EMNLP 2017 论文列表

Monolingual evaluation of Machine Translation (MT) aims to simplify human assessment by requiring assessors to compare the meaning of the MT output with a reference translation, opening up the task to a much larger pool of genuinely qualified evaluators. Monolingual evaluation runs the risk, however, of bias in favour of MT systems that happen to produce translations superficially similar to the reference and, consistent with this intuition, previous investigations have concluded monolingual assessment to be strongly biased in this respect. On re-examination of past analyses, we identify a series of potential analytical errors that force some important questions to be raised about the reliability of past conclusions, however. We subsequently carry out further investigation into reference bias via direct human assessment of MT adequacy via quality controlled crowd-sourcing. Contrary to both intuition and past conclusions, results for show no significant evidence of reference bias in monolingual evaluation of MT.

In this paper we introduce a practical first step towards the creation of an automated debate agent: a state-of-the-art recurrent predictive model for predicting debate winners. By having an accurate predictive model, we are able to objectively rate the quality of a statement made at a specific turn in a debate. The model is based on a recurrent neural network architecture with attention, which allows the model to effectively account for the entire debate when making its prediction. Our model achieves state-of-the-art accuracy on a dataset of debate transcripts annotated with audience favorability of the debate teams. Finally, we discuss how future work can leverage our proposed model for the creation of an automated debate agent. We accomplish this by determining the model input that will maximize audience favorability toward a given side of a debate at an arbitrary turn.

Hand-crafted rules and reinforcement learning (RL) are two popular choices to obtain dialogue policy. The rule-based policy is often reliable within predefined scope but not self-adaptable, whereas RL is evolvable with data but often suffers from a bad initial performance. We employ a companion learning framework to integrate the two approaches for on-line dialogue policy learning, in which a pre-defined rule-based policy acts as a “teacher” and guides a data-driven RL system by giving example actions as well as additional rewards. A novel agent-aware dropout Deep Q-Network (AAD-DQN) is proposed to address the problem of when to consult the teacher and how to learn from the teacher’s experiences. AAD-DQN, as a data-driven student policy, provides (1) two separate experience memories for student and teacher, (2) an uncertainty estimated by dropout to control the timing of consultation and learning. Simulation experiments showed that the proposed approach can significantly improve both safety and efficiency of on-line policy optimization compared to other companion learning approaches as well as supervised pre-training using static dialogue corpus.

Much of human dialogue occurs in semi-cooperative settings, where agents with different goals attempt to agree on common decisions. Negotiations require complex communication and reasoning skills, but success is easy to measure, making this an interesting task for AI. We gather a large dataset of human-human negotiations on a multi-issue bargaining task, where agents who cannot observe each other’s reward functions must reach an agreement (or a deal) via natural language dialogue. For the first time, we show it is possible to train end-to-end models for negotiation, which must learn both linguistic and reasoning skills with no annotated dialogue states. We also introduce dialogue rollouts, in which the model plans ahead by simulating possible complete continuations of the conversation, and find that this technique dramatically improves performance. Our code and dataset are publicly available.

Discourse segmentation is the first step in building discourse parsers. Most work on discourse segmentation does not scale to real-world discourse parsing across languages, for two reasons: (i) models rely on constituent trees, and (ii) experiments have relied on gold standard identification of sentence and token boundaries. We therefore investigate to what extent constituents can be replaced with universal dependencies, or left out completely, as well as how state-of-the-art segmenters fare in the absence of sentence boundaries. Our results show that dependency information is less useful than expected, but we provide a fully scalable, robust model that only relies on part-of-speech information, and show that it performs well across languages in the absence of any gold-standard annotation.

The number of word embedding models is growing every year. Most of them are based on the co-occurrence information of words and their contexts. However, it is still an open question what is the best definition of context. We provide a systematical investigation of 4 different syntactic context types and context representations for learning word embeddings. Comprehensive experiments are conducted to evaluate their effectiveness on 6 extrinsic and intrinsic tasks. We hope that this paper, along with the published code, would be helpful for choosing the best context type and representation for a given task.

In this work, we study the problem of part-of-speech tagging for Tweets. In contrast to newswire articles, Tweets are usually informal and contain numerous out-of-vocabulary words. Moreover, there is a lack of large scale labeled datasets for this domain. To tackle these challenges, we propose a novel neural network to make use of out-of-domain labeled data, unlabeled in-domain data, and labeled in-domain data. Inspired by adversarial neural networks, the proposed method tries to learn common features through adversarial discriminator. In addition, we hypothesize that domain-specific features of target domain should be preserved in some degree. Hence, the proposed method adopts a sequence-to-sequence autoencoder to perform this task. Experimental results on three different datasets show that our method achieves better performance than state-of-the-art methods.

We present a novel approach for training artificial neural networks. Our approach is inspired by broad evidence in psychology that shows human learners can learn efficiently and effectively by increasing intervals of time between subsequent reviews of previously learned materials (spaced repetition). We investigate the analogy between training neural models and findings in psychology about human memory model and develop an efficient and effective algorithm to train neural models. The core part of our algorithm is a cognitively-motivated scheduler according to which training instances and their “reviews” are spaced over time. Our algorithm uses only 34-50% of data per epoch, is 2.9-4.8 times faster than standard training, and outperforms competing state-of-the-art baselines. Our code is available at scholar.harvard.edu/hadi/RbF/.

We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes. The model is learned by using a convolutional neural network as an encoder to map an input sentence into a continuous vector, and using a long short-term memory recurrent neural network as a decoder. Several tasks are considered, including sentence reconstruction and future sentence prediction. Further, a hierarchical encoder-decoder model is proposed to encode a sentence to predict multiple future sentences. By training our models on a large collection of novels, we obtain a highly generic convolutional sentence encoder that performs well in practice. Experimental results on several benchmark datasets, and across a broad range of applications, demonstrate the superiority of the proposed model over competing methods.

