ACL 2020 Papers

We study the potential for interaction in natural language classification. We add a limited form of interaction for intent classification, where users provide an initial query using natural language, and the system asks for additional information using binary or multi-choice questions. At each turn, our system decides between asking the most informative question or making the final classification pre-diction. The simplicity of the model allows for bootstrapping of the system without interaction data, instead relying on simple crowd-sourcing tasks. We evaluate our approach on two domains, showing the benefit of interaction and the advantage of learning to balance between asking additional questions and making the final prediction.

We study the settings for which deep contextual embeddings (e.g., BERT) give large improvements in performance relative to classic pretrained embeddings (e.g., GloVe), and an even simpler baseline—random word embeddings—focusing on the impact of the training set size and the linguistic properties of the task. Surprisingly, we find that both of these simpler baselines can match contextual embeddings on industry-scale data, and often perform within 5 to 10% accuracy (absolute) on benchmark tasks. Furthermore, we identify properties of data for which contextual embeddings give particularly large gains: language containing complex structure, ambiguous word usage, and words unseen in training.

Variational Autoencoder (VAE) is widely used as a generative model to approximate a model’s posterior on latent variables by combining the amortized variational inference and deep neural networks. However, when paired with strong autoregressive decoders, VAE often converges to a degenerated local optimum known as “posterior collapse”. Previous approaches consider the Kullback–Leibler divergence (KL) individual for each datapoint. We propose to let the KL follow a distribution across the whole dataset, and analyze that it is sufficient to prevent posterior collapse by keeping the expectation of the KL’s distribution positive. Then we propose Batch Normalized-VAE (BN-VAE), a simple but effective approach to set a lower bound of the expectation by regularizing the distribution of the approximate posterior’s parameters. Without introducing any new model component or modifying the objective, our approach can avoid the posterior collapse effectively and efficiently. We further show that the proposed BN-VAE can be extended to conditional VAE (CVAE). Empirically, our approach surpasses strong autoregressive baselines on language modeling, text classification and dialogue generation, and rivals more complex approaches while keeping almost the same training time as VAE.

Visual features are a promising signal for learning bootstrap textual models. However, blackbox learning models make it difficult to isolate the specific contribution of visual components. In this analysis, we consider the case study of the Visually Grounded Neural Syntax Learner (Shi et al., 2019), a recent approach for learning syntax from a visual training signal. By constructing simplified versions of the model, we isolate the core factors that yield the model’s strong performance. Contrary to what the model might be capable of learning, we find significantly less expressive versions produce similar predictions and perform just as well, or even better. We also find that a simple lexical signal of noun concreteness plays the main role in the model’s predictions as opposed to more complex syntactic reasoning.

Generating multi-sentence descriptions for videos is one of the most challenging captioning tasks due to its high requirements for not only visual relevance but also discourse-based coherence across the sentences in the paragraph. Towards this goal, we propose a new approach called Memory-Augmented Recurrent Transformer (MART), which uses a memory module to augment the transformer architecture. The memory module generates a highly summarized memory state from the video segments and the sentence history so as to help better prediction of the next sentence (w.r.t. coreference and repetition aspects), thus encouraging coherent paragraph generation. Extensive experiments, human evaluations, and qualitative analyses on two popular datasets ActivityNet Captions and YouCookII show that MART generates more coherent and less repetitive paragraph captions than baseline methods, while maintaining relevance to the input video events.

The Minecraft Collaborative Building Task is a two-player game in which an Architect (A) instructs a Builder (B) to construct a target structure in a simulated Blocks World Environment. We define the subtask of predicting correct action sequences (block placements and removals) in a given game context, and show that capturing B’s past actions as well as B’s perspective leads to a significant improvement in performance on this challenging language understanding problem.

We apply a generative segmental model of task structure, guided by narration, to action segmentation in video. We focus on unsupervised and weakly-supervised settings where no action labels are known during training. Despite its simplicity, our model performs competitively with previous work on a dataset of naturalistic instructional videos. Our model allows us to vary the sources of supervision used in training, and we find that both task structure and narrative language provide large benefits in segmentation quality.

