arXiv subjects

Yanyan Lan

Publications and source records attributed to Yanyan Lan.

At least 91 records · Page 5Linked to original sources

arXiv2019

Neural or Statistical: An Empirical Study on Language Models for Chinese Input Recommendation on Mobile

Chinese input recommendation plays an important role in alleviating human cost in typing Chinese words, especially in the scenario of mobile applications. The fundamental problem is to predict the conditional probability of the next word given the sequence of previous words. Therefore, statistical language models, i.e.~n-grams based models, have been extensively used on this task in real application. However, the characteristics of extremely different typing behaviors usually lead to serious sparsity problem, even n-gram with smoothing will fail. A reasonable approach to tackle this problem is to use the recently proposed neural models, such as probabilistic neural language model, recurrent neural network and word2vec. They can leverage more semantically similar words for estimating the probability. However, there is no conclusion on which approach of the two will work better in real application. In this paper, we conduct an extensive empirical study to show the differences between statistical and neural language models. The experimental results show that the two different approach have individual advantages, and a hybrid approach will bring a significant improvement.

cs.CL↗

arXiv2019

Outline Generation: Understanding the Inherent Content Structure of Documents

In this paper, we introduce and tackle the Outline Generation (OG) task, which aims to unveil the inherent content structure of a multi-paragraph document by identifying its potential sections and generating the corresponding section headings. Without loss of generality, the OG task can be viewed as a novel structured summarization task. To generate a sound outline, an ideal OG model should be able to capture three levels of coherence, namely the coherence between context paragraphs, that between a section and its heading, and that between context headings. The first one is the foundation for section identification, while the latter two are critical for consistent heading generation. In this work, we formulate the OG task as a hierarchical structured prediction problem, i.e., to first predict a sequence of section boundaries and then a sequence of section headings accordingly. We propose a novel hierarchical structured neural generation model, named HiStGen, for the task. Our model attempts to capture the three-level coherence via the following ways. First, we introduce a Markov paragraph dependency mechanism between context paragraphs for section identification. Second, we employ a section-aware attention mechanism to ensure the semantic coherence between a section and its heading. Finally, we leverage a Markov heading dependency mechanism and a review mechanism between context headings to improve the consistency and eliminate duplication between section headings. Besides, we build a novel WIKIOG dataset, a public collection which consists of over 1.75 million document-outline pairs for research on the OG task. Experimental results on our benchmark dataset demonstrate that our model can significantly outperform several state-of-the-art sequential generation models for the OG task.

cs.CL↗

arXiv2019

HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering

This paper is concerned with open-domain question answering (i.e., OpenQA). Recently, some works have viewed this problem as a reading comprehension (RC) task, and directly applied successful RC models to it. However, the performances of such models are not so good as that in the RC task. In our opinion, the perspective of RC ignores three characteristics in OpenQA task: 1) many paragraphs without the answer span are included in the data collection; 2) multiple answer spans may exist within one given paragraph; 3) the end position of an answer span is dependent with the start position. In this paper, we first propose a new probabilistic formulation of OpenQA, based on a three-level hierarchical structure, i.e.,~the question level, the paragraph level and the answer span level. Then a Hierarchical Answer Spans Model (HAS-QA) is designed to capture each probability. HAS-QA has the ability to tackle the above three problems, and experiments on public OpenQA datasets show that it significantly outperforms traditional RC baselines and recent OpenQA baselines.

cs.CL↗

arXiv2018

Beyond Precision: A Study on Recall of Initial Retrieval with Neural Representations

Vocabulary mismatch is a central problem in information retrieval (IR), i.e., the relevant documents may not contain the same (symbolic) terms of the query. Recently, neural representations have shown great success in capturing semantic relatedness, leading to new possibilities to alleviate the vocabulary mismatch problem in IR. However, most existing efforts in this direction have been devoted to the re-ranking stage. That is to leverage neural representations to help re-rank a set of candidate documents, which are typically obtained from an initial retrieval stage based on some symbolic index and search scheme (e.g., BM25 over the inverted index). This naturally raises a question: if the relevant documents have not been found in the initial retrieval stage due to vocabulary mismatch, there would be no chance to re-rank them to the top positions later. Therefore, in this paper, we study the problem how to employ neural representations to improve the recall of relevant documents in the initial retrieval stage. Specifically, to meet the efficiency requirement of the initial stage, we introduce a neural index for the neural representations of documents, and propose two hybrid search schemes based on both neural and symbolic indices, namely the parallel search scheme and the sequential search scheme. Our experiments show that both hybrid index and search schemes can improve the recall of the initial retrieval stage with small overhead.

