Total: 162
We propose a novel method for enriching word-embeddings without the need of a labeled corpus. Instead, we show that relying on a regressor – trained with a small lexicon to predict pseudo-labels – significantly improves performance over current techniques that rely on human-derived sentence-level labels for an entire corpora. Our approach enables enrichment for corpora that have no labels (such as Wikipedia). Exploring the utility of this general approach in both sentiment and non-sentiment-focused tasks, we show how enriching embeddings, for both Twitter and Wikipedia-based embeddings, provide notable improvements in performance for: binary sentiment classification, SemEval Tasks, embedding analogy task, and, document classification. Importantly, our approach is notably better and more generalizable than other state-of-the-art approaches for enriching both labeled and unlabeled corpora.
Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or introduce significant latency. We propose a compression method that leverages low rank matrix factorization during training, to compress the word embedding layer which represents the size bottleneck for most NLP models. Our models are trained, compressed and then further re-trained on the downstream task to recover accuracy while maintaining the reduced size. Empirically, we show that the proposed method can achieve 90% compression with minimal impact in accuracy for sentence classification tasks, and outperforms alternative methods like fixed-point quantization or offline word embedding compression. We also analyze the inference time and storage space for our method through FLOP calculations, showing that we can compress DNN models by a configurable ratio and regain accuracy loss without introducing additional latency compared to fixed point quantization. Finally, we introduce a novel learning rate schedule, the Cyclically Annealed Learning Rate (CALR), which we empirically demonstrate to outperform other popular adaptive learning rate algorithms on a sentence classification benchmark.
Distinguishing antonyms from synonyms is a key challenge for many NLP applications focused on the lexical-semantic relation extraction. Existing solutions relying on large-scale corpora yield low performance because of huge contextual overlap of antonym and synonym pairs. We propose a novel approach entirely based on pre-trained embeddings. We hypothesize that the pre-trained embeddings comprehend a blend of lexical-semantic information and we may distill the task-specific information using Distiller, a model proposed in this paper. Later, a classifier is trained based on features constructed from the distilled sub-spaces along with some word level features to distinguish antonyms from synonyms. Experimental results show that the proposed model outperforms existing research on antonym synonym distinction in both speed and performance.
Word sense induction (WSI), or the task of automatically discovering multiple senses or meanings of a word, has three main challenges: domain adaptability, novel sense detection, and sense granularity flexibility. While current latent variable models are known to solve the first two challenges, they are not flexible to different word sense granularities, which differ very much among words, from aardvark with one sense, to play with over 50 senses. Current models either require hyperparameter tuning or nonparametric induction of the number of senses, which we find both to be ineffective. Thus, we aim to eliminate these requirements and solve the sense granularity problem by proposing AutoSense, a latent variable model based on two observations: (1) senses are represented as a distribution over topics, and (2) senses generate pairings between the target word and its neighboring word. These observations alleviate the problem by (a) throwing garbage senses and (b) additionally inducing fine-grained word senses. Results show great improvements over the stateof-the-art models on popular WSI datasets. We also show that AutoSense is able to learn the appropriate sense granularity of a word. Finally, we apply AutoSense to the unsupervised author name disambiguation task where the sense granularity problem is more evident and show that AutoSense is evidently better than competing models. We share our data and code here: https://github.com/rktamplayo/AutoSense.
Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. ADEM (Lowe et al. 2017) formulated the automatic evaluation of dialogue systems as a learning problem and showed that such a model was able to predict responses which correlate significantly with human judgements, both at utterance and system level. Their system was shown to have beaten word-overlap metrics such as BLEU with large margins. We start with the question of whether an adversary can game the ADEM model. We design a battery of targeted attacks at the neural network based ADEM evaluation system and show that automatic evaluation of dialogue systems still has a long way to go. ADEM can get confused with a variation as simple as reversing the word order in the text! We report experiments on several such adversarial scenarios that draw out counterintuitive scores on the dialogue responses. We take a systematic look at the scoring function proposed by ADEM and connect it to linear system theory to predict the shortcomings evident in the system. We also devise an attack that can fool such a system to rate a response generation system as favorable. Finally, we allude to future research directions of using the adversarial attacks to design a truly automated dialogue evaluation system.