We introduce a new task, MultiMedia Event Extraction, which aims to extract events and their arguments from multimedia documents. We develop the first benchmark and collect a dataset of 245 multimedia news articles with extensively annotated events and arguments. We propose a novel method, Weakly Aligned Structured Embedding (WASE), that encodes structured representations of semantic information from textual and visual data into a common embedding space. The structures are aligned across modalities by employing a weakly supervised training strategy, which enables exploiting available resources without explicit cross-media annotation. Compared to uni-modal state-of-the-art methods, our approach achieves 4.0% and 9.8% absolute F-score gains on text event argument role labeling and visual event extraction. Compared to state-of-the-art multimedia unstructured representations, we achieve 8.3% and 5.0% absolute F-score gains on multimedia event extraction and argument role labeling, respectively. By utilizing images, we extract 21.4% more event mentions than traditional text-only methods.

Learning to follow instructions is of fundamental importance to autonomous agents for vision-and-language navigation (VLN). In this paper, we study how an agent can navigate long paths when learning from a corpus that consists of shorter ones. We show that existing state-of-the-art agents do not generalize well. To this end, we propose BabyWalk, a new VLN agent that is learned to navigate by decomposing long instructions into shorter ones (BabySteps) and completing them sequentially. A special design memory buffer is used by the agent to turn its past experiences into contexts for future steps. The learning process is composed of two phases. In the first phase, the agent uses imitation learning from demonstration to accomplish BabySteps. In the second phase, the agent uses curriculum-based reinforcement learning to maximize rewards on navigation tasks with increasingly longer instructions. We create two new benchmark datasets (of long navigation tasks) and use them in conjunction with existing ones to examine BabyWalk’s generalization ability. Empirical results show that BabyWalk achieves state-of-the-art results on several metrics, in particular, is able to follow long instructions better. The codes and the datasets are released on our project page: https://github.com/Sha-Lab/babywalk.

Retrieve-and-edit seq2seq methods typically retrieve an output from the training set and learn a model to edit it to produce the final output. We propose to extend this framework with a simple and effective post-generation ranking approach. Our framework (i) retrieves several potentially relevant outputs for each input, (ii) edits each candidate independently, and (iii) re-ranks the edited candidates to select the final output. We use a standard editing model with simple task-specific re-ranking approaches, and we show empirically that this approach outperforms existing, significantly more complex methodologies. Experiments on two machine translation (MT) datasets show new state-of-art results. We also achieve near state-of-art performance on the Gigaword summarization dataset, where our analyses show that there is significant room for performance improvement with better candidate output selection in future work.

Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation. Further, automatically generating words with similar semantics is challenging, and hand-crafted linguistic rules are difficult to apply. We consider a text planning scheme and present a model-based imitation-learning approach to alleviate the aforementioned issues. Specifically, we propose a novel guider network to focus on the generative process over a longer horizon, which can assist next-word prediction and provide intermediate rewards for generator optimization. Extensive experiments demonstrate that the proposed method leads to improved performance.

Missing sentence generation (or sentence in-filling) fosters a wide range of applications in natural language generation, such as document auto-completion and meeting note expansion. This task asks the model to generate intermediate missing sentences that can syntactically and semantically bridge the surrounding context. Solving the sentence infilling task requires techniques in natural language processing ranging from understanding to discourse-level planning to generation. In this paper, we propose a framework to decouple the challenge and address these three aspects respectively, leveraging the power of existing large-scale pre-trained models such as BERT and GPT-2. We empirically demonstrate the effectiveness of our model in learning a sentence representation for generation and further generating a missing sentence that fits the context.

We present a simple approach for text infilling, the task of predicting missing spans of text at any position in a document. While infilling could enable rich functionality especially for writing assistance tools, more attention has been devoted to language modeling—a special case of infilling where text is predicted at the end of a document. In this paper, we aim to extend the capabilities of language models (LMs) to the more general task of infilling. To this end, we train (or fine tune) off-the-shelf LMs on sequences containing the concatenation of artificially-masked text and the text which was masked. We show that this approach, which we call infilling by language modeling, can enable LMs to infill entire sentences effectively on three different domains: short stories, scientific abstracts, and lyrics. Furthermore, we show that humans have difficulty identifying sentences infilled by our approach as machine-generated in the domain of short stories.

