COLING 2022 论文列表

Health coaching helps patients identify and accomplish lifestyle-related goals, effectively improving the control of chronic diseases and mitigating mental health conditions. However, health coaching is cost-prohibitive due to its highly personalized and labor-intensive nature. In this paper, we propose to build a dialogue system that converses with the patients, helps them create and accomplish specific goals, and can address their emotions with empathy. However, building such a system is challenging since real-world health coaching datasets are limited and empathy is subtle. Thus, we propose a modularized health coaching dialogue with simplified NLU and NLG frameworks combined with mechanism-conditioned empathetic response generation. Through automatic and human evaluation, we show that our system generates more empathetic, fluent, and coherent responses and outperforms the state-of-the-art in NLU tasks while requiring less annotation. We view our approach as a key step towards building automated and more accessible health coaching systems.

Improving the accessibility and automation capabilities of mobile devices can have a significant positive impact on the daily lives of countless users. To stimulate research in this direction, we release a human-annotated dataset with approximately 500k unique annotations aimed at increasing the understanding of the functionality of UI elements. This dataset augments images and view hierarchies from RICO, a large dataset of mobile UIs, with annotations for icons based on their shapes and semantics, and associations between different elements and their corresponding text labels, resulting in a significant increase in the number of UI elements and the categories assigned to them. We also release models using image-only and multimodal inputs; we experiment with various architectures and study the benefits of using multimodal inputs on the new dataset. Our models demonstrate strong performance on an evaluation set of unseen apps, indicating their generalizability to newer screens. These models, combined with the new dataset, can enable innovative functionalities like referring to UI elements by their labels, improved coverage and better semantics for icons etc., which would go a long way in making UIs more usable for everyone.

Fake news detection is a challenging problem due to its tremendous real-world political and social impacts. Recent fake news detection works focus on learning news features from News Propagation Graph (NPG). However, little attention is paid to the issues of both authenticity of the relationships and topology imbalance in the structure of NPG, which trick existing methods and thus lead to incorrect prediction results. To tackle these issues, in this paper, we propose a novel Topology imbalance and Relation inauthenticity aware Hierarchical Graph Attention Networks (TR-HGAN) to identify fake news on social media. Specifically, we design a new topology imbalance smoothing strategy to measure the topology weight of each node. Besides, we adopt a hierarchical-level attention mechanism for graph convolutional learning, which can adaptively identify the authenticity of relationships by assigning appropriate weights to each of them. Experiments on real-world datasets demonstrate that TR-HGAN significantly outperforms state-of-the-art methods.

Humans use different wordings depending on the context to facilitate efficient communication. For example, instead of completely new information, information related to the preceding context is typically placed at the sentence-initial position. In this study, we analyze whether neural language models (LMs) can capture such discourse-level preferences in text generation. Specifically, we focus on a particular aspect of discourse, namely the topic-comment structure. To analyze the linguistic knowledge of LMs separately, we chose the Japanese language, a topic-prominent language, for designing probing tasks, and we created human topicalization judgment data by crowdsourcing. Our experimental results suggest that LMs have different generalizations from humans; LMs exhibited less context-dependent behaviors toward topicalization judgment. These results highlight the need for the additional inductive biases to guide LMs to achieve successful discourse-level generalization.

Target-oriented dialog aims to reach a global target through multi-turn conversation. The key to the task is the global planning towards the target, which flexibly guides the dialog concerning the context. However, existing target-oriented dialog works take a local and greedy strategy for response generation, where global planning is absent. In this work, we propose global planning for target-oriented dialog on a commonsense knowledge graph (KG). We design a global reinforcement learning with the planned paths to flexibly adjust the local response generation model towards the global target. We also propose a KG-based method to collect target-oriented samples automatically from the chit-chat corpus for model training. Experiments show that our method can reach the target with a higher success rate, fewer turns, and more coherent responses.

While pre-trained language models like BERT have achieved impressive results on various natural language processing tasks, deploying them on resource-restricted devices is challenging due to their intensive computational cost and memory footprint. Previous approaches mainly focused on training smaller versions of a BERT model with competitive accuracy under limited computational resources. In this paper, we extend Length Adaptive Transformer and propose to design Token and Head Adaptive Transformer, which can compress and accelerate various BERT-based models via simple fine-tuning. We train a transformer with a progressive token and head pruning scheme, eliminating a large number of redundant tokens and attention heads in the later layers. Then, we conduct a multi-objective evolutionary search with the overall number of floating point operations (FLOPs) as its efficiency constraint to find joint token and head pruning strategies that maximize accuracy and efficiency under various computational budgets. Empirical studies show that a large portion of tokens and attention heads could be pruned while achieving superior performance compared to the baseline BERT-based models and Length Adaptive Transformers in various downstream NLP tasks. MobileBERT trained with our joint token and head pruning scheme achieves a GLUE score of 83.0, which is 1.4 higher than Length Adaptive Transformer and 2.9 higher than the original model.

