Continuous sentence embeddings using recurrent neural networks (RNNs), where variable-length sentences are encoded into fixed-dimensional vectors, are often the main building blocks of architectures applied to language tasks such as dialogue generation. While it is known that those embeddings are able to learn some structures of language (e.g. grammar) in a purely data-driven manner, there is very little work on the objective evaluation of their ability to cover the whole language space and to generalize to sentences outside the language bias of the training data. Using a manually designed context-free grammar (CFG) to generate a large-scale dataset of sentences related to the content of realistic 3D indoor scenes, we evaluate the language coverage and generalization abilities of the most common continuous sentence embeddings based on RNNs. We also propose a new embedding method based on arithmetic coding, AriEL, that is not data-driven and that efficiently encodes in continuous space any sentence from the CFG. We find that RNN-based embeddings underfit the training data and cover only a small subset of the language defined by the CFG. They also fail to learn the underlying CFG and generalize to unbiased sentences from that same CFG. We found that AriEL provides an insightful baseline.
Indian Institute of Technology Delhi（印度理工学院德里分校）；University of Washington Seattle（华盛顿大学西雅图分校）
Previous work suggests that RNNs trained on natural language corpora can capture number agreement well for simple sentences but perform less well when sentences contain agreement attractors: intervening nouns between the verb and the main subject with grammatical number opposite to the latter. This suggests these models may not learn the actual syntax of agreement, but rather infer shallower heuristics such as `agree with the recent noun'. In this work, we investigate RNN models with varying inductive biases trained on selectively chosen `hard' agreement instances, i.e., sentences with at leas…
Recurrent Neural Networks have achieved state-of-the-art results for many problems in NLP and two most popular RNN architectures are Tail Model and Pooling Model. In this paper, a hybrid architecture is proposed and we present the first empirical study using LSTMs to compare performance of the three RNN structures on sentence classification task. Experimental results show that the Max Pooling Model or Hybrid Max Pooling Model achieves the best performance on most datasets, while Tail Model does not outperform other models.
National Institute of Technology Calicut（卡利卡特国立技术学院）
Recursive neural networks (Tree-RNNs) based on dependency trees are ubiquitous in modeling sentence meanings as they effectively capture semantic relationships between non-neighborhood words. However, recognizing semantically dissimilar sentences with the same words and syntax is still a challenge to Tree-RNNs. This work proposes an improvement to Dependency Tree-RNN (DT-RNN) using the grammatical relationship type identified in the dependency parse. Our experiments on semantic relatedness scoring (SRS) and recognizing textual entailment (RTE) in sentence pairs using SICK (Sentence Involving C…
Recurrent Neural Networks (RNNs) have been widely used in processing natural language tasks and achieve huge success. Traditional RNNs usually treat each token in a sentence uniformly and equally. However, this may miss the rich semantic structure information of a sentence, which is useful for understanding natural languages. Since semantic structures such as word dependence patterns are not parameterized, it is a challenge to capture and leverage structure information. In this paper, we propose an improved variant of RNN, Multi-Channel RNN (MC-RNN), to dynamically capture and leverage local s…
Xidian University（西安电子科技大学）；The University of Texas at Austin（得克萨斯大学奥斯汀分校）
To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation. Moving beyond a conventional RNN-based language model that ignores long-range word dependencies and sentence order, the proposed model captures not only intra-sentence word dependencies, but also temporal transitions between sentences and inter-sentence topic dependencies. For inference, we develop a hybrid of sto…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Key Laboratory for Information System Security, Ministry of Education（教育部信息系统安全重点实验室）；Huawei Technologies Co., Ltd.（华为技术有限公司）
While massive efforts have been investigated in adversarial testing of convolutional neural networks (CNN), testing for recurrent neural networks (RNN) is still limited and leaves threats for vast sequential application domains. In this paper, we propose an adversarial testing framework RNN-Test for RNN systems, focusing on the main sequential domains, not only classification tasks. First, we design a novel search methodology customized for RNN models by maximizing the inconsistency of RNN states to produce adversarial inputs. Next, we introduce two state-based coverage metrics according to th…