Several approaches have been proposed to model either the explicit sequential structure of an argumentative text or its implicit hierarchical structure. So far, the adequacy of these models of overall argumentation remains unclear. This paper asks what type of structure is actually important to tackle downstream tasks in computational argumentation. We analyze patterns in the overall argumentation of texts from three corpora. Then, we adapt the idea of positional tree kernels in order to capture sequential and hierarchical argumentative structure together for the first time. In systematic experiments for three text classification tasks, we find strong evidence for the impact of both types of structure. Our results suggest that either of them is necessary while their combination may be beneficial.

Neural networks have achieved state-of-the-art performance on several structured-output prediction tasks, trained in a fully supervised fashion. However, annotated examples in structured domains are often costly to obtain, which thus limits the applications of neural networks. In this work, we propose Maximum Margin Reward Networks, a neural network-based framework that aims to learn from both explicit (full structures) and implicit supervision signals (delayed feedback on the correctness of the predicted structure). On named entity recognition and semantic parsing, our model outperforms previous systems on the benchmark datasets, CoNLL-2003 and WebQuestionsSP.

We propose a language-independent data-driven method to exhaustively extract bursty phrases of arbitrary forms (e.g., phrases other than simple noun phrases) from microblogs. The burst (i.e., the rapid increase of the occurrence) of a phrase causes the burst of overlapping N-grams including incomplete ones. In other words, bursty incomplete N-grams inevitably overlap bursty phrases. Thus, the proposed method performs the extraction of bursty phrases as the set cover problem in which all bursty N-grams are covered by a minimum set of bursty phrases. Experimental results using Japanese Twitter data showed that the proposed method outperformed word-based, noun phrase-based, and segmentation-based methods both in terms of accuracy and coverage.

Recommendations are often rated for their subjective quality, but few researchers have studied comment quality in terms of objective utility. We explore recommendation quality assessment with respect to both subjective (i.e. users’ ratings) and objective (i.e., did it influence? did it improve decisions?) metrics in a massive online geopolitical forecasting system, ultimately comparing linguistic characteristics of each quality metric. Using a variety of features, we predict all types of quality with better accuracy than the simple yet strong baseline of comment length. Looking at the most predictive content illustrates rater biases; for example, forecasters are subjectively biased in favor of comments mentioning business transactions or dealings as well as material things, even though such comments do not indeed prove any more useful objectively. Additionally, more complex sentence constructions, as evidenced by subordinate conjunctions, are characteristic of comments leading to objective improvements in forecasting.

Highlighting the recurrence of topics usage in candidates speeches is a key feature to identify the main ideas of each candidate during a political campaign. In this paper, we present a method combining standard topic modeling with signature mining for analyzing topic recurrence in speeches of Clinton and Trump during the 2016 American presidential campaign. The results show that the method extracts automatically the main ideas of each candidate and, in addition, provides information about the evolution of these topics during the campaign.

Much of our online communication is text-mediated and, lately, more common with automated agents. Unlike interacting with humans, these agents currently do not tailor their language to the type of person they are communicating to. In this pilot study, we measure the extent to which human perception of basic user trait information – gender and age – is controllable through text. Using automatic models of gender and age prediction, we estimate which tweets posted by a user are more likely to mis-characterize his traits. We perform multiple controlled crowdsourcing experiments in which we show that we can reduce the human prediction accuracy of gender to almost random – an over 20% drop in accuracy. Our experiments show that it is practically feasible for multiple applications such as text generation, text summarization or machine translation to be tailored to specific traits and perceived as such.

The framing of an action influences how we perceive its actor. We introduce connotation frames of power and agency, a pragmatic formalism organized using frame semantic representations, to model how different levels of power and agency are implicitly projected on actors through their actions. We use the new power and agency frames to measure the subtle, but prevalent, gender bias in the portrayal of modern film characters and provide insights that deviate from the well-known Bechdel test. Our contributions include an extended lexicon of connotation frames along with a web interface that provides a comprehensive analysis through the lens of connotation frames.

We focus on non-standard usages of common words on social media. In the context of social media, words sometimes have other usages that are totally different from their original. In this study, we attempt to distinguish non-standard usages on social media from standard ones in an unsupervised manner. Our basic idea is that non-standardness can be measured by the inconsistency between the expected meaning of the target word and the given context. For this purpose, we use context embeddings derived from word embeddings. Our experimental results show that the model leveraging the context embedding outperforms other methods and provide us with findings, for example, on how to construct context embeddings and which corpus to use.

Social media collect and spread on the Web personal opinions, facts, fake news and all kind of information users may be interested in. Applying argument mining methods to such heterogeneous data sources is a challenging open research issue, in particular considering the peculiarities of the language used to write textual messages on social media. In addition, new issues emerge when dealing with arguments posted on such platforms, such as the need to make a distinction between personal opinions and actual facts, and to detect the source disseminating information about such facts to allow for provenance verification. In this paper, we apply supervised classification to identify arguments on Twitter, and we present two new tasks for argument mining, namely facts recognition and source identification. We study the feasibility of the approaches proposed to address these tasks on a set of tweets related to the Grexit and Brexit news topics.

This paper presents a corpus and experiments to determine dimensions of interpersonal relationships. We define a set of dimensions heavily inspired by work in social science. We create a corpus by retrieving pairs of people, and then annotating dimensions for their relationships. A corpus analysis shows that dimensions can be annotated reliably. Experimental results show that given a pair of people, values to dimensions can be assigned automatically.