Reasoning and knowledge-related skills are considered as two fundamental skills for natural language understanding (NLU) tasks such as machine reading comprehension (MRC) and natural language inference (NLI). However, it is not clear to what extent an NLU task defined on a dataset correlates to a specific NLU skill. On the one hand, evaluating the correlation requires an understanding of the significance of the NLU skill in a dataset. Significance judges whether a dataset includes sufficient material to help the model master this skill. On the other hand, it is also necessary to evaluate the dependence of the task on the NLU skill. Dependence is a measure of how much the task defined on a dataset depends on the skill. In this paper, we propose a systematic method to diagnose the correlations between an NLU dataset and a specific skill, and then take a fundamental reasoning skill, logical reasoning, as an example for analysis. The method adopts a qualitative indicator to indicate the significance while adopting a quantitative indicator to measure the dependence. We perform diagnosis on 8 MRC datasets (including two types) and 3 NLI datasets and acquire intuitively reasonable results. We then perform the analysis to further understand the results and the proposed indicators. Based on the analysis, although the diagnostic method has some limitations, it is still an effective method to perform a basic diagnosis of the correlation between the dataset and logical reasoning skill, which also can be generalized to other NLU skills.

In this work, we discuss different threat scenarios from neural fake news generated by state-of-the-art language models. Through our experiments, we assess the performance of generated text detection systems under these threat scenarios. For each scenario, we also identify the minimax strategy for the detector that minimizes its worst-case performance. This constitutes a set of best practices that practitioners can rely on. In our analysis, we find that detectors are prone to shortcut learning (lack of out-of-distribution generalization) and discuss approaches to mitigate this problem and improve detectors more broadly. Finally, we argue that strong detectors should be released along with new generators.

Discourse parsing has proven to be useful for a number of NLP tasks that require complex reasoning. However, over a decade since the advent of the Penn Discourse Treebank, predicting implicit discourse relations in text remains challenging. There are several possible reasons for this, and we hypothesize that models should be exposed to more context as it plays an important role in accurate human annotation; meanwhile adding uncertainty measures can improve model accuracy and calibration. To thoroughly investigate this phenomenon, we perform a series of experiments to determine 1) the effects of context on human judgments, and 2) the effect of quantifying uncertainty with annotator confidence ratings on model accuracy and calibration (which we measure using the Brier score (Brier et al, 1950)). We find that including annotator accuracy and confidence improves model accuracy, and incorporating confidence in the model’s temperature function can lead to models with significantly better-calibrated confidence measures. We also find some insightful qualitative results regarding human and model behavior on these datasets.

Treebank selection for parsing evaluation and the spurious effects that might arise from a biased choice have not been explored in detail. This paper studies how evaluating on a single subset of treebanks can lead to weak conclusions. First, we take a few contrasting parsers, and run them on subsets of treebanks proposed in previous work, whose use was justified (or not) on criteria such as typology or data scarcity. Second, we run a large-scale version of this experiment, create vast amounts of random subsets of treebanks, and compare on them many parsers whose scores are available. The results show substantial variability across subsets and that although establishing guidelines for good treebank selection is hard, some inadequate strategies can be easily avoided.

Biomedical events represent complex, graphical, and semantically rich interactions expressed in the scientific literature. Almost all contributions in the event realm orbit around semantic parsing, usually employing discriminative architectures and cumbersome multi-step pipelines limited to a small number of target interaction types. We present the first lightweight framework to solve both event extraction and event verbalization with a unified text-to-text approach, allowing us to fuse all the resources so far designed for different tasks. To this end, we present a new event graph linearization technique and release highly comprehensive event-text paired datasets, covering more than 150 event types from multiple biology subareas (English language). By streamlining parsing and generation to translations, we propose baseline transformer model results according to multiple biomedical text mining benchmarks and NLG metrics. Our extractive models achieve greater state-of-the-art performance than single-task competitors and show promising capabilities for the controlled generation of coherent natural language utterances from structured data.

