Large crowdsourced datasets are widely used for training and evaluating neural models on natural language inference (NLI). Despite these efforts, neural models have a hard time capturing logical inferences, including those licensed by phrase replacements, so-called monotonicity reasoning. Since no large dataset has been developed for monotonicity reasoning, it is still unclear whether the main obstacle is the size of datasets or the model architectures themselves. To investigate this issue, we introduce a new dataset, called HELP, for handling entailments with lexical and logical phenomena. We add it to training data for the state-of-the-art neural models and evaluate them on test sets for monotonicity phenomena. The results showed that our data augmentation improved the overall accuracy. We also find that the improvement is better on monotonicity inferences with lexical replacements than on downward inferences with disjunction and modification. This suggests that some types of inferences can be improved by our data augmentation while others are immune to it.
This study explores the necessity of performing cross-corpora evaluation for grammatical error correction (GEC) models. GEC models have been previously evaluated based on a single commonly applied corpus: the CoNLL-2014 benchmark. However, the evaluation remains incomplete because the task difficulty varies depending on the test corpus and conditions such as the proficiency levels of the writers and essay topics. To overcome this limitation, we evaluate the performance of several GEC models, including NMT-based (LSTM, CNN, and transformer) and an SMT-based model, against various learner corpora (CoNLL-2013, CoNLL-2014, FCE, JFLEG, ICNALE, and KJ). Evaluation results reveal that the models' rankings considerably vary depending on the corpus, indicating that single-corpus evaluation is insufficient for GEC models.
Browsing news articles on multiple devices is now possible. The lengths of news article headlines have precise upper bounds, dictated by the size of the display of the relevant device or interface. Therefore, controlling the length of headlines is essential when applying the task of headline generation to news production. However, because there is no corpus of headlines of multiple lengths for a given article, prior researches on controlling output length in headline generation have not discussed whether the evaluation of the setting that uses a single length reference can evaluate multiple length outputs appropriately. In this paper, we introduce two corpora (JNC and JAMUL) to confirm the validity of prior experimental settings and provide for the next step toward the goal of controlling output length in headline generation. The JNC provides common supervision data for headline generation. The JAMUL is a large-scale evaluation dataset for headlines of three different lengths composed by professional editors. We report new findings on these corpora; for example, while the longest length reference summary can appropriately evaluate the existing methods controlling output length, the methods do not manage the selection of words according to length constraint.
We present a new task, suspicious news detection using micro blog text. This task aims to support human experts to detect suspicious news articles to be verified, which is costly but a crucial step before verifying the truthfulness of the articles. Specifically, in this task, given a set of posts on SNS referring to a news article, the goal is to judge whether the article is to be verified or not. For this task, we create a publicly available dataset in Japanese and provide benchmark results by using several basic machine learning techniques. Experimental results show that our models can reduce the cost of manual fact-checking process.
The current success of deep neural networks (DNNs) in an increasingly broad range of tasks for the artificial intelligence strongly depends on the quality and quantity of labeled training data. In general, the scarcity of labeled data, which is often observed in many natural language processing tasks, is one of the most important issues to be addressed. Semi-supervised learning (SSL) is a promising approach to overcome this issue by incorporating a large amount of unlabeled data. In this paper, we propose a novel scalable method of SSL for text classification tasks. The unique property of our method, Mixture of Expert/Imitator Networks, is that imitator networks learn to "imitate" the estimated label distribution of the expert network over the unlabeled data, which potentially contributes as a set of features for the classification. Our experiments demonstrate that the proposed method consistently improves the performance of several types of baseline DNNs. We also demonstrate that our method has the more data, better performance property with promising scalability to the unlabeled data.
In this paper, we propose a new kernel-based co-occurrence measure that can be applied to sparse linguistic expressions (e.g., sentences) with a very short learning time, as an alternative to pointwise mutual information (PMI). As well as deriving PMI from mutual information, we derive this new measure from the Hilbert--Schmidt independence criterion (HSIC); thus, we call the new measure the pointwise HSIC (PHSIC). PHSIC can be interpreted as a smoothed variant of PMI that allows various similarity metrics (e.g., sentence embeddings) to be plugged in as kernels. Moreover, PHSIC can be estimated by simple and fast (linear in the size of the data) matrix calculations regardless of whether we use linear or nonlinear kernels. Empirically, in a dialogue response selection task, PHSIC is learned thousands of times faster than an RNN-based PMI while outperforming PMI in accuracy. In addition, we also demonstrate that PHSIC is beneficial as a criterion of a data selection task for machine translation owing to its ability to give high (low) scores to a consistent (inconsistent) pair with other pairs.
A challenge in creating a dataset for machine reading comprehension (MRC) is to collect questions that require a sophisticated understanding of language to answer beyond using superficial cues. In this work, we investigate what makes questions easier across recent 12 MRC datasets with three question styles (answer extraction, description, and multiple choice). We propose to employ simple heuristics to split each dataset into easy and hard subsets and examine the performance of two baseline models for each of the subsets. We then manually annotate questions sampled from each subset with both validity and requisite reasoning skills to investigate which skills explain the difference between easy and hard questions. From this study, we observed that (i) the baseline performances for the hard subsets remarkably degrade compared to those of entire datasets, (ii) hard questions require knowledge inference and multiple-sentence reasoning in comparison with easy questions, and (iii) multiple-choice questions tend to require a broader range of reasoning skills than answer extraction and description questions. These results suggest that one might overestimate recent advances in MRC.
Capturing interactions among multiple predicate-argument structures (PASs) is a crucial issue in the task of analyzing PAS in Japanese. In this paper, we propose new Japanese PAS analysis models that integrate the label prediction information of arguments in multiple PASs by extending the input and last layers of a standard deep bidirectional recurrent neural network (bi-RNN) model. In these models, using the mechanisms of pooling and attention, we aim to directly capture the potential interactions among multiple PASs, without being disturbed by the word order and distance. Our experiments show that the proposed models improve the prediction accuracy specifically for cases where the predicate and argument are in an indirect dependency relation and achieve a new state of the art in the overall $F_1$ on a standard benchmark corpus.
Embedding models for entities and relations are extremely useful for recovering missing facts in a knowledge base. Intuitively, a relation can be modeled by a matrix mapping entity vectors. However, relations reside on low dimension sub-manifolds in the parameter space of arbitrary matrices---for one reason, composition of two relations $\boldsymbol{M}_1,\boldsymbol{M}_2$ may match a third $\boldsymbol{M}_3$ (e.g. composition of relations currency_of_country and country_of_film usually matches currency_of_film_budget), which imposes compositional constraints to be satisfied by the parameters (i.e. $\boldsymbol{M}_1\cdot \boldsymbol{M}_2\approx \boldsymbol{M}_3$). In this paper we investigate a dimension reduction technique by training relations jointly with an autoencoder, which is expected to better capture compositional constraints. We achieve state-of-the-art on Knowledge Base Completion tasks with strongly improved Mean Rank, and show that joint training with an autoencoder leads to interpretable sparse codings of relations, helps discovering compositional constraints and benefits from compositional training. Our source code is released at github.com/tianran/glimvec.
This paper presents the first study aimed at capturing stylistic similarity between words in an unsupervised manner. We propose extending the continuous bag of words (CBOW) model (Mikolov et al., 2013) to learn style-sensitive word vectors using a wider context window under the assumption that the style of all the words in an utterance is consistent. In addition, we introduce a novel task to predict lexical stylistic similarity and to create a benchmark dataset for this task. Our experiment with this dataset supports our assumption and demonstrates that the proposed extensions contribute to the acquisition of style-sensitive word embeddings.