ACL 2018 论文列表

Neural Machine Translation (NMT) is notorious for its need for large amounts of bilingual data. An effective approach to compensate for this requirement is Multi-Task Learning (MTL) to leverage different linguistic resources as a source of inductive bias. Current MTL architectures are based on the Seq2Seq transduction, and (partially) share different components of the models among the tasks. However, this MTL approach often suffers from task interference and is not able to fully capture commonalities among subsets of tasks. We address this issue by extending the recurrent units with multiple “blocks” along with a trainable “routing network”. The routing network enables adaptive collaboration by dynamic sharing of blocks conditioned on the task at hand, input, and model state. Empirical evaluation of two low-resource translation tasks, English to Vietnamese and Farsi, show +1 BLEU score improvements compared to strong baselines.

We create a new NLI test set that shows the deficiency of state-of-the-art models in inferences that require lexical and world knowledge. The new examples are simpler than the SNLI test set, containing sentences that differ by at most one word from sentences in the training set. Yet, the performance on the new test set is substantially worse across systems trained on SNLI, demonstrating that these systems are limited in their generalization ability, failing to capture many simple inferences.

Intelligent systems require common sense, but automatically extracting this knowledge from text can be difficult. We propose and assess methods for extracting one type of commonsense knowledge, object-property comparisons, from pre-trained embeddings. In experiments, we show that our approach exceeds the accuracy of previous work but requires substantially less hand-annotated knowledge. Further, we show that an active learning approach that synthesizes common-sense queries can boost accuracy.

We present the Supervised Directional Similarity Network, a novel neural architecture for learning task-specific transformation functions on top of general-purpose word embeddings. Relying on only a limited amount of supervision from task-specific scores on a subset of the vocabulary, our architecture is able to generalise and transform a general-purpose distributional vector space to model the relation of lexical entailment. Experiments show excellent performance on scoring graded lexical entailment, raising the state-of-the-art on the HyperLex dataset by approximately 25%.

Neural vector representations are ubiquitous throughout all subfields of NLP. While word vectors have been studied in much detail, thus far only little light has been shed on the properties of sentence embeddings. In this paper, we assess to what extent prominent sentence embedding methods exhibit select semantic properties. We propose a framework that generate triplets of sentences to explore how changes in the syntactic structure or semantics of a given sentence affect the similarities obtained between their sentence embeddings.

Chart constraints, which specify at which string positions a constituent may begin or end, have been shown to speed up chart parsers for PCFGs. We generalize chart constraints to more expressive grammar formalisms and describe a neural tagger which predicts chart constraints at very high precision. Our constraints accelerate both PCFG and TAG parsing, and combine effectively with other pruning techniques (coarse-to-fine and supertagging) for an overall speedup of two orders of magnitude, while improving accuracy.

How to make the most of multiple heterogeneous treebanks when training a monolingual dependency parser is an open question. We start by investigating previously suggested, but little evaluated, strategies for exploiting multiple treebanks based on concatenating training sets, with or without fine-tuning. We go on to propose a new method based on treebank embeddings. We perform experiments for several languages and show that in many cases fine-tuning and treebank embeddings lead to substantial improvements over single treebanks or concatenation, with average gains of 2.0–3.5 LAS points. We argue that treebank embeddings should be preferred due to their conceptual simplicity, flexibility and extensibility.

This paper investigates the construction of a strong baseline based on general purpose sequence-to-sequence models for constituency parsing. We incorporate several techniques that were mainly developed in natural language generation tasks, e.g., machine translation and summarization, and demonstrate that the sequence-to-sequence model achieves the current top-notch parsers’ performance (almost) without requiring any explicit task-specific knowledge or architecture of constituent parsing.

We propose a tri-modal architecture to predict Big Five personality trait scores from video clips with different channels for audio, text, and video data. For each channel, stacked Convolutional Neural Networks are employed. The channels are fused both on decision-level and by concatenating their respective fully connected layers. It is shown that a multimodal fusion approach outperforms each single modality channel, with an improvement of 9.4% over the best individual modality (video). Full backpropagation is also shown to be better than a linear combination of modalities, meaning complex interactions between modalities can be leveraged to build better models. Furthermore, we can see the prediction relevance of each modality for each trait. The described model can be used to increase the emotional intelligence of virtual agents.

The process of obtaining high quality labeled data for natural language understanding tasks is often slow, error-prone, complicated and expensive. With the vast usage of neural networks, this issue becomes more notorious since these networks require a large amount of labeled data to produce satisfactory results. We propose a methodology to blend high quality but scarce strong labeled data with noisy but abundant weak labeled data during the training of neural networks. Experiments in the context of topic-dependent evidence detection with two forms of weak labeled data show the advantages of the blending scheme. In addition, we provide a manually annotated data set for the task of topic-dependent evidence detection. We believe that blending weak and strong labeled data is a general notion that may be applicable to many language understanding tasks, and can especially assist researchers who wish to train a network but have a small amount of high quality labeled data for their task of interest.