Considerable attention has recently been devoted to the problem of automatically extending knowledge bases by applying some form of inductive reasoning. While the vast majority of existing work is centred around so-called knowledge graphs, in this paper we consider a setting where the input consists of a set of (existential) rules. To this end, we exploit a vector space representation of the considered concepts, which is partly induced from the rule base itself and partly from a pre-trained word embedding. Inspired by recent approaches to concept induction, we then model rule templates in this vector space embedding using Gaussian distributions. Unlike many existing approaches, we learn rules by directly exploiting regularities in the given rule base, and do not require that a database with concept and relation instances is given. As a result, our method can be applied to a wide variety of ontologies. We present experimental results that demonstrate the effectiveness of our method.
The dominant approaches for named entity recognitionm (NER) mostly adopt complex recurrent neural networks (RNN), e.g., long-short-term-memory (LSTM). However, RNNs are limited by their recurrent nature in terms of computational efficiency. In contrast, convolutional neural networks (CNN) can fully exploit the GPU parallelism with their feedforward architectures. However, little attention has been paid to performing NER with CNNs, mainly owing to their difficulties in capturing the long-term context information in a sequence. In this paper, we propose a simple but effective CNN-based network for NER, i.e., gated relation network (GRN), which is more capable than common CNNs in capturing long-term context. Specifically, in GRN we firstly employ CNNs to explore the local context features of each word. Then we model the relations between words and use them as gates to fuse local context features into global ones for predicting labels. Without using recurrent layers that process a sentence in a sequential manner, our GRN allows computations to be performed in parallel across the entire sentence. Experiments on two benchmark NER datasets (i.e., CoNLL2003 and Ontonotes 5.0) show that, our proposed GRN can achieve state-of-the-art performance with or without external knowledge. It also enjoys lower time costs to train and test.
The ability to select an appropriate story ending is the first step towards perfect narrative comprehension. Story ending prediction requires not only the explicit clues within the context, but also the implicit knowledge (such as commonsense) to construct a reasonable and consistent story. However, most previous approaches do not explicitly use background commonsense knowledge. We present a neural story ending selection model that integrates three types of information: narrative sequence, sentiment evolution and commonsense knowledge. Experiments show that our model outperforms state-ofthe-art approaches on a public dataset, ROCStory Cloze Task (Mostafazadeh et al. 2017), and the performance gain from adding the additional commonsense knowledge is significant.
Short text classification is one of important tasks in Natural Language Processing (NLP). Unlike paragraphs or documents, short texts are more ambiguous since they have not enough contextual information, which poses a great challenge for classification. In this paper, we retrieve knowledge from external knowledge source to enhance the semantic representation of short texts. We take conceptual information as a kind of knowledge and incorporate it into deep neural networks. For the purpose of measuring the importance of knowledge, we introduce attention mechanisms and propose deep Short Text Classification with Knowledge powered Attention (STCKA). We utilize Concept towards Short Text (CST) attention and Concept towards Concept Set (C-CS) attention to acquire the weight of concepts from two aspects. And we classify a short text with the help of conceptual information. Unlike traditional approaches, our model acts like a human being who has intrinsic ability to make decisions based on observation (i.e., training data for machines) and pays more attention to important knowledge. We also conduct extensive experiments on four public datasets for different tasks. The experimental results and case studies show that our model outperforms the state-of-the-art methods, justifying the effectiveness of knowledge powered attention.
In this paper, we propose an approach for transferring the knowledge of a neural model for sequence labeling, learned from the source domain, to a new model trained on a target domain, where new label categories appear. Our transfer learning (TL) techniques enable to adapt the source model using the target data and new categories, without accessing to the source data. Our solution consists in adding new neurons in the output layer of the target model and transferring parameters from the source model, which are then fine-tuned with the target data. Additionally, we propose a neural adapter to learn the difference between the source and the target label distribution, which provides additional important information to the target model. Our experiments on Named Entity Recognition show that (i) the learned knowledge in the source model can be effectively transferred when the target data contains new categories and (ii) our neural adapter further improves such transfer.