Recurrent neural networks (RNNs) have long been an architecture of interest for computational models of human sentence processing. The recently introduced Transformer architecture outperforms RNNs on many natural language processing tasks but little is known about its ability to model human language processing. We compare Transformer- and RNN-based language models' ability to account for measures of human reading effort. Our analysis shows Transformers to outperform RNNs in explaining self-paced reading times and neural activity during reading English sentences, challenging the widely held ide…
Google DeepMind（谷歌DeepMind）；University College London（伦敦大学学院）
Recent work on language modelling has shifted focus from count-based models to neural models. In these works, the words in each sentence are always considered in a left-to-right order. In this paper we show how we can improve the performance of the recurrent neural network (RNN) language model by incorporating the syntactic dependencies of a sentence, which have the effect of bringing relevant contexts closer to the word being predicted. We evaluate our approach on the Microsoft Research Sentence Completion Challenge and show that the dependency RNN proposed improves over the RNN by about 10 p…
Speaker change detection (SCD) is an important task in dialog modeling. Our paper addresses the problem of text-based SCD, which differs from existing audio-based studies and is useful in various scenarios, for example, processing dialog transcripts where speaker identities are missing (e.g., OpenSubtitle), and enhancing audio SCD with textual information. We formulate text-based SCD as a matching problem of utterances before and after a certain decision point; we propose a hierarchical recurrent neural network (RNN) with static sentence-level attention. Experimental results show that neural n…
The Australian National University（澳大利亚国立大学）；Data61/CSIRO（澳大利亚联邦科学与工业研究组织数据61中心）；University of Turku（图尔库大学）
Sentence compression is a Natural Language Processing (NLP) task aimed at shortening original sentences and preserving their key information. Its applications can benefit many fields e.g. one can build tools for language education. However, current methods are largely based on Recurrent Neural Network (RNN) models which suffer from poor processing speed. To address this issue, in this paper, we propose a token-wise Convolutional Neural Network, a CNN-based model along with pre-trained Bidirectional Encoder Representations from Transformers (BERT) features for deletion-based sentence compressio…
Athens University of Economics and Business（雅典经济与商业大学）；Cognitiv+ Ltd.（Cognitiv+有限公司）
We consider the task of detecting contractual obligations and prohibitions. We show that a self-attention mechanism improves the performance of a BILSTM classifier, the previous state of the art for this task, by allowing it to focus on indicative tokens. We also introduce a hierarchical BILSTM, which converts each sentence to an embedding, and processes the sentence embeddings to classify each sentence. Apart from being faster to train, the hierarchical BILSTM outperforms the flat one, even when the latter considers surrounding sentences, because the hierarchical model has a broader discourse…
Google, Inc.（谷歌公司）；Stanford University（斯坦福大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Google Brain（谷歌大脑）
The standard recurrent neural network language model (RNNLM) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an RNN-based variational autoencoder generative model that incorporates distributed latent representations of entire sentences. This factorization allows it to explicitly model holistic properties of sentences such as style, topic, and high-level syntactic features. Samples from the prior over these sentence representations remarkably produce diverse and well-formed sentences through simple de…
Stony Brook University（石溪大学）；University of Southern California（南加州大学）；University of California, Los Angeles（加州大学洛杉矶分校）
Despite deep recurrent neural networks (RNNs) demonstrate strong performance in text classification, training RNN models are often expensive and requires an extensive collection of annotated data which may not be available. To overcome the data limitation issue, existing approaches leverage either pre-trained word embedding or sentence representation to lift the burden of training RNNs from scratch. In this paper, we show that jointly learning sentence representations from multiple text classification tasks and combining them with pre-trained word-level and sentence level encoders result in ro…
Institute of Computer Science and Technology, Peking University（北京大学计算机科学技术研究所）；ByteDance AI Lab（字节跳动人工智能实验室）；AdeptMind Research（AdeptMind研究中心）
