Total: 725
Neural sequence generation is typically performed token-by-token and left-to-right. Whenever a token is generated only previously produced tokens are taken into consideration. In contrast, for problems such as sequence classification, bidirectional attention, which takes both past and future tokens into consideration, has been shown to perform much better. We propose to make the sequence generation process bidirectional by employing special placeholder tokens. Treated as a node in a fully connected graph, a placeholder token can take past and future tokens into consideration when generating the actual output token. We verify the effectiveness of our approach experimentally on two conversational tasks where the proposed bidirectional model outperforms competitive baselines by a large margin.
Attention mechanisms play a central role in NLP systems, especially within recurrent neural network (RNN) models. Recently, there has been increasing interest in whether or not the intermediate representations offered by these modules may be used to explain the reasoning for a model’s prediction, and consequently reach insights regarding the model’s decision-making process. A recent paper claims that ‘Attention is not Explanation’ (Jain and Wallace, 2019). We challenge many of the assumptions underlying this work, arguing that such a claim depends on one’s definition of explanation, and that testing it needs to take into account all elements of the model. We propose four alternative tests to determine when/whether attention can be used as explanation: a simple uniform-weights baseline; a variance calibration based on multiple random seed runs; a diagnostic framework using frozen weights from pretrained models; and an end-to-end adversarial attention training protocol. Each allows for meaningful interpretation of attention mechanisms in RNN models. We show that even when reliable adversarial distributions can be found, they don’t perform well on the simple diagnostic, indicating that prior work does not disprove the usefulness of attention mechanisms for explainability.
Active learning (AL) is a widely-used training strategy for maximizing predictive performance subject to a fixed annotation budget. In AL, one iteratively selects training examples for annotation, often those for which the current model is most uncertain (by some measure). The hope is that active sampling leads to better performance than would be achieved under independent and identically distributed (i.i.d.) random samples. While AL has shown promise in retrospective evaluations, these studies often ignore practical obstacles to its use. In this paper, we show that while AL may provide benefits when used with specific models and for particular domains, the benefits of current approaches do not generalize reliably across models and tasks. This is problematic because in practice, one does not have the opportunity to explore and compare alternative AL strategies. Moreover, AL couples the training dataset with the model used to guide its acquisition. We find that subsequently training a successor model with an actively-acquired dataset does not consistently outperform training on i.i.d. sampled data. Our findings raise the question of whether the downsides inherent to AL are worth the modest and inconsistent performance gains it tends to afford.
Deep learning systems thrive on abundance of labeled training data but such data is not always available, calling for alternative methods of supervision. One such method is expectation regularization (XR) (Mann and McCallum, 2007), where models are trained based on expected label proportions. We propose a novel application of the XR framework for transfer learning between related tasks, where knowing the labels of task A provides an estimation of the label proportion of task B. We then use a model trained for A to label a large corpus, and use this corpus with an XR loss to train a model for task B. To make the XR framework applicable to large-scale deep-learning setups, we propose a stochastic batched approximation procedure. We demonstrate the approach on the task of Aspect-based Sentiment classification, where we effectively use a sentence-level sentiment predictor to train accurate aspect-based predictor. The method improves upon fully supervised neural system trained on aspect-level data, and is also cumulative with LM-based pretraining, as we demonstrate by improving a BERT-based Aspect-based Sentiment model.
Contextual word representations, typically trained on unstructured, unlabeled text, do not contain any explicit grounding to real world entities and are often unable to remember facts about those entities. We propose a general method to embed multiple knowledge bases (KBs) into large scale models, and thereby enhance their representations with structured, human-curated knowledge. For each KB, we first use an integrated entity linker to retrieve relevant entity embeddings, then update contextual word representations via a form of word-to-entity attention. In contrast to previous approaches, the entity linkers and self-supervised language modeling objective are jointly trained end-to-end in a multitask setting that combines a small amount of entity linking supervision with a large amount of raw text. After integrating WordNet and a subset of Wikipedia into BERT, the knowledge enhanced BERT (KnowBert) demonstrates improved perplexity, ability to recall facts as measured in a probing task and downstream performance on relationship extraction, entity typing, and word sense disambiguation. KnowBert’s runtime is comparable to BERT’s and it scales to large KBs.
Replacing static word embeddings with contextualized word representations has yielded significant improvements on many NLP tasks. However, just how contextual are the contextualized representations produced by models such as ELMo and BERT? Are there infinitely many context-specific representations for each word, or are words essentially assigned one of a finite number of word-sense representations? For one, we find that the contextualized representations of all words are not isotropic in any layer of the contextualizing model. While representations of the same word in different contexts still have a greater cosine similarity than those of two different words, this self-similarity is much lower in upper layers. This suggests that upper layers of contextualizing models produce more context-specific representations, much like how upper layers of LSTMs produce more task-specific representations. In all layers of ELMo, BERT, and GPT-2, on average, less than 5% of the variance in a word’s contextualized representations can be explained by a static embedding for that word, providing some justification for the success of contextualized representations.