Keyphrase generation (KG) aims to generate a set of keyphrases given a document, which is a fundamental task in natural language processing (NLP). Most previous methods solve this problem in an extractive manner, while recently, several attempts are made under the generative setting using deep neural networks. However, the state-of-the-art generative methods simply treat the document title and the document main body equally, ignoring the leading role of the title to the overall document. To solve this problem, we introduce a new model called Title-Guided Network (TG-Net) for automatic keyphrase generation task based on the encoderdecoder architecture with two new features: (i) the title is additionally employed as a query-like input, and (ii) a titleguided encoder gathers the relevant information from the title to each word in the document. Experiments on a range of KG datasets demonstrate that our model outperforms the state-of-the-art models with a large margin, especially for documents with either very low or very high title length ratios.
Machine Reading Comprehension (MRC) with multiplechoice questions requires the machine to read given passage and select the correct answer among several candidates. In this paper, we propose a novel approach called Convolutional Spatial Attention (CSA) model which can better handle the MRC with multiple-choice questions. The proposed model could fully extract the mutual information among the passage, question, and the candidates, to form the enriched representations. Furthermore, to merge various attention results, we propose to use convolutional operation to dynamically summarize the attention values within the different size of regions. Experimental results show that the proposed model could give substantial improvements over various state-of- the-art systems on both RACE and SemEval-2018 Task11 datasets.
Implicit arguments, which cannot be detected solely through syntactic cues, make it harder to extract predicate-argument tuples. We present a new model for implicit argument prediction that draws on reading comprehension, casting the predicate-argument tuple with the missing argument as a query. We also draw on pointer networks and multi-hop computation. Our model shows good performance on an argument cloze task as well as on a nominal implicit argument prediction task.
In encoder-decoder based sequence-to-sequence modeling, the most common practice is to stack a number of recurrent, convolutional, or feed-forward layers in the encoder and decoder. While the addition of each new layer improves the sequence generation quality, this also leads to a significant increase in the number of parameters. In this paper, we propose to share parameters across all layers thereby leading to a recurrently stacked sequence-to-sequence model. We report on an extensive case study on neural machine translation (NMT) using our proposed method, experimenting with a variety of datasets. We empirically show that the translation quality of a model that recurrently stacks a single-layer 6 times, despite its significantly fewer parameters, approaches that of a model that stacks 6 different layers. We also show how our method can benefit from a prevalent way for improving NMT, i.e., extending training data with pseudo-parallel corpora generated by back-translation. We then analyze the effects of recurrently stacked layers by visualizing the attentions of models that use recurrently stacked layers and models that do not. Finally, we explore the limits of parameter sharing where we share even the parameters between the encoder and decoder in addition to recurrent stacking of layers.
Joint entity and relation extraction is to detect entity and relation using a single model. In this paper, we present a novel unified joint extraction model which directly tags entity and relation labels according to a query word position p, i.e., detecting entity at p, and identifying entities at other positions that have relationship with the former. To this end, we first design a tagging scheme to generate n tag sequences for an n-word sentence. Then a position-attention mechanism is introduced to produce different sentence representations for every query position to model these n tag sequences. In this way, our method can simultaneously extract all entities and their type, as well as all overlapping relations. Experiment results show that our framework performances significantly better on extracting overlapping relations as well as detecting long-range relation, and thus we achieve state-of-the-art performance on two public datasets.
Despite the remarkable evolution of deep neural networks in natural language processing (NLP), their interpretability remains a challenge. Previous work largely focused on what these models learn at the representation level. We break this analysis down further and study individual dimensions (neurons) in the vector representation learned by end-to-end neural models in NLP tasks. We propose two methods: Linguistic Correlation Analysis, based on a supervised method to extract the most relevant neurons with respect to an extrinsic task, and Cross-model Correlation Analysis, an unsupervised method to extract salient neurons w.r.t. the model itself. We evaluate the effectiveness of our techniques by ablating the identified neurons and reevaluating the network’s performance for two tasks: neural machine translation (NMT) and neural language modeling (NLM). We further present a comprehensive analysis of neurons with the aim to address the following questions: i) how localized or distributed are different linguistic properties in the models? ii) are certain neurons exclusive to some properties and not others? iii) is the information more or less distributed in NMT vs. NLM? and iv) how important are the neurons identified through the linguistic correlation method to the overall task? Our code is publicly available as part of the NeuroX toolkit (Dalvi et al. 2019a). This paper is a non-archived version of the paper published at AAAI (Dalvi et al. 2019b).