In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements. Existing language generation techniques are usually based on recurrent neural networks (RNNs). However, it is non-trivial to impose constraints on RNNs while maintaining generation quality, since RNNs generate sentences sequentially (or with beam search) from the first word to the last. In this paper, we propose CGMH, a novel approach using Metropolis-Hastings sampling for constrained sentence generation. CGMH allows complicated con…
University of British Columbia（不列颠哥伦比亚大学）；Microsoft Research（微软研究院）
This paper develops a model that addresses sentence embedding, a hot topic in current natural language processing research, using recurrent neural networks with Long Short-Term Memory (LSTM) cells. Due to its ability to capture long term memory, the LSTM-RNN accumulates increasingly richer information as it goes through the sentence, and when it reaches the last word, the hidden layer of the network provides a semantic representation of the whole sentence. In this paper, the LSTM-RNN is trained in a weakly supervised manner on user click-through data logged by a commercial web search engine. V…
Recently, span-based constituency parsing has achieved competitive accuracies with extremely simple models by using bidirectional RNNs to model "spans". However, the minimal span parser of Stern et al (2017a) which holds the current state of the art accuracy is a chart parser running in cubic time, $O(n^3)$, which is too slow for longer sentences and for applications beyond sentence boundaries such as end-to-end discourse parsing and joint sentence boundary detection and parsing. We propose a linear-time constituency parser with RNNs and dynamic programming using graph-structured stack and bea…
Recent language models, especially those based on recurrent neural networks (RNNs), make it possible to generate natural language from a learned probability. Language generation has wide applications including machine translation, summarization, question answering, conversation systems, etc. Existing methods typically learn a joint probability of words conditioned on additional information, which is (either statically or dynamically) fed to RNN's hidden layer. In many applications, we are likely to impose hard constraints on the generated texts, i.e., a particular word must appear in the sente…
Inferring the probability distribution of sentences or word sequences is a key process in natural language processing. While word-level language models (LMs) have been widely adopted for computing the joint probabilities of word sequences, they have difficulty in capturing a context long enough for sentence probability estimation (SPE). To overcome this, recent studies introduced training methods using sentence-level noise-contrastive estimation (NCE) with recurrent neural networks (RNNs). In this work, we attempt to extend it for contextual SPE, which aims to estimate a conditional sentence p…
PSL Research University（巴黎文理研究大学）；Bar Ilan University（巴伊兰大学）；CNRS（法国国家科学研究中心）；EHESS（法国社会科学高等研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）
Recent work has explored the syntactic abilities of RNNs using the subject-verb agreement task, which diagnoses sensitivity to sentence structure. RNNs performed this task well in common cases, but faltered in complex sentences (Linzen et al., 2016). We test whether these errors are due to inherent limitations of the architecture or to the relatively indirect supervision provided by most agreement dependencies in a corpus. We trained a single RNN to perform both the agreement task and an additional task, either CCG supertagging or language modeling. Multi-task training led to significantly low…
With internet quickly becoming an easy access to many, voice calling over internet is slowly gaining momentum. Individuals has been engaging in video communication across the world in different languages. The decade saw the emergence of language translation using neural networks as well. With more data being generated in audio and visual forms, there has become a need and a challenge to analyse such information for many researchers from academia and industry. The availability of video chat corpora is limited as organizations protect user privacy and ensure data security. For this reason, an au…
Johns Hopkins University（约翰斯·霍普金斯大学）；Université Paris Diderot（巴黎狄德罗大学）；CNRS（法国国家科学研究中心）；Microsoft Research AI（微软研究院人工智能部门）
Recurrent neural networks (RNNs) can learn continuous vector representations of symbolic structures such as sequences and sentences; these representations often exhibit linear regularities (analogies). Such regularities motivate our hypothesis that RNNs that show such regularities implicitly compile symbolic structures into tensor product representations (TPRs; Smolensky, 1990), which additively combine tensor products of vectors representing roles (e.g., sequence positions) and vectors representing fillers (e.g., particular words). To test this hypothesis, we introduce Tensor Product Decompos…
AWS Deep Learning, Amazon（亚马逊 AWS 深度学习）；IBM Research（IBM 研究院）
