ACL 2022 Papers

Procedural text contains rich anaphoric phenomena, yet has not received much attention in NLP. To fill this gap, we investigate the textual properties of two types of procedural text, recipes and chemical patents, and generalize an anaphora annotation framework developed for the chemical domain for modeling anaphoric phenomena in recipes. We apply this framework to annotate the RecipeRef corpus with both bridging and coreference relations. Through comparison to chemical patents, we show the complexity of anaphora resolution in recipes. We demonstrate empirically that transfer learning from the chemical domain improves resolution of anaphora in recipes, suggesting transferability of general procedural knowledge.

Deep learning has demonstrated performance advantages in a wide range of natural language processing tasks, including neural machine translation (NMT). Transformer NMT models are typically strengthened by deeper encoder layers, but deepening their decoder layers usually results in failure. In this paper, we first identify the cause of the failure of the deep decoder in the Transformer model. Inspired by this discovery, we then propose approaches to improving it, with respect to model structure and model training, to make the deep decoder practical in NMT. Specifically, with respect to model structure, we propose a cross-attention drop mechanism to allow the decoder layers to perform their own different roles, to reduce the difficulty of deep-decoder learning. For model training, we propose a collapse reducing training approach to improve the stability and effectiveness of deep-decoder training. We experimentally evaluated our proposed Transformer NMT model structure modification and novel training methods on several popular machine translation benchmarks. The results showed that deepening the NMT model by increasing the number of decoder layers successfully prevented the deepened decoder from degrading to an unconditional language model. In contrast to prior work on deepening an NMT model on the encoder, our method can deepen the model on both the encoder and decoder at the same time, resulting in a deeper model and improved performance.

For a natural language understanding benchmark to be useful in research, it has to consist of examples that are diverse and difficult enough to discriminate among current and near-future state-of-the-art systems. However, we do not yet know how best to select text sources to collect a variety of challenging examples. In this study, we crowdsource multiple-choice reading comprehension questions for passages taken from seven qualitatively distinct sources, analyzing what attributes of passages contribute to the difficulty and question types of the collected examples. To our surprise, we find that passage source, length, and readability measures do not significantly affect question difficulty. Through our manual annotation of seven reasoning types, we observe several trends between passage sources and reasoning types, e.g., logical reasoning is more often required in questions written for technical passages. These results suggest that when creating a new benchmark dataset, selecting a diverse set of passages can help ensure a diverse range of question types, but that passage difficulty need not be a priority.

Recent researches show that multi-criteria resources and n-gram features are beneficial to Chinese Word Segmentation (CWS). However, these methods rely heavily on such additional information mentioned above and focus less on the model itself. We thus propose a novel neural framework, named Weighted self Distillation for Chinese word segmentation (WeiDC). The framework, which only requires unigram features, adopts self-distillation technology with four hand-crafted weight modules and two teacher models configurations. Experiment results show that WeiDC can make use of character features to learn contextual knowledge and successfully achieve state-of-the-art or competitive performance in terms of strictly closed test settings on SIGHAN Bakeoff benchmark datasets. Moreover, further experiments and analyses also demonstrate the robustness of WeiDC. Source codes of this paper are available on Github.

Word and morpheme segmentation are fundamental steps of language documentation as they allow to discover lexical units in a language for which the lexicon is unknown. However, in most language documentation scenarios, linguists do not start from a blank page: they may already have a pre-existing dictionary or have initiated manual segmentation of a small part of their data. This paper studies how such a weak supervision can be taken advantage of in Bayesian non-parametric models of segmentation. Our experiments on two very low resource languages (Mboshi and Japhug), whose documentation is still in progress, show that weak supervision can be beneficial to the segmentation quality. In addition, we investigate an incremental learning scenario where manual segmentations are provided in a sequential manner. This work opens the way for interactive annotation tools for documentary linguists.

We contribute a new dataset for the task of automated fact checking and an evaluation of state of the art algorithms. The dataset includes claims (from speeches, interviews, social media and news articles), review articles published by professional fact checkers and premise articles used by those professional fact checkers to support their review and verify the veracity of the claims. An important challenge in the use of premise articles is the identification of relevant passages that will help to infer the veracity of a claim. We show that transferring a dense passage retrieval model trained with review articles improves the retrieval quality of passages in premise articles. We report results for the prediction of claim veracity by inference from premise articles.

Signed Language Processing (SLP) concerns the automated processing of signed languages, the main means of communication of Deaf and hearing impaired individuals. SLP features many different tasks, ranging from sign recognition to translation and production of signed speech, but has been overlooked by the NLP community thus far. In this paper, we bring to attention the task of modelling the phonology of sign languages. We leverage existing resources to construct a large-scale dataset of American Sign Language signs annotated with six different phonological properties. We then conduct an extensive empirical study to investigate whether data-driven end-to-end and feature-based approaches can be optimised to automatically recognise these properties. We find that, despite the inherent challenges of the task, graph-based neural networks that operate over skeleton features extracted from raw videos are able to succeed at the task to a varying degree. Most importantly, we show that this performance pertains even on signs unobserved during training.

