EMNLP 2019 Papers

This paper studies keyphrase extraction in real-world scenarios where documents are from diverse domains and have variant content quality. We curate and release OpenKP, a large scale open domain keyphrase extraction dataset with near one hundred thousand web documents and expert keyphrase annotations. To handle the variations of domain and content quality, we develop BLING-KPE, a neural keyphrase extraction model that goes beyond language understanding using visual presentations of documents and weak supervision from search queries. Experimental results on OpenKP confirm the effectiveness of BLING-KPE and the contributions of its neural architecture, visual features, and search log weak supervision. Zero-shot evaluations on DUC-2001 demonstrate the improved generalization ability of learning from the open domain data compared to a specific domain.

Most state-of-the-art models for named entity recognition (NER) rely on the availability of large amounts of labeled data, making them challenging to extend to new, lower-resourced languages. However, there are now many proposed solutions to this problem involving either cross-lingual transfer learning, which learns from other highly resourced languages, or active learning, which efficiently selects effective training data based on model predictions. In this paper, we ask the question: given this recent progress, and some amount of human annotation, what is the most effective method for efficiently creating high-quality entity recognizers in under-resourced languages? Based on extensive experimentation using both simulated and real human annotation, we settle on a recipe of starting with a cross-lingual transferred model, then performing targeted annotation of only uncertain entity spans in the target language, minimizing annotator effort. Results demonstrate that cross-lingual transfer is a powerful tool when very little data can be annotated, but an entity-targeted annotation strategy can achieve competitive accuracy quickly, with just one-tenth of training data.

Everyone makes mistakes. So do human annotators when curating labels for named entity recognition (NER). Such label mistakes might hurt model training and interfere model comparison. In this study, we dive deep into one of the widely-adopted NER benchmark datasets, CoNLL03 NER. We are able to identify label mistakes in about 5.38% test sentences, which is a significant ratio considering that the state-of-the-art test F1 score is already around 93%. Therefore, we manually correct these label mistakes and form a cleaner test set. Our re-evaluation of popular models on this corrected test set leads to more accurate assessments, compared to those on the original test set. More importantly, we propose a simple yet effective framework, CrossWeigh, to handle label mistakes during NER model training. Specifically, it partitions the training data into several folds and train independent NER models to identify potential mistakes in each fold. Then it adjusts the weights of training data accordingly to train the final NER model. Extensive experiments demonstrate significant improvements of plugging various NER models into our proposed framework on three datasets. All implementations and corrected test set are available at our Github repo https://github.com/ZihanWangKi/CrossWeigh.

In this paper, we focus on natural language video localization: localizing (ie, grounding) a natural language description in a long and untrimmed video sequence. All currently published models for addressing this problem can be categorized into two types: (i) top-down approach: it does classification and regression for a set of pre-cut video segment candidates; (ii) bottom-up approach: it directly predicts probabilities for each video frame as the temporal boundaries (ie, start and end time point). However, both two approaches suffer several limitations: the former is computation-intensive for densely placed candidates, while the latter has trailed the performance of the top-down counterpart thus far. To this end, we propose a novel dense bottom-up framework: DEnse Bottom-Up Grounding (DEBUG). DEBUG regards all frames falling in the ground truth segment as foreground, and each foreground frame regresses the unique distances from its location to bi-directional ground truth boundaries. Extensive experiments on three challenging benchmarks (TACoS, Charades-STA, and ActivityNet Captions) show that DEBUG is able to match the speed of bottom-up models while surpassing the performance of the state-of-the-art top-down models.

Multimodal semantic comprehension has attracted increasing research interests recently such as visual question answering and caption generation. However, due to the data limitation, fine-grained semantic comprehension has not been well investigated, which requires to capture semantic details of multimodal contents. In this work, we introduce “YouMakeup”, a large-scale multimodal instructional video dataset to support fine-grained semantic comprehension research in specific domain. YouMakeup contains 2,800 videos from YouTube, spanning more than 420 hours in total. Each video is annotated with a sequence of natural language descriptions for instructional steps, grounded in temporal video range and spatial facial areas. The annotated steps in a video involve subtle difference in actions, products and regions, which requires fine-grained understanding and reasoning both temporally and spatially. In order to evaluate models’ ability for fined-grained comprehension, we further propose two groups of tasks including generation tasks and visual question answering from different aspects. We also establish a baseline of step caption generation for future comparison. The dataset will be publicly available at https://github.com/AIM3-RUC/YouMakeup to support research investigation in fine-grained semantic comprehension.