Answer selection and knowledge base question answering (KBQA) are two important tasks of question answering (QA) systems. Existing methods solve these two tasks separately, which requires large number of repetitive work and neglects the rich correlation information between tasks. In this paper, we tackle answer selection and KBQA tasks simultaneously via multi-task learning (MTL), motivated by the following motivations. First, both answer selection and KBQA can be regarded as a ranking problem, with one at text-level while the other at knowledge-level. Second, these two tasks can benefit each other: answer selection can incorporate the external knowledge from knowledge base (KB), while KBQA can be improved by learning contextual information from answer selection. To fulfill the goal of jointly learning these two tasks, we propose a novel multi-task learning scheme that utilizes multi-view attention learned from various perspectives to enable these tasks to interact with each other as well as learn more comprehensive sentence representations. The experiments conducted on several real-world datasets demonstrate the effectiveness of the proposed method, and the performance of answer selection and KBQA is improved. Also, the multi-view attention scheme is proved to be effective in assembling attentive information from different representational perspectives.
Temporal word embeddings have been proposed to support the analysis of word meaning shifts during time and to study the evolution of languages. Different approaches have been proposed to generate vector representations of words that embed their meaning during a specific time interval. However, the training process used in these approaches is complex, may be inefficient or it may require large text corpora. As a consequence, these approaches may be difficult to apply in resource-scarce domains or by scientists with limited in-depth knowledge of embedding models. In this paper, we propose a new heuristic to train temporal word embeddings based on the Word2vec model. The heuristic consists in using atemporal vectors as a reference, i.e., as a compass, when training the representations specific to a given time interval. The use of the compass simplifies the training process and makes it more efficient. Experiments conducted using state-of-the-art datasets and methodologies suggest that our approach outperforms or equals comparable approaches while being more robust in terms of the required corpus size.
Recognizing time expressions is a fundamental and important task in many applications of natural language understanding, such as reading comprehension and question answering. Several newest state-of-the-art approaches have achieved good performance on recognizing time expressions. These approaches are black-boxed or based on heuristic rules, which leads to the difficulty in understanding the temporal information. On the contrary, classic rule-based or semantic parsing approaches can capture rich structural information, but their performances on recognition are not so good. In this paper, we propose a pattern-based approach, called PTime, which automatically generates and selects patterns for recognizing time expressions. In this approach, time expressions in training text are abstracted into type sequences by using fine-grained token types, thus the problem is transformed to select an appropriate subset of the sequential patterns. We use the Extended Budgeted Maximum Coverage (EBMC) model to optimize the pattern selection. The main idea is to maximize the correct token sequences matched by the selected patterns while the number of the mistakes should be limited by an adjustable budget. The interpretability of patterns and the adjustability of permitted number of mistakes make PTime a very promising approach for many applications. Experimental results show that PTime achieves a very competitive performance as compared with existing state-of-the-art approaches.
Emotion cause identification aims at identifying the potential causes that lead to a certain emotion expression in text. Several techniques including rule based methods and traditional machine learning methods have been proposed to address this problem based on manually designed rules and features. More recently, some deep learning methods have also been applied to this task, with the attempt to automatically capture the causal relationship of emotion and its causes embodied in the text. In this work, we find that in addition to the content of the text, there are another two kinds of information, namely relative position and global labels, that are also very important for emotion cause identification. To integrate such information, we propose a model based on the neural network architecture to encode the three elements (i.e., text content, relative position and global label), in an unified and end-to-end fashion. We introduce a relative position augmented embedding learning algorithm, and transform the task from an independent prediction problem to a reordered prediction problem, where the dynamic global label information is incorporated. Experimental results on a benchmark emotion cause dataset show that our model achieves new state-ofthe-art performance and performs significantly better than a number of competitive baselines. Further analysis shows the effectiveness of the relative position augmented embedding learning algorithm and the reordered prediction mechanism with dynamic global labels.