Word embeddings are increasingly used for the automatic detection of semantic change; yet, a robust evaluation and systematic comparison of the choices involved has been lacking. We propose a new evaluation framework for semantic change detection and find that (i) using the whole time series is preferable over only comparing between the first and last time points; (ii) independently trained and aligned embeddings perform better than continuously trained embeddings for long time periods; and (iii) that the reference point for comparison matters. We also present an analysis of the changes detected on a large Twitter dataset spanning 5.5 years.
Similarity measures based purely on word embeddings are comfortably competing with much more sophisticated deep learning and expert-engineered systems on unsupervised semantic textual similarity (STS) tasks. In contrast to commonly used geometric approaches, we treat a single word embedding as e.g. 300 observations from a scalar random variable. Using this paradigm, we first illustrate that similarities derived from elementary pooling operations and classic correlation coefficients yield excellent results on standard STS benchmarks, outperforming many recently proposed methods while being much faster and trivial to implement. Next, we demonstrate how to avoid pooling operations altogether and compare sets of word embeddings directly via correlation operators between reproducing kernel Hilbert spaces. Just like cosine similarity is used to compare individual word vectors, we introduce a novel application of the centered kernel alignment (CKA) as a natural generalisation of squared cosine similarity for sets of word vectors. Likewise, CKA is very easy to implement and enjoys very strong empirical results.
Game-theoretic models, thanks to their intrinsic ability to exploit contextual information, have shown to be particularly suited for the Word Sense Disambiguation task. They represent ambiguous words as the players of a non cooperative game and their senses as the strategies that the players can select in order to play the games. The interaction among the players is modeled with a weighted graph and the payoff as an embedding similarity function, that the players try to maximize. The impact of the word and sense embedding representations in the framework has been tested and analyzed extensively: experiments on standard benchmarks show state-of-art performances and different tests hint at the usefulness of using disambiguation to obtain contextualized word representations.
Dialog policy decides what and how a task-oriented dialog system will respond, and plays a vital role in delivering effective conversations. Many studies apply Reinforcement Learning to learn a dialog policy with the reward function which requires elaborate design and pre-specified user goals. With the growing needs to handle complex goals across multiple domains, such manually designed reward functions are not affordable to deal with the complexity of real-world tasks. To this end, we propose Guided Dialog Policy Learning, a novel algorithm based on Adversarial Inverse Reinforcement Learning for joint reward estimation and policy optimization in multi-domain task-oriented dialog. The proposed approach estimates the reward signal and infers the user goal in the dialog sessions. The reward estimator evaluates the state-action pairs so that it can guide the dialog policy at each dialog turn. Extensive experiments on a multi-domain dialog dataset show that the dialog policy guided by the learned reward function achieves remarkably higher task success than state-of-the-art baselines.
Multi-turn retrieval-based conversation is an important task for building intelligent dialogue systems. Existing works mainly focus on matching candidate responses with every context utterance on multiple levels of granularity, which ignore the side effect of using excessive context information. Context utterances provide abundant information for extracting more matching features, but it also brings noise signals and unnecessary information. In this paper, we will analyze the side effect of using too many context utterances and propose a multi-hop selector network (MSN) to alleviate the problem. Specifically, MSN firstly utilizes a multi-hop selector to select the relevant utterances as context. Then, the model matches the filtered context with the candidate response and obtains a matching score. Experimental results show that MSN outperforms some state-of-the-art methods on three public multi-turn dialogue datasets.
Previous research on empathetic dialogue systems has mostly focused on generating responses given certain emotions. However, being empathetic not only requires the ability of generating emotional responses, but more importantly, requires the understanding of user emotions and replying appropriately. In this paper, we propose a novel end-to-end approach for modeling empathy in dialogue systems: Mixture of Empathetic Listeners (MoEL). Our model first captures the user emotions and outputs an emotion distribution. Based on this, MoEL will softly combine the output states of the appropriate Listener(s), which are each optimized to react to certain emotions, and generate an empathetic response. Human evaluations on EMPATHETIC-DIALOGUES dataset confirm that MoEL outperforms multitask training baseline in terms of empathy, relevance, and fluency. Furthermore, the case study on generated responses of different Listeners shows high interpretability of our model.
