Total: 93
In this paper, we study the problem of addressee and response selection in multi-party conversations. Understanding multi-party conversations is challenging because of complex speaker interactions: multiple speakers exchange messages with each other, playing different roles (sender, addressee, observer), and these roles vary across turns. To tackle this challenge, we propose the Speaker Interaction Recurrent Neural Network (SI-RNN). Whereas the previous state-of-the-art system updated speaker embeddings only for the sender, SI-RNN uses a novel dialog encoder to update speaker embeddings in a role-sensitive way. Additionally, unlike the previous work that selected the addressee and response separately, SI-RNN selects them jointly by viewing the task as a sequence prediction problem. Experimental results show that SI-RNN significantly improves the accuracy of addressee and response selection, particularly in complex conversations with many speakers and responses to distant messages many turns in the past.
It is difficult to train a personalized task-oriented dialogue system because the data collected from each individual is often insufficient. Personalized dialogue systems trained on a small dataset is likely to overfit and make it difficult to adapt to different user needs. One way to solve this problem is to consider a collection of multiple users as a source domain and an individual user as a target domain, and to perform transfer learning from the source domain to the target domain. By following this idea, we propose a PErsonalized Task-oriented diALogue (PETAL) system, a transfer reinforcement learning framework based on POMDP, to construct a personalized dialogue system. The PETAL system first learns common dialogue knowledge from the source domain and then adapts this knowledge to the target domain. The proposed PETAL system can avoid the negative transfer problem by considering differences between the source and target users in a personalized Q-function. Experimental results on a real-world coffee-shopping data and simulation data show that the proposed PETAL system can learn optimal policies for different users, and thus effectively improve the dialogue quality under the personalized setting.
Representing the semantics of words is a long-standing problem for the natural language processing community. Most methods compute word semantics given their textual context in large corpora. More recently, researchers attempted to integrate perceptual and visual features. Most of these works consider the visual appearance of objects to enhance word representations but they ignore the visual environment and context in which objects appear. We propose to unify text-based techniques with vision-based techniques by simultaneously leveraging textual and visual context to learn multimodal word embeddings. We explore various choices for what can serve as a visual context and present an end-to-end method to integrate visual context elements in a multimodal skip-gram model. We provide experiments and extensive analysis of the obtained results.
Automatically scoring metaphor novelty has been largely unexplored, but could be of benefit to a wide variety of NLP applications. We introduce a large, publicly available metaphor novelty dataset to stimulate research in this area, and propose a regression-based approach to automatically score the novelty of potential metaphors that are expressed as word pairs. We additionally investigate which types of features are most useful for this task, and show that our approach outperforms baseline metaphor novelty scoring and standard metaphor detection approaches on this task.
Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable computation, significantly less training time, and flexibility in modeling dependencies. We propose a novel attention mechanism in which the attention between elements from input sequence(s) is directional and multi-dimensional (i.e., feature-wise). A light-weight neural net, "Directional Self-Attention Network (DiSAN)," is then proposed to learn sentence embedding, based solely on the proposed attention without any RNN/CNN structure. DiSAN is only composed of a directional self-attention with temporal order encoded, followed by a multi-dimensional attention that compresses the sequence into a vector representation. Despite its simple form, DiSAN outperforms complicated RNN models on both prediction quality and time efficiency. It achieves the best test accuracy among all sentence encoding methods and improves the most recent best result by 1.02% on the Stanford Natural Language Inference (SNLI) dataset, and shows state-of-the-art test accuracy on the Stanford Sentiment Treebank (SST), Multi-Genre natural language inference (MultiNLI), Sentences Involving Compositional Knowledge (SICK), Customer Review, MPQA, TREC question-type classification and Subjectivity (SUBJ) datasets.
Representing the semantics of words is a fundamental task in text processing. Several research studies have shown that text and knowledge bases (KBs) are complementary sources for word embedding learning. Most existing methods only consider relationships within word-pairs in the usage of KBs. We argue that the structural information of well-organized words within the KBs is able to convey more effective and stable knowledge in capturing semantics of words. In this paper, we propose a semantic structure-based word embedding method, and introduce concept convergence and word divergence to reveal semantic structures in the word embedding learning process. To assess the effectiveness of our method, we use WordNet for training and conduct extensive experiments on word similarity, word analogy, text classification and query expansion. The experimental results show that our method outperforms state-of-the-art methods, including the methods trained solely on the corpus, and others trained on the corpus and the KBs.