We present a new topic model that generates documents by sampling a topic for one whole sentence at a time, and generating the words in the sentence using an RNN decoder that is conditioned on the topic of the sentence. We argue that this novel formalism will help us not only visualize and model the topical discourse structure in a document better, but also potentially lead to more interpretable topics since we can now illustrate topics by sampling representative sentences instead of bag of words or phrases. We present a variational auto-encoder approach for learning in which we use a factoriz…
Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the language generator should generate sentences that convey desired information. Traditional template-based generators can produce sentences with all necessary information, but these sentences are not sufficiently diverse. With RNN-based models, the diversity of the generated sentences can be high, however, in the process some information is lost. In this work, we improve an RNN-based generator by considering latent inform…
Recurrent Neural Networks with Long Short-Term Memory cell (LSTM-RNN) have impressive ability in sequence data processing, particularly for language model building and text classification. This research proposes the combination of sentiment analysis, new approach of sentence vectors and LSTM-RNN as a novel way for Sexual Predator Identification (SPI). LSTM-RNN language model is applied to generate sentence vectors which are the last hidden states in the language model. Sentence vectors are fed into another LSTM-RNN classifier, so as to capture suspicious conversations. Hidden state enables to …
Context plays an important role in human language understanding, thus it may also be useful for machines learning vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised context-based sentence representation learning. We carefully designed experiments to show that neither an autoregressive decoder nor an RNN decoder is required. After that, we designed a model which still keeps an RNN as the encoder, while using a non-autoregressive convolutional decoder. We further combine a suite of effective designs to significantly improve mode…
Perplexity (per word) is the most widely used metric for evaluating language models. Despite this, there has been no dearth of criticism for this metric. Most of these criticisms center around lack of correlation with extrinsic metrics like word error rate (WER), dependence upon shared vocabulary for model comparison and unsuitability for unnormalized language model evaluation. In this paper, we address the last problem and propose a new discriminative entropy based intrinsic metric that works for both traditional word level models and unnormalized language models like sentence level models. W…
Sequence-to-sequence (Seq2seq) models have played an important role in the recent success of various natural language processing methods, such as machine translation, text summarization, and speech recognition. However, current Seq2seq models have trouble preserving global latent information from a long sequence of words. Variational autoencoder (VAE) alleviates this problem by learning a continuous semantic space of the input sentence. However, it does not solve the problem completely. In this paper, we propose a new recurrent neural network (RNN)-based Seq2seq model, RNN semantic variational…
Institute for Logic, Language and Computation（逻辑、语言与计算研究所）；University of Amsterdam（阿姆斯特丹大学）
In Recurrent Neural Networks (RNNs), encoding information in a suboptimal or erroneous way can impact the quality of representations based on later elements in the sequence and subsequently lead to wrong predictions and a worse model performance. In humans, challenging cases like garden path sentences (an instance of this being the infamous "The horse raced past the barn fell") can lead their language understanding astray. However, they are still able to correct their representation accordingly and recover when new information is encountered. Inspired by this, I propose an augmentation to stan…
Determining the correct form of a verb in context requires an understanding of the syntactic structure of the sentence. Recurrent neural networks have been shown to perform this task with an error rate comparable to humans, despite the fact that they are not designed with explicit syntactic representations. To examine the extent to which the syntactic representations of these networks are similar to those used by humans when processing sentences, we compare the detailed pattern of errors that RNNs and humans make on this task. Despite significant similarities (attraction errors, asymmetry betw…
Baidu Research（百度研究院）；University of California, Los Angeles（加州大学洛杉矶分校）
In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel sentence descriptions to explain the content of images. It directly models the probability distribution of generating a word given previous words and the image. Image descriptions are generated by sampling from this distribution. The model consists of two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. These two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of our model is valid…