Querying the knowledge base (KB) has long been a challenge in the end-to-end task-oriented dialogue system. Previous sequence-to-sequence (Seq2Seq) dialogue generation work treats the KB query as an attention over the entire KB, without the guarantee that the generated entities are consistent with each other. In this paper, we propose a novel framework which queries the KB in two steps to improve the consistency of generated entities. In the first step, inspired by the observation that a response can usually be supported by a single KB row, we introduce a KB retrieval component which explicitly returns the most relevant KB row given a dialogue history. The retrieval result is further used to filter the irrelevant entities in a Seq2Seq response generation model to improve the consistency among the output entities. In the second step, we further perform the attention mechanism to address the most correlated KB column. Two methods are proposed to make the training feasible without labeled retrieval data, which include distant supervision and Gumbel-Softmax technique. Experiments on two publicly available task oriented dialog datasets show the effectiveness of our model by outperforming the baseline systems and producing entity-consistent responses.
Reinforcement learning (RL) is an effective approach to learn an optimal dialog policy for task-oriented visual dialog systems. A common practice is to apply RL on a neural sequence-to-sequence(seq2seq) framework with the action space being the output vocabulary in the decoder. However, it is difficult to design a reward function that can achieve a balance between learning an effective policy and generating a natural dialog response. This paper proposes a novel framework that alternatively trains a RL policy for image guessing and a supervised seq2seq model to improve dialog generation quality. We evaluate our framework on the GuessWhich task and the framework achieves the state-of-the-art performance in both task completion and dialog quality.
Emotion recognition in conversation (ERC) has received much attention, lately, from researchers due to its potential widespread applications in diverse areas, such as health-care, education, and human resources. In this paper, we present Dialogue Graph Convolutional Network (DialogueGCN), a graph neural network based approach to ERC. We leverage self and inter-speaker dependency of the interlocutors to model conversational context for emotion recognition. Through the graph network, DialogueGCN addresses context propagation issues present in the current RNN-based methods. We empirically show that this method alleviates such issues, while outperforming the current state of the art on a number of benchmark emotion classification datasets.
Messages in human conversations inherently convey emotions. The task of detecting emotions in textual conversations leads to a wide range of applications such as opinion mining in social networks. However, enabling machines to analyze emotions in conversations is challenging, partly because humans often rely on the context and commonsense knowledge to express emotions. In this paper, we address these challenges by proposing a Knowledge-Enriched Transformer (KET), where contextual utterances are interpreted using hierarchical self-attention and external commonsense knowledge is dynamically leveraged using a context-aware affective graph attention mechanism. Experiments on multiple textual conversation datasets demonstrate that both context and commonsense knowledge are consistently beneficial to the emotion detection performance. In addition, the experimental results show that our KET model outperforms the state-of-the-art models on most of the tested datasets in F1 score.
Multiple emotions with different intensities are often evoked by events described in documents. Oftentimes, such event information is hidden and needs to be discovered from texts. Unveiling the hidden event information can help to understand how the emotions are evoked and provide explainable results. However, existing studies often ignore the latent event information. In this paper, we proposed a novel interpretable relevant emotion ranking model with the event information incorporated into a deep learning architecture using the event-driven attentions. Moreover, corpus-level event embeddings and document-level event distributions are introduced respectively to consider the global events in corpus and the document-specific events simultaneously. Experimental results on three real-world corpora show that the proposed approach performs remarkably better than the state-of-the-art emotion detection approaches and multi-label approaches. Moreover, interpretable results can be obtained to shed light on the events which trigger certain emotions.
Several recent works have considered the problem of generating reviews (or ‘tips’) as a form of explanation as to why a recommendation might match a customer’s interests. While promising, we demonstrate that existing approaches struggle (in terms of both quality and content) to generate justifications that are relevant to users’ decision-making process. We seek to introduce new datasets and methods to address the recommendation justification task. In terms of data, we first propose an ‘extractive’ approach to identify review segments which justify users’ intentions; this approach is then used to distantly label massive review corpora and construct large-scale personalized recommendation justification datasets. In terms of generation, we are able to design two personalized generation models with this data: (1) a reference-based Seq2Seq model with aspect-planning which can generate justifications covering different aspects, and (2) an aspect-conditional masked language model which can generate diverse justifications based on templates extracted from justification histories. We conduct experiments on two real-world datasets which show that our model is capable of generating convincing and diverse justifications.
Customers ask questions and customer service staffs answer their questions, which is the basic service model via multi-turn customer service (CS) dialogues on E-commerce platforms. Existing studies fail to provide comprehensive service satisfaction analysis, namely satisfaction polarity classification (e.g., well satisfied, met and unsatisfied) and sentimental utterance identification (e.g., positive, neutral and negative). In this paper, we conduct a pilot study on the task of service satisfaction analysis (SSA) based on multi-turn CS dialogues. We propose an extensible Context-Assisted Multiple Instance Learning (CAMIL) model to predict the sentiments of all the customer utterances and then aggregate those sentiments into service satisfaction polarity. After that, we propose a novel Context Clue Matching Mechanism (CCMM) to enhance the representations of all customer utterances with their matched context clues, i.e., sentiment and reasoning clues. We construct two CS dialogue datasets from a top E-commerce platform. Extensive experimental results are presented and contrasted against a few previous models to demonstrate the efficacy of our model.
