NAACL 2018 Papers

Machine Learning has been the quintessential solution for many AI problems, but learning models are heavily dependent on specific training data. Some learning models can be incorporated with prior knowledge using a Bayesian setup, but these learning models do not have the ability to access any organized world knowledge on demand. In this work, we propose to enhance learning models with world knowledge in the form of Knowledge Graph (KG) fact triples for Natural Language Processing (NLP) tasks. Our aim is to develop a deep learning model that can extract relevant prior support facts from knowledge graphs depending on the task using attention mechanism. We introduce a convolution-based model for learning representations of knowledge graph entity and relation clusters in order to reduce the attention space. We show that the proposed method is highly scalable to the amount of prior information that has to be processed and can be applied to any generic NLP task. Using this method we show significant improvement in performance for text classification with 20Newsgroups (News20) & DBPedia datasets, and natural language inference with Stanford Natural Language Inference (SNLI) dataset. We also demonstrate that a deep learning model can be trained with substantially less amount of labeled training data, when it has access to organized world knowledge in the form of a knowledge base.

Information about the meaning of mathematical variables in text is useful in NLP/IR tasks such as symbol disambiguation, topic modeling and mathematical information retrieval (MIR). We introduce variable typing, the task of assigning one mathematical type (multi-word technical terms referring to mathematical concepts) to each variable in a sentence of mathematical text. As part of this work, we also introduce a new annotated data set composed of 33,524 data points extracted from scientific documents published on arXiv. Our intrinsic evaluation demonstrates that our data set is sufficient to successfully train and evaluate current classifiers from three different model architectures. The best performing model is evaluated on an extrinsic task: MIR, by producing a typed formula index. Our results show that the best performing MIR models make use of our typed index, compared to a formula index only containing raw symbols, thereby demonstrating the usefulness of variable typing.

Can attention- or gradient-based visualization techniques be used to infer token-level labels for binary sequence tagging problems, using networks trained only on sentence-level labels? We construct a neural network architecture based on soft attention, train it as a binary sentence classifier and evaluate against token-level annotation on four different datasets. Inferring token labels from a network provides a method for quantitatively evaluating what the model is learning, along with generating useful feedback in assistance systems. Our results indicate that attention-based methods are able to predict token-level labels more accurately, compared to gradient-based methods, sometimes even rivaling the supervised oracle network.

Task extraction is the process of identifying search intents over a set of queries potentially spanning multiple search sessions. Most existing research on task extraction has focused on identifying tasks within a single session, where the notion of a session is defined by a fixed length time window. By contrast, in this work we seek to identify tasks that span across multiple sessions. To identify tasks, we conduct a global analysis of a query log in its entirety without restricting analysis to individual temporal windows. To capture inherent task semantics, we represent queries as vectors in an abstract space. We learn the embedding of query words in this space by leveraging the temporal and lexical contexts of queries. Embedded query vectors are then clustered into tasks. Experiments demonstrate that task extraction effectiveness is improved significantly with our proposed method of query vector embedding in comparison to existing approaches that make use of documents retrieved from a collection to estimate semantic similarities between queries.

We propose a framework for computer-assisted text editing. It applies to translation post-editing and to paraphrasing. Our proposal relies on very simple interactions: a human editor modifies a sentence by marking tokens they would like the system to change. Our model then generates a new sentence which reformulates the initial sentence by avoiding marked words. The approach builds upon neural sequence-to-sequence modeling and introduces a neural network which takes as input a sentence along with change markers. Our model is trained on translation bitext by simulating post-edits. We demonstrate the advantage of our approach for translation post-editing through simulated post-edits. We also evaluate our model for paraphrasing through a user study.