Grounding a pronoun to a visual object it refers to requires complex reasoning from various information sources, especially in conversational scenarios. For example, when people in a conversation talk about something all speakers can see, they often directly use pronouns (e.g., it) to refer to it without previous introduction. This fact brings a huge challenge for modern natural language understanding systems, particularly conventional context-based pronoun coreference models. To tackle this challenge, in this paper, we formally define the task of visual-aware pronoun coreference resolution (PCR) and introduce VisPro, a large-scale dialogue PCR dataset, to investigate whether and how the visual information can help resolve pronouns in dialogues. We then propose a novel visual-aware PCR model, VisCoref, for this task and conduct comprehensive experiments and case studies on our dataset. Results demonstrate the importance of the visual information in this PCR case and show the effectiveness of the proposed model.

The phrase grounding task aims to ground each entity mention in a given caption of an image to a corresponding region in that image. Although there are clear dependencies between how different mentions of the same caption should be grounded, previous structured prediction methods that aim to capture such dependencies need to resort to approximate inference or non-differentiable losses. In this paper, we formulate phrase grounding as a sequence labeling task where we treat candidate regions as potential labels, and use neural chain Conditional Random Fields (CRFs) to model dependencies among regions for adjacent mentions. In contrast to standard sequence labeling tasks, the phrase grounding task is defined such that there may be multiple correct candidate regions. To address this multiplicity of gold labels, we define so-called Soft-Label Chain CRFs, and present an algorithm that enables convenient end-to-end training. Our method establishes a new state-of-the-art on phrase grounding on the Flickr30k Entities dataset. Analysis shows that our model benefits both from the entity dependencies captured by the CRF and from the soft-label training regime. Our code is available at github.com/liujch1998/SoftLabelCCRF

Vision-and-language reasoning requires an understanding of visual concepts, language semantics, and, most importantly, the alignment and relationships between these two modalities. We thus propose the LXMERT (Learning Cross-Modality Encoder Representations from Transformers) framework to learn these vision-and-language connections. In LXMERT, we build a large-scale Transformer model that consists of three encoders: an object relationship encoder, a language encoder, and a cross-modality encoder. Next, to endow our model with the capability of connecting vision and language semantics, we pre-train the model with large amounts of image-and-sentence pairs, via five diverse representative pre-training tasks: masked language modeling, masked object prediction (feature regression and label classification), cross-modality matching, and image question answering. These tasks help in learning both intra-modality and cross-modality relationships. After fine-tuning from our pre-trained parameters, our model achieves the state-of-the-art results on two visual question answering datasets (i.e., VQA and GQA). We also show the generalizability of our pre-trained cross-modality model by adapting it to a challenging visual-reasoning task, NLVR2, and improve the previous best result by 22% absolute (54% to 76%). Lastly, we demonstrate detailed ablation studies to prove that both our novel model components and pre-training strategies significantly contribute to our strong results. Code and pre-trained models publicly available at: https://github.com/airsplay/lxmert

Text generation is among the most fundamental tasks in natural language processing. In this paper, we propose a text generation model that learns semantics and structural features simultaneously. This model captures structural features by a sequential variational autoencoder component and leverages a topic modeling component based on Gaussian distribution to enhance the recognition of text semantics. To make the reconstructed text more coherent to the topics, the model further adapts the encoder of the topic modeling component for a discriminator. The results of experiments over several datasets demonstrate that our model outperforms several states of the art models in terms of text perplexity and topic coherence. Moreover, the latent representations learned by our model is superior to others in a text classification task. Finally, given the input texts, our model can generate meaningful texts which hold similar structures but under different topics.