Transcript disfluency detection (TDD) is an important component of the real-time speech translation system, which arouses more and more interests in recent years. This paper presents our study on adapting neural machine translation (NMT) models for TDD. We propose a general training framework for adapting NMT models to TDD task rapidly. In this framework, the main structure of the model is implemented similar to the NMT model. Additionally, several extended modules and training techniques which are independent of the NMT model are proposed to improve the performance, such as the constrained decoding, denoising autoencoder initialization and a TDD-specific training object. With the proposed training framework, we achieve significant improvement. However, it is too slow in decoding to be practical. To build a feasible and production-ready solution for TDD, we propose a fast non-autoregressive TDD model following the non-autoregressive NMT model emerged recently. Even we do not assume the specific architecture of the NMT model, we build our TDD model on the basis of Transformer, which is the state-of-the-art NMT model. We conduct extensive experiments on the publicly available set, Switchboard, and in-house Chinese set. Experimental results show that the proposed model significantly outperforms previous state-ofthe-art models.
Text classification is one of the fundamental tasks in natural language processing. Recently, deep neural networks have achieved promising performance in the text classification task compared to shallow models. Despite of the significance of deep models, they ignore the fine-grained (matching signals between words and classes) classification clues since their classifications mainly rely on the text-level representations. To address this problem, we introduce the interaction mechanism to incorporate word-level matching signals into the text classification task. In particular, we design a novel framework, EXplicit interAction Model (dubbed as EXAM), equipped with the interaction mechanism. We justified the proposed approach on several benchmark datasets including both multilabel and multi-class text classification tasks. Extensive experimental results demonstrate the superiority of the proposed method. As a byproduct, we have released the codes and parameter settings to facilitate other researches.
The performances of machine translation (MT) systems are usually evaluated by the metric BLEU when the golden references are provided. However, in the case of model inference or production deployment, golden references are usually expensively available, such as human annotation with bilingual expertise. In order to address the issue of translation quality estimation (QE) without reference, we propose a general framework for automatic evaluation of the translation output for the QE task in the Conference on Statistical Machine Translation (WMT). We first build a conditional target language model with a novel bidirectional transformer, named neural bilingual expert model, which is pre-trained on large parallel corpora for feature extraction. For QE inference, the bilingual expert model can simultaneously produce the joint latent representation between the source and the translation, and real-valued measurements of possible erroneous tokens based on the prior knowledge learned from parallel data. Subsequently, the features will further be fed into a simple Bi-LSTM predictive model for quality estimation. The experimental results show that our approach achieves the state-of-the-art performance in most public available datasets of WMT 2017/2018 QE task.
Query-document semantic interactions are essential for the success of many cloze-style question answering models. Recently, researchers have proposed several attention-based methods to predict the answer by focusing on appropriate subparts of the context document. In this paper, we design a novel module to produce the query-aware context vector, named Multi-Space based Context Fusion (MSCF), with the following considerations: (1) interactions are applied across multiple latent semantic spaces; (2) attention is measured at bit level, not at token level. Moreover, we extend MSCF to the multi-hop architecture. This unified model is called Enhanced Attentive Reader (EA Reader). During the iterative inference process, the reader is equipped with a novel memory update rule and maintains the understanding of documents through read, update and write operations. We conduct extensive experiments on four real-world datasets. Our results demonstrate that EA Reader outperforms state-of-the-art models.
Neural generative models have become popular and achieved promising performance on short-text conversation tasks. They are generally trained to build a 1-to-1 mapping from the input post to its output response. However, a given post is often associated with multiple replies simultaneously in real applications. Previous research on this task mainly focuses on improving the relevance and informativeness of the top one generated response for each post. Very few works study generating multiple accurate and diverse responses for the same post. In this paper, we propose a novel response generation model, which considers a set of responses jointly and generates multiple diverse responses simultaneously. A reinforcement learning algorithm is designed to solve our model. Experiments on two short-text conversation tasks validate that the multiple responses generated by our model obtain higher quality and larger diversity compared with various state-ofthe-art generative models.