Natural language applied to natural 2D images describes a fundamentally 3D world. We present the Voxel-informed Language Grounder (VLG), a language grounding model that leverages 3D geometric information in the form of voxel maps derived from the visual input using a volumetric reconstruction model. We show that VLG significantly improves grounding accuracy on SNARE, an object reference game task. At the time of writing, VLG holds the top place on the SNARE leaderboard, achieving SOTA results with a 2.0% absolute improvement.

Probing is popular to analyze whether linguistic information can be captured by a well-trained deep neural model, but it is hard to answer how the change of the encoded linguistic information will affect task performance. To this end, we study the dynamic relationship between the encoded linguistic information and task performance from the viewpoint of Pareto Optimality. Its key idea is to obtain a set of models which are Pareto-optimal in terms of both objectives. From this viewpoint, we propose a method to optimize the Pareto-optimal models by formalizing it as a multi-objective optimization problem. We conduct experiments on two popular NLP tasks, i.e., machine translation and language modeling, and investigate the relationship between several kinds of linguistic information and task performances. Experimental results demonstrate that the proposed method is better than a baseline method. Our empirical findings suggest that some syntactic information is helpful for NLP tasks whereas encoding more syntactic information does not necessarily lead to better performance, because the model architecture is also an important factor.

Vision-language navigation (VLN) is a challenging task due to its large searching space in the environment. To address this problem, previous works have proposed some methods of fine-tuning a large model that pretrained on large-scale datasets. However, the conventional fine-tuning methods require extra human-labeled navigation data and lack self-exploration capabilities in environments, which hinders their generalization of unseen scenes. To improve the ability of fast cross-domain adaptation, we propose Prompt-based Environmental Self-exploration (ProbES), which can self-explore the environments by sampling trajectories and automatically generates structured instructions via a large-scale cross-modal pretrained model (CLIP). Our method fully utilizes the knowledge learned from CLIP to build an in-domain dataset by self-exploration without human labeling. Unlike the conventional approach of fine-tuning, we introduce prompt tuning to achieve fast adaptation for language embeddings, which substantially improves the learning efficiency by leveraging prior knowledge. By automatically synthesizing trajectory-instruction pairs in any environment without human supervision and instruction prompt tuning, our model can adapt to diverse vision-language navigation tasks, including VLN and REVERIE. Both qualitative and quantitative results show that our ProbES significantly improves the generalization ability of the navigation model.

A long-term goal of AI research is to build intelligent agents that can communicate with humans in natural language, perceive the environment, and perform real-world tasks. Vision-and-Language Navigation (VLN) is a fundamental and interdisciplinary research topic towards this goal, and receives increasing attention from natural language processing, computer vision, robotics, and machine learning communities. In this paper, we review contemporary studies in the emerging field of VLN, covering tasks, evaluation metrics, methods, etc. Through structured analysis of current progress and challenges, we also highlight the limitations of current VLN and opportunities for future work. This paper serves as a thorough reference for the VLN research community.

As an important task in sentiment analysis, Multimodal Aspect-Based Sentiment Analysis (MABSA) has attracted increasing attention inrecent years. However, previous approaches either (i) use separately pre-trained visual and textual models, which ignore the crossmodalalignment or (ii) use vision-language models pre-trained with general pre-training tasks, which are inadequate to identify fine-grainedaspects, opinions, and their alignments across modalities. To tackle these limitations, we propose a task-specific Vision-LanguagePre-training framework for MABSA (VLP-MABSA), which is a unified multimodal encoder-decoder architecture for all the pretrainingand downstream tasks. We further design three types of task-specific pre-training tasks from the language, vision, and multimodalmodalities, respectively. Experimental results show that our approach generally outperforms the state-of-the-art approaches on three MABSA subtasks. Further analysis demonstrates the effectiveness of each pre-training task. The source code is publicly released at https://github.com/NUSTM/VLP-MABSA.

Despite profound successes, contrastive representation learning relies on carefully designed data augmentations using domain-specific knowledge. This challenge is magnified in natural language processing, where no general rules exist for data augmentation due to the discrete nature of natural language. We tackle this challenge by presenting a Virtual augmentation Supported Contrastive Learning of sentence representations (VaSCL). Originating from the interpretation that data augmentation essentially constructs the neighborhoods of each training instance, we, in turn, utilize the neighborhood to generate effective data augmentations. Leveraging the large training batch size of contrastive learning, we approximate the neighborhood of an instance via its K-nearest in-batch neighbors in the representation space. We then define an instance discrimination task regarding the neighborhood and generate the virtual augmentation in an adversarial training manner. We access the performance of VaSCL on a wide range of downstream tasks and set a new state-of-the-art for unsupervised sentence representation learning.