Generating sequential natural language descriptions from graph-structured data (e.g., knowledge graph) is challenging, partly because of the structural differences between the input graph and the output text. Hence, popular sequence-to-sequence models, which require serialized input, are not a natural fit for this task. Graph neural networks, on the other hand, can better encode the input graph but broaden the structural gap between the encoder and decoder, making faithful generation difficult. To narrow this gap, we propose DualEnc, a dual encoding model that can not only incorporate the graph structure, but can also cater to the linear structure of the output text. Empirical comparisons with strong single-encoder baselines demonstrate that dual encoding can significantly improve the quality of the generated text.

In the last few years, a number of successful approaches have emerged that are able to adequately model various aspects of natural language. In particular, language models based on neural networks have improved the state of the art with regard to predictive language modeling, while topic models are successful at capturing clear-cut, semantic dimensions. In this paper, we will explore how these approaches can be adapted and combined to model the linguistic and literary aspects needed for poetry generation. The system is exclusively trained on standard, non-poetic text, and its output is constrained in order to confer a poetic character to the generated verse. The framework is applied to the generation of poems in both English and French, and is equally evaluated for both languages. Even though it only uses standard, non-poetic text as input, the system yields state of the art results for poetry generation.

We introduce dodecaDialogue: a set of 12 tasks that measures if a conversational agent can communicate engagingly with personality and empathy, ask questions, answer questions by utilizing knowledge resources, discuss topics and situations, and perceive and converse about images. By multi-tasking on such a broad large-scale set of data, we hope to both move towards and measure progress in producing a single unified agent that can perceive, reason and converse with humans in an open-domain setting. We show that such multi-tasking improves over a BERT pre-trained baseline, largely due to multi-tasking with very large dialogue datasets in a similar domain, and that the multi-tasking in general provides gains to both text and image-based tasks using several metrics in both the fine-tune and task transfer settings. We obtain state-of-the-art results on many of the tasks, providing a strong baseline for this challenge.

The timings of spoken response offsets in human dialogue have been shown to vary based on contextual elements of the dialogue. We propose neural models that simulate the distributions of these response offsets, taking into account the response turn as well as the preceding turn. The models are designed to be integrated into the pipeline of an incremental spoken dialogue system (SDS). We evaluate our models using offline experiments as well as human listening tests. We show that human listeners consider certain response timings to be more natural based on the dialogue context. The introduction of these models into SDS pipelines could increase the perceived naturalness of interactions.

Evaluating the quality of a dialogue interaction between two agents is a difficult task, especially in open-domain chit-chat style dialogue. There have been recent efforts to develop automatic dialogue evaluation metrics, but most of them do not generalize to unseen datasets and/or need a human-generated reference response during inference, making it infeasible for online evaluation. Here, we propose an unreferenced automated evaluation metric that uses large pre-trained language models to extract latent representations of utterances, and leverages the temporal transitions that exist between them. We show that our model achieves higher correlation with human annotations in an online setting, while not requiring true responses for comparison during inference.

To achieve the long-term goal of machines being able to engage humans in conversation, our models should captivate the interest of their speaking partners. Communication grounded in images, whereby a dialogue is conducted based on a given photo, is a setup naturally appealing to humans (Hu et al., 2014). In this work we study large-scale architectures and datasets for this goal. We test a set of neural architectures using state-of-the-art image and text representations, considering various ways to fuse the components. To test such models, we collect a dataset of grounded human-human conversations, where speakers are asked to play roles given a provided emotional mood or style, as the use of such traits is also a key factor in engagingness (Guo et al., 2019). Our dataset, Image-Chat, consists of 202k dialogues over 202k images using 215 possible style traits. Automatic metrics and human evaluations of engagingness show the efficacy of our approach; in particular, we obtain state-of-the-art performance on the existing IGC task, and our best performing model is almost on par with humans on the Image-Chat test set (preferred 47.7% of the time).