We study response generation for open domain conversation in chatbots. Existing methods assume that words in responses are generated from an identical vocabulary regardless of their inputs, which not only makes them vulnerable to generic patterns and irrelevant noise, but also causes a high cost in decoding. We propose a dynamic vocabulary sequence-to-sequence (DVS2S) model which allows each input to possess their own vocabulary in decoding. In training, vocabulary construction and response generation are jointly learned by maximizing a lower bound of the true objective with a Monte Carlo sampling method. In inference, the model dynamically allocates a small vocabulary for an input with the word prediction model, and conducts decoding only with the small vocabulary. Because of the dynamic vocabulary mechanism, DVS2S eludes many generic patterns and irrelevant words in generation, and enjoys efficient decoding at the same time. Experimental results on both automatic metrics and human annotations show that DVS2S can significantly outperform state-of-the-art methods in terms of response quality, but only requires 60% decoding time compared to the most efficient baseline.
In this paper, we present a generative model to generate a natural language sentence describing a table region, e.g., a row. The model maps a row from a table to a continuous vector and then generates a natural language sentence by leveraging the semantics of a table. To deal with rare words appearing in a table, we develop a flexible copying mechanism that selectively replicates contents from the table in the output sequence. Extensive experiments demonstrate the accuracy of the model and the power of the copying mechanism. On two synthetic datasets, WIKIBIO and SIMPLEQUESTIONS, our model improves the current state-of-the-art BLEU-4 score from 34.70 to 40.26 and from 33.32 to 39.12, respectively. Furthermore, we introduce an open-domain dataset WIKITABLETEXT including 13,318 explanatory sentences for 4,962 tables. Our model achieves a BLEU-4 score of 38.23, which outperforms template based and language model based approaches.
While the incipient internet was largely text-based, the modern digital world is becoming increasingly multi-modal. Here, we examine multi-modal classification where one modality is discrete, e.g. text, and the other is continuous, e.g. visual representations transferred from a convolutional neural network. In particular, we focus on scenarios where we have to be able to classify large quantities of data quickly. We investigate various methods for performing multi-modal fusion and analyze their trade-offs in terms of classification accuracy and computational efficiency. Our findings indicate that the inclusion of continuous information improves performance over text-only on a range of multi-modal classification tasks, even with simple fusion methods. In addition, we experiment with discretizing the continuous features in order to speed up and simplify the fusion process even further. Our results show that fusion with discretized features outperforms text-only classification, at a fraction of the computational cost of full multi-modal fusion, with the additional benefit of improved interpretability.
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as ε-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail.
Generating texts from structured data (e.g., a table) is important for various natural language processing tasks such as question answering and dialog systems. In recent studies, researchers use neural language models and encoder-decoder frameworks for table-to-text generation. However, these neural network-based approaches typically do not model the order of content during text generation. When a human writes a summary based on a given table, he or she would probably consider the content order before wording. In this paper, we propose an order-planning text generation model, where order information is explicitly captured by link-based attention. Then a self-adaptive gate combines the link-based attention with traditional content-based attention. We conducted experiments on the WikiBio dataset and achieve higher performance than previous methods in terms of BLEU, ROUGE, and NIST scores; we also performed ablation tests to analyze each component of our model.
Text matching is a core issue for question answering (QA), information retrieval (IR) and many other fields. We propose to reformulate the original text, i.e., generating a new text that is semantically equivalent to original text, to improve text matching degree. Intuitively, the generated text improves mutual information between two text sequences. We employ the generative adversarial network as the reformulation model where there is a discriminator to guide the text generating process. In this work, we focus on matching question and answers. The task is to rank answers based on QA matching degree. We first reformulate the original question without changing the asker's intent, then compute a relevance score for each answer. To evaluate the method, we collected questions and answers from Zhihu. In addition, we also conduct substantial experiments on public data such as SemEval and WikiQA to compare our method with existing methods. Experimental results demonstrate that after adding the reformulated question, the ranking performance across different matching models can be improved consistently, indicating that the reformulated question has enhanced mutual information and effectively bridged the semantic gap between QA.
Long text brings a big challenge to neural network based text matching approaches due to their complicated structures. To tackle the challenge, we propose a knowledge enhanced hybrid neural network (KEHNN) that leverages prior knowledge to identify useful information and filter out noise in long text and performs matching from multiple perspectives. The model fuses prior knowledge into word representations by knowledge gates and establishes three matching channels with words, sequential structures of text given by Gated Recurrent Units (GRUs), and knowledge enhanced representations. The three channels are processed by a convolutional neural network to generate high level features for matching, and the features are synthesized as a matching score by a multilayer perceptron. In this paper, we focus on exploring the use of taxonomy knowledge for text matching. Evaluation results from extensive experiments on public data sets of question answering and conversation show that KEHNN can significantly outperform state-of-the-art matching models and particularly improve matching accuracy on pairs with long text.