In this work, we model abstractive text summarization using Attentional Encoder-Decoder Recurrent Neural Networks, and show that they achieve state-of-the-art performance on two different corpora. We propose several novel models that address critical problems in summarization that are not adequately modeled by the basic architecture, such as modeling key-words, capturing the hierarchy of sentence-to-word structure, and emitting words that are rare or unseen at training time. Our work shows that many of our proposed models contribute to further improvement in performance. We also propose a new …
Generating natural language descriptions for images is a challenging task. The traditional way is to use the convolutional neural network (CNN) to extract image features, followed by recurrent neural network (RNN) to generate sentences. In this paper, we present a new model that added memory cells to gate the feeding of image features to the deep neural network. The intuition is enabling our model to memorize how much information from images should be fed at each stage of the RNN. Experiments on Flickr8K and Flickr30K datasets showed that our model outperforms other state-of-the-art models wit…
Informatics Institute, University of Amsterdam（阿姆斯特丹大学信息学研究所）
Recurrent Neural Networks (RNN) have obtained excellent result in many natural language processing (NLP) tasks. However, understanding and interpreting the source of this success remains a challenge. In this paper, we propose Recurrent Memory Network (RMN), a novel RNN architecture, that not only amplifies the power of RNN but also facilitates our understanding of its internal functioning and allows us to discover underlying patterns in data. We demonstrate the power of RMN on language modeling and sentence completion tasks. On language modeling, RMN outperforms Long Short-Term Memory (LSTM) n…
We present novel methods for analyzing the activation patterns of RNNs from a linguistic point of view and explore the types of linguistic structure they learn. As a case study, we use a multi-task gated recurrent network architecture consisting of two parallel pathways with shared word embeddings trained on predicting the representations of the visual scene corresponding to an input sentence, and predicting the next word in the same sentence. Based on our proposed method to estimate the amount of contribution of individual tokens in the input to the final prediction of the networks we show th…
Japan Advanced Institute of Science and Technology（日本先进科学技术大学院大学）
Natural language generation (NLG) is a critical component in a spoken dialogue system. This paper presents a Recurrent Neural Network based Encoder-Decoder architecture, in which an LSTM-based decoder is introduced to select, aggregate semantic elements produced by an attention mechanism over the input elements, and to produce the required utterances. The proposed generator can be jointly trained both sentence planning and surface realization to produce natural language sentences. The proposed model was extensively evaluated on four different NLG datasets. The experimental results showed that …
Centre of Artificial Intelligence, FEIT, University of Technology Sydney（悉尼科技大学工程与信息技术学院人工智能中心）；Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）
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 lea…
Japan Advanced Institute of Science and Technology（日本北陆先端科学技术大学院大学）；University of Information and Communication Technology（信息与通信技术大学）
Natural language generation (NLG) plays a critical role in spoken dialogue systems. This paper presents a new approach to NLG by using recurrent neural networks (RNN), in which a gating mechanism is applied before RNN computation. This allows the proposed model to generate appropriate sentences. The RNN-based generator can be learned from unaligned data by jointly training sentence planning and surface realization to produce natural language responses. The model was extensively evaluated on four different NLG domains. The results show that the proposed generator achieved better performance on …
University of Southern California（南加州大学）；Disney Research（迪士尼研究院）
Spoken Language Understanding (SLU) typically comprises of an automatic speech recognition (ASR) followed by a natural language understanding (NLU) module. The two modules process signals in a blocking sequential fashion, i.e., the NLU often has to wait for the ASR to finish processing on an utterance basis, potentially leading to high latencies that render the spoken interaction less natural. In this paper, we propose recurrent neural network (RNN) based incremental processing towards the SLU task of intent detection. The proposed methodology offers lower latencies than a typical SLU system, …