cs.IR↗

arXiv2018

A Tree Search Algorithm for Sequence Labeling

In this paper we propose a novel reinforcement learning based model for sequence tagging, referred to as MM-Tag. Inspired by the success and methodology of the AlphaGo Zero, MM-Tag formalizes the problem of sequence tagging with a Monte Carlo tree search (MCTS) enhanced Markov decision process (MDP) model, in which the time steps correspond to the positions of words in a sentence from left to right, and each action corresponds to assign a tag to a word. Two long short-term memory networks (LSTM) are used to summarize the past tag assignments and words in the sentence. Based on the outputs of LSTMs, the policy for guiding the tag assignment and the value for predicting the whole tagging accuracy of the whole sentence are produced. The policy and value are then strengthened with MCTS, which takes the produced raw policy and value as inputs, simulates and evaluates the possible tag assignments at the subsequent positions, and outputs a better search policy for assigning tags. A reinforcement learning algorithm is proposed to train the model parameters. Our work is the first to apply the MCTS enhanced MDP model to the sequence tagging task. We show that MM-Tag can accurately predict the tags thanks to the exploratory decision making mechanism introduced by MCTS. Experimental results show based on a chunking benchmark showed that MM-Tag outperformed the state-of-the-art sequence tagging baselines including CRF and CRF with LSTM.

cs.CL↗

arXiv2018

Modeling Diverse Relevance Patterns in Ad-hoc Retrieval

Assessing relevance between a query and a document is challenging in ad-hoc retrieval due to its diverse patterns, i.e., a document could be relevant to a query as a whole or partially as long as it provides sufficient information for users' need. Such diverse relevance patterns require an ideal retrieval model to be able to assess relevance in the right granularity adaptively. Unfortunately, most existing retrieval models compute relevance at a single granularity, either document-wide or passage-level, or use fixed combination strategy, restricting their ability in capturing diverse relevance patterns. In this work, we propose a data-driven method to allow relevance signals at different granularities to compete with each other for final relevance assessment. Specifically, we propose a HIerarchical Neural maTching model (HiNT) which consists of two stacked components, namely local matching layer and global decision layer. The local matching layer focuses on producing a set of local relevance signals by modeling the semantic matching between a query and each passage of a document. The global decision layer accumulates local signals into different granularities and allows them to compete with each other to decide the final relevance score. Experimental results demonstrate that our HiNT model outperforms existing state-of-the-art retrieval models significantly on benchmark ad-hoc retrieval datasets.

cs.IR↗

arXiv2018

MQGrad: Reinforcement Learning of Gradient Quantization in Parameter Server

One of the most significant bottleneck in training large scale machine learning models on parameter server (PS) is the communication overhead, because it needs to frequently exchange the model gradients between the workers and servers during the training iterations. Gradient quantization has been proposed as an effective approach to reducing the communication volume. One key issue in gradient quantization is setting the number of bits for quantizing the gradients. Small number of bits can significantly reduce the communication overhead while hurts the gradient accuracies, and vise versa. An ideal quantization method would dynamically balance the communication overhead and model accuracy, through adjusting the number bits according to the knowledge learned from the immediate past training iterations. Existing methods, however, quantize the gradients either with fixed number of bits, or with predefined heuristic rules. In this paper we propose a novel adaptive quantization method within the framework of reinforcement learning. The method, referred to as MQGrad, formalizes the selection of quantization bits as actions in a Markov decision process (MDP) where the MDP states records the information collected from the past optimization iterations (e.g., the sequence of the loss function values). During the training iterations of a machine learning algorithm, MQGrad continuously updates the MDP state according to the changes of the loss function. Based on the information, MDP learns to select the optimal actions (number of bits) to quantize the gradients. Experimental results based on a benchmark dataset showed that MQGrad can accelerate the learning of a large scale deep neural network while keeping its prediction accuracies.

cs.LG↗

arXiv2017

Locally Smoothed Neural Networks

Convolutional Neural Networks (CNN) and the locally connected layer are limited in capturing the importance and relations of different local receptive fields, which are often crucial for tasks such as face verification, visual question answering, and word sequence prediction. To tackle the issue, we propose a novel locally smoothed neural network (LSNN) in this paper. The main idea is to represent the weight matrix of the locally connected layer as the product of the kernel and the smoother, where the kernel is shared over different local receptive fields, and the smoother is for determining the importance and relations of different local receptive fields. Specifically, a multi-variate Gaussian function is utilized to generate the smoother, for modeling the location relations among different local receptive fields. Furthermore, the content information can also be leveraged by setting the mean and precision of the Gaussian function according to the content. Experiments on some variant of MNIST clearly show our advantages over CNN and locally connected layer.