Sentence relation extraction aims to extract relational facts from sentences, which is an important task in natural language processing field. Previous models rely on the manually labeled supervised dataset. However, the human annotation is costly and limits to the number of relation and data size, which is difficult to scale to large domains. In order to conduct largely scaled relation extraction, we utilize an existing knowledge base to heuristically align with texts, which not rely on human annotation and easy to scale. However, using distant supervised data for relation extraction is facing a new challenge: sentences in the distant supervised dataset are not directly labeled and not all sentences that mentioned an entity pair can represent the relation between them. To solve this problem, we propose a novel model with reinforcement learning. The relation of the entity pair is used as distant supervision and guide the training of relation extractor with the help of reinforcement learning method. We conduct two types of experiments on a publicly released dataset. Experiment results demonstrate the effectiveness of the proposed method compared with baseline models, which achieves 13.36\% improvement.
We introduce the Attentive Unsupervised Text (W)riter (AUTR), which is a word level generative model for natural language. It uses a recurrent neural network with a dynamic attention and canvas memory mechanism to iteratively construct sentences. By viewing the state of the memory at intermediate stages and where the model is placing its attention, we gain insight into how it constructs sentences. We demonstrate that AUTR learns a meaningful latent representation for each sentence, and achieves competitive log-likelihood lower bounds whilst being computationally efficient. It is effective at generating and reconstructing sentences, as well as imputing missing words.
We describe an intelligent context-aware conversational system that incorporates screen context information to service multimodal user requests. Screen content is used for disambiguation of utterances that refer to screen objects and for enabling the user to act upon screen objects using voice commands. We propose a deep learning architecture that jointly models the user utterance and the screen and incorporates detailed screen content features. Our model is trained to optimize end to end semantic accuracy across contextual and non-contextual functionality, therefore learns the desired behavior directly from the data. We show that this approach outperforms a rule-based alternative, and can be extended in a straightforward manner to new contextual use cases. We perform detailed evaluation of contextual and non-contextual use cases and show that our system displays accurate contextual behavior without degrading the performance of non-contextual user requests.
In this study we formulate the problem of conversational model adaptation, where we aim to build a generative conversational model for a target domain based on a limited amount of dialogue data from this target domain and some existing dialogue models from related source domains. This model facilitates the fast building of a chatbot platform, where a new vertical chatbot with only a small number of conversation data can be supported by other related mature chatbots. Previous studies on model adaptation and transfer learning mostly focus on classification and recommendation problems, however, how these models work for conversation generation are still unexplored. To this end, we leverage a KL divergence (KLD) regularization to adapt the existing conversational models. Specifically, it employs the KLD to measure the distance between source and target domain. Adding KLD as a regularization to the objective function allows the proposed method to utilize the information from source domains effectively. We also evaluate the performance of this adaptation model for the online chatbots in Wechat platform of public accounts using both the BLEU metric and human judgement. The experiments empirically show that the proposed method visibly improves these evaluation metrics.
Neural models aiming at generating meaningful and diverse response is attracting increasing attention over recent years. For a given post, the conventional encoder-decoder models tend to learn high-frequency but trivial responses, or are difficult to determine which speaking styles are suitable to generate responses. To address this issue, we propose the elastic responding machine (ERM), which is based on a proposed encoder-diverter-filter-decoder framework. ERM models the multiple responding mechanisms to not only generate acceptable responses for a given post but also improve the diversity of responses. Here, the mechanisms could be regraded as some latent variables, and for a given post different responses may be generated by different mechanisms. The experiments demonstrate the quality and diversity of the generated responses, intuitively show how the learned model controls response mechanism when responding, and reveal some underlying relationship between mechanism and language style.
An emotionally-competent computer agent could be a valuable assistive technology in performing various affective tasks. For example caring for the elderly, low-cost ubiquitous chat therapy, and providing emotional support in general, by promoting a more positive emotional state through dialogue system interaction. However, despite the increase of interest in this task, existing works face a number of shortcomings: system scalability, restrictive modeling, and weak emphasis on maximizing user emotional experience. In this paper, we build a fully data driven chat-oriented dialogue system that can dynamically mimic affective human interactions by utilizing a neural network architecture. In particular, we propose a sequence-to-sequence response generator that considers the emotional context of the dialogue. An emotion encoder is trained jointly with the entire network to encode and maintain the emotional context throughout the dialogue. The encoded emotion information is then incorporated in the response generation process. We train the network with a dialogue corpus that contains positive-emotion eliciting responses, collected through crowd-sourcing. Objective evaluation shows that incorporation of emotion into the training process helps reduce the perplexity of the generated responses, even when a small dataset is used. Subsequent subjective evaluation shows that the proposed method produces responses that are more natural and likely to elicit a more positive emotion.