University of Pennsylvania（宾夕法尼亚大学）；Center for Information and Language Processing（信息与语言处理中心）；LMU Munich（慕尼黑大学）
In NLP, convolutional neural networks (CNNs) have benefited less than recurrent neural networks (RNNs) from attention mechanisms. We hypothesize that this is because the attention in CNNs has been mainly implemented as attentive pooling (i.e., it is applied to pooling) rather than as attentive convolution (i.e., it is integrated into convolution). Convolution is the differentiator of CNNs in that it can powerfully model the higher-level representation of a word by taking into account its local fixed-size context in the input text t^x. In this work, we propose an attentive convolution network, …
In this paper, we propose a generative model which learns the relationship between language and human action in order to generate a human action sequence given a sentence describing human behavior. The proposed generative model is a generative adversarial network (GAN), which is based on the sequence to sequence (SEQ2SEQ) model. Using the proposed generative network, we can synthesize various actions for a robot or a virtual agent using a text encoder recurrent neural network (RNN) and an action decoder RNN. The proposed generative network is trained from 29,770 pairs of actions and sentence a…
Department of Computer Science, Johns Hopkins University（约翰霍普金斯大学计算机科学系）；Johns Hopkins University（约翰霍普金斯大学）
We show how the spellings of known words can help us deal with unknown words in open-vocabulary NLP tasks. The method we propose can be used to extend any closed-vocabulary generative model, but in this paper we specifically consider the case of neural language modeling. Our Bayesian generative story combines a standard RNN language model (generating the word tokens in each sentence) with an RNN-based spelling model (generating the letters in each word type). These two RNNs respectively capture sentence structure and word structure, and are kept separate as in linguistics. By invoking the seco…
Harvard University（哈佛大学）；MIT（麻省理工学院）；Primate Research Institute, Kyoto University（京都大学灵长类研究所）；UC Irvine（加州大学欧文分校）
RNN language models have achieved state-of-the-art perplexity results and have proven useful in a suite of NLP tasks, but it is as yet unclear what syntactic generalizations they learn. Here we investigate whether state-of-the-art RNN language models represent long-distance filler-gap dependencies and constraints on them. Examining RNN behavior on experimentally controlled sentences designed to expose filler-gap dependencies, we show that RNNs can represent the relationship in multiple syntactic positions and over large spans of text. Furthermore, we show that RNNs learn a subset of the known …
This paper introduces the Multi-Genre Natural Language Inference (MultiNLI) corpus, a dataset designed for use in the development and evaluation of machine learning models for sentence understanding. In addition to being one of the largest corpora available for the task of NLI, at 433k examples, this corpus improves upon available resources in its coverage: it offers data from ten distinct genres of written and spoken English--making it possible to evaluate systems on nearly the full complexity of the language--and it offers an explicit setting for the evaluation of cross-genre domain adaptati…
Despite the effectiveness of recurrent neural network language models, their maximum likelihood estimation suffers from two limitations. It treats all sentences that do not match the ground truth as equally poor, ignoring the structure of the output space. Second, it suffers from "exposure bias": during training tokens are predicted given ground-truth sequences, while at test time prediction is conditioned on generated output sequences. To overcome these limitations we build upon the recent reward augmented maximum likelihood approach \ie sequence-level smoothing that encourages the model to p…
Cognitive Neuroimaging Unit（认知神经影像单元）；NeuroSpin center（NeuroSpin中心）；Facebook AI Research（脸书人工智能研究院）；Laboratoire des systèmes perceptif（感知系统实验室）；École normale supérieure（巴黎高等师范学院）；PSL University（巴黎文理研究大学）；CNRS（法国国家科学研究中心）；Université Paris Diderot（巴黎第七大学）；Collège De France（法兰西公学院）
One of the fundamental principles of contemporary linguistics states that language processing requires the ability to extract recursively nested tree structures. However, it remains unclear whether and how this code could be implemented in neural circuits. Recent advances in Recurrent Neural Networks (RNNs), which achieve near-human performance in some language tasks, provide a compelling model to address such questions. Here, we present a new framework to study recursive processing in RNNs, using subject-verb agreement as a probe into the representations of the neural network. We trained six …