We demonstrate that current state-of-the-art approaches to Automated Essay Scoring (AES) are not well-suited to capturing adversarially crafted input of grammatical but incoherent sequences of sentences. We develop a neural model of local coherence that can effectively learn connectedness features between sentences, and propose a framework for integrating and jointly training the local coherence model with a state-of-the-art AES model. We evaluate our approach against a number of baselines and experimentally demonstrate its effectiveness on both the AES task and the task of flagging adversarial input, further contributing to the development of an approach that strengthens the validity of neural essay scoring models.

We present a reading comprehension challenge in which questions can only be answered by taking into account information from multiple sentences. We solicit and verify questions and answers for this challenge through a 4-step crowdsourcing experiment. Our challenge dataset contains 6,500+ questions for 1000+ paragraphs across 7 different domains (elementary school science, news, travel guides, fiction stories, etc) bringing in linguistic diversity to the texts and to the questions wordings. On a subset of our dataset, we found human solvers to achieve an F1-score of 88.1%. We analyze a range of baselines, including a recent state-of-art reading comprehension system, and demonstrate the difficulty of this challenge, despite a high human performance. The dataset is the first to study multi-sentence inference at scale, with an open-ended set of question types that requires reasoning skills.

We present a content-based method for recommending citations in an academic paper draft. We embed a given query document into a vector space, then use its nearest neighbors as candidates, and rerank the candidates using a discriminative model trained to distinguish between observed and unobserved citations. Unlike previous work, our method does not require metadata such as author names which can be missing, e.g., during the peer review process. Without using metadata, our method outperforms the best reported results on PubMed and DBLP datasets with relative improvements of over 18% in F1@20 and over 22% in MRR. We show empirically that, although adding metadata improves the performance on standard metrics, it favors self-citations which are less useful in a citation recommendation setup. We release an online portal for citation recommendation based on our method, (URL: http://bit.ly/citeDemo) and a new dataset OpenCorpus of 7 million research articles to facilitate future research on this task.

Studies in Social Sciences have revealed that when people evaluate someone else, their evaluations often reflect their biases. As a result, rater bias may introduce highly subjective factors that make their evaluations inaccurate. This may affect automated essay scoring models in many ways, as these models are typically designed to model (potentially biased) essay raters. While there is sizeable literature on rater effects in general settings, it remains unknown how rater bias affects automated essay scoring. To this end, we present a new annotated corpus containing essays and their respective scores. Different from existing corpora, our corpus also contains comments provided by the raters in order to ground their scores. We present features to quantify rater bias based on their comments, and we found that rater bias plays an important role in automated essay scoring. We investigated the extent to which rater bias affects models based on hand-crafted features. Finally, we propose to rectify the training set by removing essays associated with potentially biased scores while learning the scoring model.

We present a neural model for question generation from knowledge graphs triples in a “Zero-shot” setup, that is generating questions for predicate, subject types or object types that were not seen at training time. Our model leverages triples occurrences in the natural language corpus in a encoder-decoder architecture, paired with an original part-of-speech copy action mechanism to generate questions. Benchmark and human evaluation show that our model outperforms state-of-the-art on this task.

Lexical simplification involves identifying complex words or phrases that need to be simplified, and recommending simpler meaning-preserving substitutes that can be more easily understood. We propose a complex word identification (CWI) model that exploits both lexical and contextual features, and a simplification mechanism which relies on a word-embedding lexical substitution model to replace the detected complex words with simpler paraphrases. We compare our CWI and lexical simplification models to several baselines, and evaluate the performance of our simplification system against human judgments. The results show that our models are able to detect complex words with higher accuracy than other commonly used methods, and propose good simplification substitutes in context. They also highlight the limited contribution of context features for CWI, which nonetheless improve simplification compared to context-unaware models.