Automatic news comment generation is beneficial for real applications but has not attracted enough attention from the research community. In this paper, we propose a “read-attend-comment” procedure for news comment generation and formalize the procedure with a reading network and a generation network. The reading network comprehends a news article and distills some important points from it, then the generation network creates a comment by attending to the extracted discrete points and the news title. We optimize the model in an end-to-end manner by maximizing a variational lower bound of the true objective using the back-propagation algorithm. Experimental results on two public datasets indicate that our model can significantly outperform existing methods in terms of both automatic evaluation and human judgment.

Generating intriguing question is a key step towards building human-like open-domain chatbots. Although some recent works have focused on this task, compared with questions raised by humans, significant gaps remain in maintaining semantic coherence with post, which may result in generating dull or deviated questions. We observe that the answer has strong semantic coherence to its question and post, which can be used to guide question generation. Thus, we devise two methods to further enhance semantic coherence between post and question under the guidance of answer. First, the coherence score between generated question and answer is used as the reward function in a reinforcement learning framework, to encourage the cases that are consistent with the answer in semantic. Second, we incorporate adversarial training to explicitly control question generation in the direction of question-answer coherence. Extensive experiments show that our two methods outperform state-of-the-art baseline algorithms with large margins in raising semantic coherent questions.

We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task. Target texts are reconstructed from the inputs using three main edit operations: keeping a token, deleting it, and adding a phrase before the token. To predict the edit operations, we propose a novel model, which combines a BERT encoder with an autoregressive Transformer decoder. This approach is evaluated on English text on four tasks: sentence fusion, sentence splitting, abstractive summarization, and grammar correction. LaserTagger achieves new state-of-the-art results on three of these tasks, performs comparably to a set of strong seq2seq baselines with a large number of training examples, and outperforms them when the number of examples is limited. Furthermore, we show that at inference time tagging can be more than two orders of magnitude faster than comparable seq2seq models, making it more attractive for running in a live environment.

Counterfactual reasoning requires predicting how alternative events, contrary to what actually happened, might have resulted in different outcomes. Despite being considered a necessary component of AI-complete systems, few resources have been developed for evaluating counterfactual reasoning in narratives. In this paper, we propose Counterfactual Story Rewriting: given an original story and an intervening counterfactual event, the task is to minimally revise the story to make it compatible with the given counterfactual event. Solving this task will require deep understanding of causal narrative chains and counterfactual invariance, and integration of such story reasoning capabilities into conditional language generation models. We present TIMETRAVEL, a new dataset of 29,849 counterfactual rewritings, each with the original story, a counterfactual event, and human-generated revision of the original story compatible with the counterfactual event. Additionally, we include 81,407 counterfactual “branches” without a rewritten storyline to support future work on semi- or un-supervised approaches to counterfactual story rewriting. Finally, we evaluate the counterfactual rewriting capacities of several competitive baselines based on pretrained language models, and assess whether common overlap and model-based automatic metrics for text generation correlate well with human scores for counterfactual rewriting.

Symptom diagnosis is a challenging yet profound problem in natural language processing. Most previous research focus on investigating the standard electronic medical records for symptom diagnosis, while the dialogues between doctors and patients that contain more rich information are not well studied. In this paper, we first construct a dialogue symptom diagnosis dataset based on an online medical forum with a large amount of dialogues between patients and doctors. Then, we provide some benchmark models on this dataset to boost the research of dialogue symptom diagnosis. In order to further enhance the performance of symptom diagnosis over dialogues, we propose a global attention mechanism to capture more symptom related information, and build a symptom graph to model the associations between symptoms rather than treating each symptom independently. Experimental results show that both the global attention and symptom graph are effective to boost dialogue symptom diagnosis. In particular, our proposed model achieves the state-of-the-art performance on the constructed dataset.