Medical relation extraction discovers relations between entity mentions in text, such as research articles. For this task, dependency syntax has been recognized as a crucial source of features. Yet in the medical domain, 1-best parse trees suffer from relatively low accuracies, diminishing their usefulness. We investigate a method to alleviate this problem by utilizing dependency forests. Forests contain more than one possible decisions and therefore have higher recall but more noise compared with 1-best outputs. A graph neural network is used to represent the forests, automatically distinguishing the useful syntactic information from parsing noise. Results on two benchmarks show that our method outperforms the standard tree-based methods, giving the state-of-the-art results in the literature.
Open relation extraction (OpenRE) aims to extract relational facts from the open-domain corpus. To this end, it discovers relation patterns between named entities and then clusters those semantically equivalent patterns into a united relation cluster. Most OpenRE methods typically confine themselves to unsupervised paradigms, without taking advantage of existing relational facts in knowledge bases (KBs) and their high-quality labeled instances. To address this issue, we propose Relational Siamese Networks (RSNs) to learn similarity metrics of relations from labeled data of pre-defined relations, and then transfer the relational knowledge to identify novel relations in unlabeled data. Experiment results on two real-world datasets show that our framework can achieve significant improvements as compared with other state-of-the-art methods. Our code is available at https://github.com/thunlp/RSN.
While attention mechanisms have been proven to be effective in many NLP tasks, majority of them are data-driven. We propose a novel knowledge-attention encoder which incorporates prior knowledge from external lexical resources into deep neural networks for relation extraction task. Furthermore, we present three effective ways of integrating knowledge-attention with self-attention to maximize the utilization of both knowledge and data. The proposed relation extraction system is end-to-end and fully attention-based. Experiment results show that the proposed knowledge-attention mechanism has complementary strengths with self-attention, and our integrated models outperform existing CNN, RNN, and self-attention based models. State-of-the-art performance is achieved on TACRED, a complex and large-scale relation extraction dataset.
Entity alignment is a viable means for integrating heterogeneous knowledge among different knowledge graphs (KGs). Recent developments in the field often take an embedding-based approach to model the structural information of KGs so that entity alignment can be easily performed in the embedding space. However, most existing works do not explicitly utilize useful relation representations to assist in entity alignment, which, as we will show in the paper, is a simple yet effective way for improving entity alignment. This paper presents a novel joint learning framework for entity alignment. At the core of our approach is a Graph Convolutional Network (GCN) based framework for learning both entity and relation representations. Rather than relying on pre-aligned relation seeds to learn relation representations, we first approximate them using entity embeddings learned by the GCN. We then incorporate the relation approximation into entities to iteratively learn better representations for both. Experiments performed on three real-world cross-lingual datasets show that our approach substantially outperforms state-of-the-art entity alignment methods.
For large-scale knowledge graphs (KGs), recent research has been focusing on the large proportion of infrequent relations which have been ignored by previous studies. For example few-shot learning paradigm for relations has been investigated. In this work, we further advocate that handling uncommon entities is inevitable when dealing with infrequent relations. Therefore, we propose a meta-learning framework that aims at handling infrequent relations with few-shot learning and uncommon entities by using textual descriptions. We design a novel model to better extract key information from textual descriptions. Besides, we also develop a novel generative model in our framework to enhance the performance by generating extra triplets during the training stage. Experiments are conducted on two datasets from real-world KGs, and the results show that our framework outperforms previous methods when dealing with infrequent relations and their accompanying uncommon entities.
Name tagging in low-resource languages or domains suffers from inadequate training data. Existing work heavily relies on additional information, while leaving those noisy annotations unexplored that extensively exist on the web. In this paper, we propose a novel neural model for name tagging solely based on weakly labeled (WL) data, so that it can be applied in any low-resource settings. To take the best advantage of all WL sentences, we split them into high-quality and noisy portions for two modules, respectively: (1) a classification module focusing on the large portion of noisy data can efficiently and robustly pretrain the tag classifier by capturing textual context semantics; and (2) a costly sequence labeling module focusing on high-quality data utilizes Partial-CRFs with non-entity sampling to achieve global optimum. Two modules are combined via shared parameters. Extensive experiments involving five low-resource languages and fine-grained food domain demonstrate our superior performance (6% and 7.8% F1 gains on average) as well as efficiency.