Coreference resolution over semantic graphs like AMRs aims to group the graph nodes that represent the same entity. This is a crucial step for making document-level formal semantic representations. With annotated data on AMR coreference resolution, deep learning approaches have recently shown great potential for this task, yet they are usually data hunger and annotations are costly. We propose a general pretraining method using variational graph autoencoder (VGAE) for AMR coreference resolution, which can leverage any general AMR corpus and even automatically parsed AMR data. Experiments on benchmarks show that the pretraining approach achieves performance gains of up to 6% absolute F1 points. Moreover, our model significantly improves on the previous state-of-the-art model by up to 11% F1.

Interactive robots navigating photo-realistic environments need to be trained to effectively leverage and handle the dynamic nature of dialogue in addition to the challenges underlying vision-and-language navigation (VLN). In this paper, we present VISITRON, a multi-modal Transformer-based navigator better suited to the interactive regime inherent to Cooperative Vision-and-Dialog Navigation (CVDN). VISITRON is trained to: i) identify and associate object-level concepts and semantics between the environment and dialogue history, ii) identify when to interact vs. navigate via imitation learning of a binary classification head. We perform extensive pre-training and fine-tuning ablations with VISITRON to gain empirical insights and improve performance on CVDN. VISITRON’s ability to identify when to interact leads to a natural generalization of the game-play mode introduced by Roman et al. (2020) for enabling the use of such models in different environments. VISITRON is competitive with models on the static CVDN leaderboard and attains state-of-the-art performance on the Success weighted by Path Length (SPL) metric.

English Natural Language Understanding (NLU) systems have achieved great performances and even outperformed humans on benchmarks like GLUE and SuperGLUE. However, these benchmarks contain only textbook Standard American English (SAE). Other dialects have been largely overlooked in the NLP community. This leads to biased and inequitable NLU systems that serve only a sub-population of speakers. To understand disparities in current models and to facilitate more dialect-competent NLU systems, we introduce the VernAcular Language Understanding Evaluation (VALUE) benchmark, a challenging variant of GLUE that we created with a set of lexical and morphosyntactic transformation rules. In this initial release (V.1), we construct rules for 11 features of African American Vernacular English (AAVE), and we recruit fluent AAVE speakers to validate each feature transformation via linguistic acceptability judgments in a participatory design manner. Experiments show that these new dialectal features can lead to a drop in model performance.

We propose VALSE (Vision And Language Structured Evaluation), a novel benchmark designed for testing general-purpose pretrained vision and language (V&L) models for their visio-linguistic grounding capabilities on specific linguistic phenomena. VALSE offers a suite of six tests covering various linguistic constructs. Solving these requires models to ground linguistic phenomena in the visual modality, allowing more fine-grained evaluations than hitherto possible. We build VALSE using methods that support the construction of valid foils, and report results from evaluating five widely-used V&L models. Our experiments suggest that current models have considerable difficulty addressing most phenomena. Hence, we expect VALSE to serve as an important benchmark to measure future progress of pretrained V&L models from a linguistic perspective, complementing the canonical task-centred V&L evaluations.

In this work, we present an extensive study on the use of pre-trained language models for the task of automatic Counter Narrative (CN) generation to fight online hate speech in English. We first present a comparative study to determine whether there is a particular Language Model (or class of LMs) and a particular decoding mechanism that are the most appropriate to generate CNs. Findings show that autoregressive models combined with stochastic decodings are the most promising. We then investigate how an LM performs in generating a CN with regard to an unseen target of hate. We find out that a key element for successful ‘out of target’ experiments is not an overall similarity with the training data but the presence of a specific subset of training data, i. e. a target that shares some commonalities with the test target that can be defined a-priori. We finally introduce the idea of a pipeline based on the addition of an automatic post-editing step to refine generated CNs.

The environmental costs of research are progressively important to the NLP community and their associated challenges are increasingly debated. In this work, we analyse the carbon cost (measured as CO2-equivalent) associated with journeys made by researchers attending in-person NLP conferences. We obtain the necessary data by text-mining all publications from the ACL anthology available at the time of the study (n=60,572) and extracting information about an author’s affiliation, including their address. This allows us to estimate the corresponding carbon cost and compare it to previously known values for training large models. Further, we look at the benefits of in-person conferences by demonstrating that they can increase participation diversity by encouraging attendance from the region surrounding the host country. We show how the trade-off between carbon cost and diversity of an event depends on its location and type. Our aim is to foster further discussion on the best way to address the joint issue of emissions and diversity in the future.