RNN language models have achieved state-of-the-art results on various tasks, but what exactly they are representing about syntax is as yet unclear. Here we investigate whether RNN language models learn humanlike word order preferences in syntactic alternations. We collect language model surprisal scores for controlled sentence stimuli exhibiting major syntactic alternations in English: heavy NP shift, particle shift, the dative alternation, and the genitive alternation. We show that RNN language models reproduce human preferences in these alternations based on NP length, animacy, and definiten…
We present a simple sequential sentence encoder for multi-domain natural language inference. Our encoder is based on stacked bidirectional LSTM-RNNs with shortcut connections and fine-tuning of word embeddings. The overall supervised model uses the above encoder to encode two input sentences into two vectors, and then uses a classifier over the vector combination to label the relationship between these two sentences as that of entailment, contradiction, or neural. Our Shortcut-Stacked sentence encoders achieve strong improvements over existing encoders on matched and mismatched multi-domain na…
Japan Advanced Institute of Science and Technology（日本北陆先端科学技术大学院大学）；University of Information and Communication Technology（信息与通信技术大学）；Thai Nguyen University（太原大学）
Natural language generation (NLG) is an important component in spoken dialogue systems. This paper presents a model called Encoder-Aggregator-Decoder which is an extension of an Recurrent Neural Network based Encoder-Decoder architecture. The proposed Semantic Aggregator consists of two components: an Aligner and a Refiner. The Aligner is a conventional attention calculated over the encoded input information, while the Refiner is another attention or gating mechanism stacked over the attentive Aligner in order to further select and aggregate the semantic elements. The proposed model can be joi…
The Chinese University of Hong Kong（香港中文大学）；Tencent AI Lab（腾讯人工智能实验室）
Target-oriented sentiment classification aims at classifying sentiment polarities over individual opinion targets in a sentence. RNN with attention seems a good fit for the characteristics of this task, and indeed it achieves the state-of-the-art performance. After re-examining the drawbacks of attention mechanism and the obstacles that block CNN to perform well in this classification task, we propose a new model to overcome these issues. Instead of attention, our model employs a CNN layer to extract salient features from the transformed word representations originated from a bi-directional RN…
In this paper we describe a deep learning system that has been designed and built for the WASSA 2017 Emotion Intensity Shared Task. We introduce a representation learning approach based on inner attention on top of an RNN. Results show that our model offers good capabilities and is able to successfully identify emotion-bearing words to predict intensity without leveraging on lexicons, obtaining the 13th place among 22 shared task competitors.
University of Geneva（日内瓦大学）；Facebook AI Research（脸书人工智能研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）
Recurrent neural networks (RNNs) have achieved impressive results in a variety of linguistic processing tasks, suggesting that they can induce non-trivial properties of language. We investigate here to what extent RNNs learn to track abstract hierarchical syntactic structure. We test whether RNNs trained with a generic language modeling objective in four languages (Italian, English, Hebrew, Russian) can predict long-distance number agreement in various constructions. We include in our evaluation nonsensical sentences where RNNs cannot rely on semantic or lexical cues ("The colorless green idea…
Recently, neural networks have shown promising results for named entity recognition (NER), which needs a number of labeled data to for model training. When meeting a new domain (target domain) for NER, there is no or a few labeled data, which makes domain NER much more difficult. As NER has been researched for a long time, some similar domain already has well labelled data (source domain). Therefore, in this paper, we focus on domain NER by studying how to utilize the labelled data from such similar source domain for the new target domain. We design a kernel function based instance transfer st…
University of California, Los Angeles（加州大学洛杉矶分校）；University of Southern California（南加州大学）；Fudan University（复旦大学）；University of Virginia（弗吉尼亚大学）
Learning distributed sentence representations is one of the key challenges in natural language processing. Previous work demonstrated that a recurrent neural network (RNNs) based sentence encoder trained on a large collection of annotated natural language inference data, is efficient in the transfer learning to facilitate other related tasks. In this paper, we show that joint learning of multiple tasks results in better generalizable sentence representations by conducting extensive experiments and analysis comparing the multi-task and single-task learned sentence encoders. The quantitative ana…