cs.LG↗

arXiv2017

Learning Visual Features from Snapshots for Web Search

When applying learning to rank algorithms to Web search, a large number of features are usually designed to capture the relevance signals. Most of these features are computed based on the extracted textual elements, link analysis, and user logs. However, Web pages are not solely linked texts, but have structured layout organizing a large variety of elements in different styles. Such layout itself can convey useful visual information, indicating the relevance of a Web page. For example, the query-independent layout (i.e., raw page layout) can help identify the page quality, while the query-dependent layout (i.e., page rendered with matched query words) can further tell rich structural information (e.g., size, position and proximity) of the matching signals. However, such visual information of layout has been seldom utilized in Web search in the past. In this work, we propose to learn rich visual features automatically from the layout of Web pages (i.e., Web page snapshots) for relevance ranking. Both query-independent and query-dependent snapshots are considered as the new inputs. We then propose a novel visual perception model inspired by human's visual search behaviors on page viewing to extract the visual features. This model can be learned end-to-end together with traditional human-crafted features. We also show that such visual features can be efficiently acquired in the online setting with an extended inverted indexing scheme. Experiments on benchmark collections demonstrate that learning visual features from Web page snapshots can significantly improve the performance of relevance ranking in ad-hoc Web retrieval tasks.

cs.IR↗

arXiv2017

A Deep Investigation of Deep IR Models

The effective of information retrieval (IR) systems have become more important than ever. Deep IR models have gained increasing attention for its ability to automatically learning features from raw text; thus, many deep IR models have been proposed recently. However, the learning process of these deep IR models resemble a black box. Therefore, it is necessary to identify the difference between automatically learned features by deep IR models and hand-crafted features used in traditional learning to rank approaches. Furthermore, it is valuable to investigate the differences between these deep IR models. This paper aims to conduct a deep investigation on deep IR models. Specifically, we conduct an extensive empirical study on two different datasets, including Robust and LETOR4.0. We first compared the automatically learned features and hand-crafted features on the respects of query term coverage, document length, embeddings and robustness. It reveals a number of disadvantages compared with hand-crafted features. Therefore, we establish guidelines for improving existing deep IR models. Furthermore, we compare two different categories of deep IR models, i.e. representation-focused models and interaction-focused models. It is shown that two types of deep IR models focus on different categories of words, including topic-related words and query-related words.

cs.IR↗

arXiv2017

MatchZoo: A Toolkit for Deep Text Matching

In recent years, deep neural models have been widely adopted for text matching tasks, such as question answering and information retrieval, showing improved performance as compared with previous methods. In this paper, we introduce the MatchZoo toolkit that aims to facilitate the designing, comparing and sharing of deep text matching models. Specifically, the toolkit provides a unified data preparation module for different text matching problems, a flexible layer-based model construction process, and a variety of training objectives and evaluation metrics. In addition, the toolkit has implemented two schools of representative deep text matching models, namely representation-focused models and interaction-focused models. Finally, users can easily modify existing models, create and share their own models for text matching in MatchZoo.

cs.IR↗

arXiv2017

Spherical Paragraph Model

Representing texts as fixed-length vectors is central to many language processing tasks. Most traditional methods build text representations based on the simple Bag-of-Words (BoW) representation, which loses the rich semantic relations between words. Recent advances in natural language processing have shown that semantically meaningful representations of words can be efficiently acquired by distributed models, making it possible to build text representations based on a better foundation called the Bag-of-Word-Embedding (BoWE) representation. However, existing text representation methods using BoWE often lack sound probabilistic foundations or cannot well capture the semantic relatedness encoded in word vectors. To address these problems, we introduce the Spherical Paragraph Model (SPM), a probabilistic generative model based on BoWE, for text representation. SPM has good probabilistic interpretability and can fully leverage the rich semantics of words, the word co-occurrence information as well as the corpus-wide information to help the representation learning of texts. Experimental results on topical classification and sentiment analysis demonstrate that SPM can achieve new state-of-the-art performances on several benchmark datasets.

cs.CL↗

arXiv2016

Efficient Delivery Policy to Minimize User Traffic Consumption in Guaranteed Advertising

In this work, we study the guaranteed delivery model which is widely used in online display advertising. In the guaranteed delivery scenario, ad exposures (which are also called impressions in some works) to users are guaranteed by contracts signed in advance between advertisers and publishers. A crucial problem for the advertising platform is how to fully utilize the valuable user traffic to generate as much as possible revenue. Different from previous works which usually minimize the penalty of unsatisfied contracts and some other cost (e.g. representativeness), we propose the novel consumption minimization model, in which the primary objective is to minimize the user traffic consumed to satisfy all contracts. Under this model, we develop a near optimal method to deliver ads for users. The main advantage of our method lies in that it consumes nearly as least as possible user traffic to satisfy all contracts, therefore more contracts can be accepted to produce more revenue. It also enables the publishers to estimate how much user traffic is redundant or short so that they can sell or buy this part of traffic in bulk in the exchange market. Furthermore, it is robust with regard to priori knowledge of user type distribution. Finally, the simulation shows that our method outperforms the traditional state-of-the-art methods.