One key task of fine-grained sentiment analysis of product reviews is to extract product aspects or features that users have expressed opinions on. This paper focuses on supervised aspect extraction using deep learning. Unlike other highly sophisticated supervised deep learning models, this paper proposes a novel and yet simple CNN model employing two types of pre-trained embeddings for aspect extraction: general-purpose embeddings and domain-specific embeddings. Without using any additional supervision, this model achieves surprisingly good results, outperforming state-of-the-art sophisticated existing methods. To our knowledge, this paper is the first to report such double embeddings based CNN model for aspect extraction and achieve very good results.

Humor is one of the most attractive parts in human communication. However, automatically recognizing humor in text is challenging due to the complex characteristics of humor. This paper proposes to model sentiment association between discourse units to indicate how the punchline breaks the expectation of the setup. We found that discourse relation, sentiment conflict and sentiment transition are effective indicators for humor recognition. On the perspective of using sentiment related features, sentiment association in discourse is more useful than counting the number of emotional words.

Attention-based long short-term memory (LSTM) networks have proven to be useful in aspect-level sentiment classification. However, due to the difficulties in annotating aspect-level data, existing public datasets for this task are all relatively small, which largely limits the effectiveness of those neural models. In this paper, we explore two approaches that transfer knowledge from document-level data, which is much less expensive to obtain, to improve the performance of aspect-level sentiment classification. We demonstrate the effectiveness of our approaches on 4 public datasets from SemEval 2014, 2015, and 2016, and we show that attention-based LSTM benefits from document-level knowledge in multiple ways.

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) embedding model (Mikolov et al., 2013b) 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.

Negative sampling is an important component in word2vec for distributed word representation learning. We hypothesize that taking into account global, corpus-level information and generating a different noise distribution for each target word better satisfies the requirements of negative examples for each training word than the original frequency-based distribution. In this purpose we pre-compute word co-occurrence statistics from the corpus and apply to it network algorithms such as random walk. We test this hypothesis through a set of experiments whose results show that our approach boosts the word analogy task by about 5% and improves the performance on word similarity tasks by about 1% compared to the skip-gram negative sampling baseline.

Word embeddings are crucial to many natural language processing tasks. The quality of embeddings relies on large non-noisy corpora. Arabic dialects lack large corpora and are noisy, being linguistically disparate with no standardized spelling. We make three contributions to address this noise. First, we describe simple but effective adaptations to word embedding tools to maximize the informative content leveraged in each training sentence. Second, we analyze methods for representing disparate dialects in one embedding space, either by mapping individual dialects into a shared space or learning a joint model of all dialects. Finally, we evaluate via dictionary induction, showing that two metrics not typically reported in the task enable us to analyze our contributions’ effects on low and high frequency words. In addition to boosting performance between 2-53%, we specifically improve on noisy, low frequency forms without compromising accuracy on high frequency forms.

Word Embeddings have recently imposed themselves as a standard for representing word meaning in NLP. Semantic similarity between word pairs has become the most common evaluation benchmark for these representations, with vector cosine being typically used as the only similarity metric. In this paper, we report experiments with a rank-based metric for WE, which performs comparably to vector cosine in similarity estimation and outperforms it in the recently-introduced and challenging task of outlier detection, thus suggesting that rank-based measures can improve clustering quality.

A homographic pun is a form of wordplay in which one signifier (usually a word) suggests two or more meanings by exploiting polysemy for an intended humorous or rhetorical effect. In this paper, we focus on the task of pun location, which aims to identify the pun word in a given short text. We propose a sense-aware neural model to address this challenging task. Our model first obtains several WSD results for the text, and then leverages a bidirectional LSTM network to model each sequence of word senses. The outputs at each time step for different LSTM networks are then concatenated for prediction. Evaluation results on the benchmark SemEval 2017 dataset demonstrate the efficacy of our proposed model.

This work deals with SciTail, a natural entailment challenge derived from a multi-choice question answering problem. The premises and hypotheses in SciTail were generated with no awareness of each other, and did not specifically aim at the entailment task. This makes it more challenging than other entailment data sets and more directly useful to the end-task – question answering. We propose DEISTE (deep explorations of inter-sentence interactions for textual entailment) for this entailment task. Given word-to-word interactions between the premise-hypothesis pair (P, H), DEISTE consists of: (i) a parameter-dynamic convolution to make important words in P and H play a dominant role in learnt representations; and (ii) a position-aware attentive convolution to encode the representation and position information of the aligned word pairs. Experiments show that DEISTE gets ≈5% improvement over prior state of the art and that the pretrained DEISTE on SciTail generalizes well on RTE-5.