Most recent approaches use the sequence-to-sequence model for paraphrase generation. The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words. Therefore, the generated sentences are often grammatically correct but semantically improper. In this work, we introduce a novel model based on the encoder-decoder framework, called Word Embedding Attention Network (WEAN). Our proposed model generates the words by querying distributed word representations (i.e. neural word embeddings), hoping to capturing the meaning of the according words. Following previous work, we evaluate our model on two paraphrase-oriented tasks, namely text simplification and short text abstractive summarization. Experimental results show that our model outperforms the sequence-to-sequence baseline by the BLEU score of 6.3 and 5.5 on two English text simplification datasets, and the ROUGE-2 F1 score of 5.7 on a Chinese summarization dataset. Moreover, our model achieves state-of-the-art performances on these three benchmark datasets.

Memory augmented encoder-decoder framework has achieved promising progress for natural language generation tasks. Such frameworks enable a decoder to retrieve from a memory during generation. However, less research has been done to take care of the memory contents from different sources, which are often of heterogeneous formats. In this work, we propose a novel attention mechanism to encourage the decoder to actively interact with the memory by taking its heterogeneity into account. Our solution attends across the generated history and memory to explicitly avoid repetition, and introduce related knowledge to enrich our generated sentences. Experiments on the answer sentence generation task show that our method can effectively explore heterogeneous memory to produce readable and meaningful answer sentences while maintaining high coverage for given answer information.

In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to model cross-sentence ordering as a means to approximate desired discourse structure. Empirical results demonstrate that a generator trained with the learned reward produces more coherent and less repetitive text than models trained with cross-entropy or with reinforcement learning with commonly used scores as rewards.

This paper presents a novel, data-driven language model that produces entire lyrics for a given input melody. Previously proposed models for lyrics generation suffer from the inability of capturing the relationship between lyrics and melody partly due to the unavailability of lyrics-melody aligned data. In this study, we first propose a new practical method for creating a large collection of lyrics-melody aligned data and then create a collection of 1,000 lyrics-melody pairs augmented with precise syllable-note alignments and word/sentence/paragraph boundaries. We then provide a quantitative analysis of the correlation between word/sentence/paragraph boundaries in lyrics and melodies. We then propose an RNN-based lyrics language model conditioned on a featurized melody. Experimental results show that the proposed model generates fluent lyrics while maintaining the compatibility between boundaries of lyrics and melody structures.

Natural language generation lies at the core of generative dialogue systems and conversational agents. We describe an ensemble neural language generator, and present several novel methods for data representation and augmentation that yield improved results in our model. We test the model on three datasets in the restaurant, TV and laptop domains, and report both objective and subjective evaluations of our best model. Using a range of automatic metrics, as well as human evaluators, we show that our approach achieves better results than state-of-the-art models on the same datasets.

We argue that semantic meanings of a sentence or clause can not be interpreted independently from the rest of a paragraph, or independently from all discourse relations and the overall paragraph-level discourse structure. With the goal of improving implicit discourse relation classification, we introduce a paragraph-level neural networks that model inter-dependencies between discourse units as well as discourse relation continuity and patterns, and predict a sequence of discourse relations in a paragraph. Experimental results show that our model outperforms the previous state-of-the-art systems on the benchmark corpus of PDTB.

Style transfer is the task of automatically transforming a piece of text in one particular style into another. A major barrier to progress in this field has been a lack of training and evaluation datasets, as well as benchmarks and automatic metrics. In this work, we create the largest corpus for a particular stylistic transfer (formality) and show that techniques from the machine translation community can serve as strong baselines for future work. We also discuss challenges of using automatic metrics.

Analyzing language in context, both from a theoretical and from a computational perspective, is receiving increased interest. Complementing the research in linguistics on discourse and information structure, in computational linguistics identifying discourse concepts was also shown to improve the performance of certain applications, for example, Short Answer Assessment systems (Ziai and Meurers, 2014). Building on the research that established detailed annotation guidelines for manual annotation of information structural concepts for written (Dipper et al., 2007; Ziai and Meurers, 2014) and spoken language data (Calhoun et al., 2010), this paper presents the first approach automating the analysis of focus in authentic written data. Our classification approach combines a range of lexical, syntactic, and semantic features to achieve an accuracy of 78.1% for identifying focus.