Paraphrase generation is an important problem in NLP, especially in question answering, information retrieval, information extraction, conversation systems, to name a few. In this paper, we address the problem of generating paraphrases automatically. Our proposed method is based on a combination of deep generative models (VAE) with sequence-to-sequence models (LSTM) to generate paraphrases, given an input sentence. Traditional VAEs when combined with recurrent neural networks can generate free text but they are not suitable for paraphrase generation for a given sentence. We address this problem by conditioning the both, encoder and decoder sides of VAE, on the original sentence, so that it can generate the given sentence's paraphrases. Unlike most existing models, our model is simple, modular and can generate multiple paraphrases, for a given sentence. Quantitative evaluation of the proposed method on a benchmark paraphrase dataset demonstrates its efficacy, and its performance improvement over the state-of-the-art methods by a significant margin, whereas qualitative human evaluation indicate that the generated paraphrases are well-formed, grammatically correct, and are relevant to the input sentence. Furthermore, we evaluate our method on a newly released question paraphrase dataset, and establish a new baseline for future research.
Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc. Recently, by combining with policy gradient, Generative Adversarial Nets(GAN) that use a discriminative model to guide the training of the generative model as a reinforcement learning policy has shown promising results in text generation. However, the scalar guiding signal is only available after the entire text has been generated and lacks intermediate information about text structure during the generative process. As such, it limits its success when the length of the generated text samples is long (more than 20 words). In this paper, we propose a new framework, called LeakGAN, to address the problem for long text generation. We allow the discriminative net to leak its own high-level extracted features to the generative net to further help the guidance. The generator incorporates such informative signals into all generation steps through an additional MANAGER module, which takes the extracted features of current generated words and outputs a latent vector to guide the WORKER module for next-word generation.Our extensive experiments on synthetic data and various real-world tasks with Turing test demonstrate that LeakGAN is highly effective in long text generation and also improves the performance in short text generation scenarios. More importantly, without any supervision, LeakGAN would be able to implicitly learn sentence structures only through the interaction between MANAGER and WORKER.
We describe a technique for structured prediction, based on canonical correlation analysis. Our learning algorithm finds two projections for the input and the output spaces that aim at projecting a given input and its correct output into points close to each other. We demonstrate our technique on a language-vision problem, namely the problem of giving a textual description to an "abstract scene".
In recent years, deep neural networks have achieved significant success in Chinese word segmentation and many other natural language processing tasks. Most of these algorithms are end-to-end trainable systems and can effectively process and learn from large scale labeled datasets. However, these methods typically lack the capability of processing rare words and data whose domains are different from training data. Previous statistical methods have demonstrated that human knowledge can provide valuable information for handling rare cases and domain shifting problems. In this paper, we seek to address the problem of incorporating dictionaries into neural networks for the Chinese word segmentation task. Two different methods that extend the bi-directional long short-term memory neural network are proposed to perform the task. To evaluate the performance of the proposed methods, state-of-the-art supervised models based methods and domain adaptation approaches are compared with our methods on nine datasets from different domains. The experimental results demonstrate that the proposed methods can achieve better performance than other state-of-the-art neural network methods and domain adaptation approaches in most cases.
Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and decoding, yielding the KL-vanishing problem and inconsistent training objective. In this paper, we separate the training step into two phases: The first phase learns to autoencode discrete texts into continuous embeddings, from which the second phase learns to generalize latent representations by reconstructing the encoded embedding. In this case, latent variables are sampled by transforming Gaussian noise through multi-layer perceptrons and are trained with a separate VED model, which has the potential of realizing a much more flexible distribution. We compare our model with current popular models and the experiment demonstrates substantial improvement in both metric-based and human evaluations.
Knowing the correct distribution of senses within a corpus can potentially boost the performance of Word Sense Disambiguation (WSD) systems by many points. We present two fully automatic and language-independent methods for computing the distribution of senses given a raw corpus of sentences. Intrinsic and extrinsic evaluations show that our methods outperform the current state of the art in sense distribution learning and the strongest baselines for the most frequent sense in multiple languages and on domain-specific test sets. Our sense distributions are available at http://trainomatic.org.