Current neural query auto-completion (QAC) systems rely on character-level language models, but they slow down when queries are long. We present how to utilize subword language models for the fast and accurate generation of query completion candidates. Representing queries with subwords shorten a decoding length significantly. To deal with issues coming from introducing subword language model, we develop a retrace algorithm and a reranking method by approximate marginalization. As a result, our model achieves up to 2.5 times faster while maintaining a similar quality of generated results compared to the character-level baseline. Also, we propose a new evaluation metric, mean recoverable length (MRL), measuring how many upcoming characters the model could complete correctly. It provides more explicit meaning and eliminates the need for prefix length sampling for existing rank-based metrics. Moreover, we performed a comprehensive analysis with ablation study to figure out the importance of each component.

Recently, there has been a great interest in the development of small and accurate neural networks that run entirely on devices such as mobile phones, smart watches and IoT. This enables user privacy, consistent user experience and low latency. Although a wide range of applications have been targeted from wake word detection to short text classification, yet there are no on-device networks for long text classification. We propose a novel projection attention neural network PRADO that combines trainable projections with attention and convolutions. We evaluate our approach on multiple large document text classification tasks. Our results show the effectiveness of the trainable projection model in finding semantically similar phrases and reaching high performance while maintaining compact size. Using this approach, we train tiny neural networks just 200 Kilobytes in size that improve over prior CNN and LSTM models and achieve near state of the art performance on multiple long document classification tasks. We also apply our model for transfer learning, show its robustness and ability to further improve the performance in limited data scenarios.

Management of collaborative documents can be difficult, given the profusion of edits and comments that multiple authors make during a document’s evolution. Reliably modeling the relationship between edits and comments is a crucial step towards helping the user keep track of a document in flux. A number of authoring tasks, such as categorizing and summarizing edits, detecting completed to-dos, and visually rearranging comments could benefit from such a contribution. Thus, in this paper we explore the relationship between comments and edits by defining two novel, related tasks: Comment Ranking and Edit Anchoring. We begin by collecting a dataset with more than half a million comment-edit pairs based on Wikipedia revision histories. We then propose a hierarchical multi-layer deep neural-network to model the relationship between edits and comments. Our architecture tackles both Comment Ranking and Edit Anchoring tasks by encoding specific edit actions such as additions and deletions, while also accounting for document context. In a number of evaluation settings, our experimental results show that our approach outperforms several strong baselines significantly. We are able to achieve a precision@1 of 71.0% and a precision@3 of 94.4% for Comment Ranking, while we achieve 74.4% accuracy on Edit Anchoring.

Despite great scalability on large data and their ability to understand correlations between topics, spectral topic models have not been widely used due to the absence of reliability in real data and lack of practical implementations. This paper aims to solidify the foundations of spectral topic inference and provide a practical implementation for anchor-based topic modeling. Beginning with vocabulary curation, we scrutinize every single inference step with other viable options. We also evaluate our matrix-based approach against popular alternatives including a tensor-based spectral method as well as probabilistic algorithms. Our quantitative and qualitative experiments demonstrate the power of Rectified Anchor Word algorithm in various real datasets, providing a complete guide to practical correlated topic modeling.

Recently we proposed the Span Attribute Tagging (SAT) Model to infer clinical entities (e.g., symptoms) and their properties (e.g., duration). It tackles the challenge of large label space and limited training data using a hierarchical two-stage approach that identifies the span of interest in a tagging step and assigns labels to the span in a classification step. We extend the SAT model to jointly infer not only entities and their properties but also relations between them. Most relation extraction models restrict inferring relations between tokens within a few neighboring sentences, mainly to avoid high computational complexity. In contrast, our proposed Relation-SAT (R-SAT) model is computationally efficient and can infer relations over the entire conversation, spanning an average duration of 10 minutes. We evaluate our model on a corpus of clinical conversations. When the entities are given, the R-SAT outperforms baselines in identifying relations between symptoms and their properties by about 32% (0.82 vs 0.62 F-score) and by about 50% (0.60 vs 0.41 F-score) on medications and their properties. On the more difficult task of jointly inferring entities and relations, the R-SAT model achieves a performance of 0.34 and 0.45 for symptoms and medications respectively, which is significantly better than 0.18 and 0.35 for the baseline model. The contributions of different components of the model are quantified using ablation analysis.