tagging task. When tested on Penn Treebank WSJ test set, a state-of-the-art performance of 97.40 tagging accuracy is achieved. Without using morphological features, this approach can also achieve a good performance comparable with the Stanford POS tagger.

cs.CL↗

arXiv2015

Probabilistic Models for High-Order Projective Dependency Parsing

This paper presents generalized probabilistic models for high-order projective dependency parsing and an algorithmic framework for learning these statistical models involving dependency trees. Partition functions and marginals for high-order dependency trees can be computed efficiently, by adapting our algorithms which extend the inside-outside algorithm to higher-order cases. To show the effectiveness of our algorithms, we perform experiments on three languages---English, Chinese and Czech, using maximum conditional likelihood estimation for model training and L-BFGS for parameter estimation. Our methods achieve competitive performance for English, and outperform all previously reported dependency parsers for Chinese and Czech.

cs.CL↗

arXiv2014

Improving controllability of complex networks by rewiring links regularly

Network science have constantly been in the focus of research for the last decade, with considerable advances in the controllability of their structural. However, much less effort has been devoted to study that how to improve the controllability of complex networks. In this paper, a new algorithm is proposed to improve the controllability of complex networks by rewiring links regularly which transforms the network structure. Then it is demonstrated that our algorithm is very effective after numerical simulation experiment on typical network models (Erdös-Rényi and scale-free network). We find that our algorithm is mainly determined by the average degree and positive correlation of in-degree and out-degree of network and it has nothing to do with the network size. Furthermore, we analyze and discuss the correlation between controllability of complex networks and degree distribution index: power-law exponent and heterogeneity

eess.SY↗

arXiv2014

Integrative Semantic Dependency Parsing via Efficient Large-scale Feature Selection

Semantic parsing, i.e., the automatic derivation of meaning representation such as an instantiated predicate-argument structure for a sentence, plays a critical role in deep processing of natural language. Unlike all other top systems of semantic dependency parsing that have to rely on a pipeline framework to chain up a series of submodels each specialized for a specific subtask, the one presented in this article integrates everything into one model, in hopes of achieving desirable integrity and practicality for real applications while maintaining a competitive performance. This integrative approach tackles semantic parsing as a word pair classification problem using a maximum entropy classifier. We leverage adaptive pruning of argument candidates and large-scale feature selection engineering to allow the largest feature space ever in use so far in this field, it achieves a state-of-the-art performance on the evaluation data set for CoNLL-2008 shared task, on top of all but one top pipeline system, confirming its feasibility and effectiveness.

cs.CL↗