cs.DS↗

arXiv2016

A Study of MatchPyramid Models on Ad-hoc Retrieval

Deep neural networks have been successfully applied to many text matching tasks, such as paraphrase identification, question answering, and machine translation. Although ad-hoc retrieval can also be formalized as a text matching task, few deep models have been tested on it. In this paper, we study a state-of-the-art deep matching model, namely MatchPyramid, on the ad-hoc retrieval task. The MatchPyramid model employs a convolutional neural network over the interactions between query and document to produce the matching score. We conducted extensive experiments to study the impact of different pooling sizes, interaction functions and kernel sizes on the retrieval performance. Finally, we show that the MatchPyramid models can significantly outperform several recently introduced deep matching models on the retrieval task, but still cannot compete with the traditional retrieval models, such as BM25 and language models.

cs.IR↗

arXiv2016

Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN

Semantic matching, which aims to determine the matching degree between two texts, is a fundamental problem for many NLP applications. Recently, deep learning approach has been applied to this problem and significant improvements have been achieved. In this paper, we propose to view the generation of the global interaction between two texts as a recursive process: i.e. the interaction of two texts at each position is a composition of the interactions between their prefixes as well as the word level interaction at the current position. Based on this idea, we propose a novel deep architecture, namely Match-SRNN, to model the recursive matching structure. Firstly, a tensor is constructed to capture the word level interactions. Then a spatial RNN is applied to integrate the local interactions recursively, with importance determined by four types of gates. Finally, the matching score is calculated based on the global interaction. We show that, after degenerated to the exact matching scenario, Match-SRNN can approximate the dynamic programming process of longest common subsequence. Thus, there exists a clear interpretation for Match-SRNN. Our experiments on two semantic matching tasks showed the effectiveness of Match-SRNN, and its ability of visualizing the learned matching structure.

cs.CL↗

arXiv2016

Semantic Regularities in Document Representations

Recent work exhibited that distributed word representations are good at capturing linguistic regularities in language. This allows vector-oriented reasoning based on simple linear algebra between words. Since many different methods have been proposed for learning document representations, it is natural to ask whether there is also linear structure in these learned representations to allow similar reasoning at document level. To answer this question, we design a new document analogy task for testing the semantic regularities in document representations, and conduct empirical evaluations over several state-of-the-art document representation models. The results reveal that neural embedding based document representations work better on this analogy task than conventional methods, and we provide some preliminary explanations over these observations.

cs.CL↗

arXiv2016

Text Matching as Image Recognition

Matching two texts is a fundamental problem in many natural language processing tasks. An effective way is to extract meaningful matching patterns from words, phrases, and sentences to produce the matching score. Inspired by the success of convolutional neural network in image recognition, where neurons can capture many complicated patterns based on the extracted elementary visual patterns such as oriented edges and corners, we propose to model text matching as the problem of image recognition. Firstly, a matching matrix whose entries represent the similarities between words is constructed and viewed as an image. Then a convolutional neural network is utilized to capture rich matching patterns in a layer-by-layer way. We show that by resembling the compositional hierarchies of patterns in image recognition, our model can successfully identify salient signals such as n-gram and n-term matchings. Experimental results demonstrate its superiority against the baselines.

cs.CL↗

arXiv2015

A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations

Matching natural language sentences is central for many applications such as information retrieval and question answering. Existing deep models rely on a single sentence representation or multiple granularity representations for matching. However, such methods cannot well capture the contextualized local information in the matching process. To tackle this problem, we present a new deep architecture to match two sentences with multiple positional sentence representations. Specifically, each positional sentence representation is a sentence representation at this position, generated by a bidirectional long short term memory (Bi-LSTM). The matching score is finally produced by aggregating interactions between these different positional sentence representations, through $k$-Max pooling and a multi-layer perceptron. Our model has several advantages: (1) By using Bi-LSTM, rich context of the whole sentence is leveraged to capture the contextualized local information in each positional sentence representation; (2) By matching with multiple positional sentence representations, it is flexible to aggregate different important contextualized local information in a sentence to support the matching; (3) Experiments on different tasks such as question answering and sentence completion demonstrate the superiority of our model.

cs.AI↗