Access to higher education is critical for minority populations and emergent bilingual students. However, the language used by higher education institutions to communicate with prospective students is often too complex; concretely, many institutions in the US publish admissions application instructions far above the average reading level of a typical high school graduate, often near the 13th or 14th grade level. This leads to an unnecessary barrier between students and access to higher education. This work aims to tackle this challenge via text simplification. We present PSAT (Professionally Simplified Admissions Texts), a dataset with 112 admissions instructions randomly selected from higher education institutions across the US. These texts are then professionally simplified, and verified and accepted by subject-matter experts who are full-time employees in admissions offices at various institutions. Additionally, PSAT comes with manual alignments of 1,883 original-simplified sentence pairs. The result is a first-of-its-kind corpus for the evaluation and fine-tuning of text simplification systems in a high-stakes genre distinct from existing simplification resources.

Previous work has demonstrated that pre-trained large language models (LLM) acquire knowledge during pre-training which enables reasoning over relationships between words (e.g, hyponymy) and more complex inferences over larger units of meaning such as sentences. Here, we investigate whether lexical entailment (LE, i.e. hyponymy or the is a relation between words) can be generalised in a compositional manner. Accordingly, we introduce PLANE (Phrase-Level Adjective-Noun Entailment), a new benchmark to test models on fine-grained compositional entailment using adjective-noun phrases. Our experiments show that knowledge extracted via In–Context and transfer learning is not enough to solve PLANE. However, a LLM trained on PLANE can generalise well to out–of–distribution sets, since the required knowledge can be stored in the representations of subwords (SW) tokens.

The recently proposed capability-based NLP testing allows model developers to test the functional capabilities of NLP models, revealing functional failures for models with good held-out evaluation scores. However, existing work on capability-based testing requires the developer to compose each individual test template from scratch. Such approach thus requires extensive manual efforts and is less scalable. In this paper, we investigate a different approach that requires the developer to only annotate a few test templates, while leveraging the GPT-3 engine to generate the majority of test cases. While our approach saves the manual efforts by design, it guarantees the correctness of the generated suites with a validity checker. Moreover, our experimental results show that the test suites generated by GPT-3 are more diverse than the manually created ones; they can also be used to detect more errors compared to manually created counterparts. Our test suites can be downloaded at https://anonymous-researcher-nlp.github.io/testaug/.

Knowledge Graphs (KGs) stores world knowledge that benefits various reasoning-based applications. Due to their incompleteness, a fundamental task for KGs, which is known as Knowledge Graph Completion (KGC), is to perform link prediction and infer new facts based on the known facts. Recently, link prediction on the temporal KGs becomes an active research topic. Numerous Temporal Knowledge Graph Completion (TKGC) methods have been proposed by mapping the entities and relations in TKG to the high-dimensional representations. However, most existing TKGC methods are mainly based on deterministic vector embeddings, which are not flexible and expressive enough. In this paper, we propose a novel TKGC method, TKGC-AGP, by mapping the entities and relations in TKG to the approximations of multivariate Gaussian processes (MGPs). Equipped with the flexibility and capacity of MGP, the global trends as well as the local fluctuations in the TKGs can be simultaneously modeled. Moreover, the temporal uncertainties can be also captured with the kernel function and the covariance matrix of MGP. Moreover, a first-order Markov assumption-based training algorithm is proposed to effective optimize the proposed method. Experimental results show the effectiveness of the proposed approach on two real-world benchmark datasets compared with some state-of-the-art TKGC methods.

Language evolves over time, and word meaning changes accordingly. This is especially true in social media, since its dynamic nature leads to faster semantic shifts, making it challenging for NLP models to deal with new content and trends. However, the number of datasets and models that specifically address the dynamic nature of these social platforms is scarce. To bridge this gap, we present TempoWiC, a new benchmark especially aimed at accelerating research in social media-based meaning shift. Our results show that TempoWiC is a challenging benchmark, even for recently-released language models specialized in social media.

Answering complex questions that require multi-step multi-type reasoning over raw text is challenging, especially when conducting numerical reasoning. Neural Module Networks (NMNs), follow the programmer-interpreter framework and design trainable modules to learn different reasoning skills. However, NMNs only have limited reasoning abilities, and lack numerical reasoning capability. We upgrade NMNs by: (a) bridging the gap between its interpreter and the complex questions; (b) introducing addition and subtraction modules that perform numerical reasoning over numbers. On a subset of DROP, experimental results show that our proposed methods enhance NMNs’ numerical reasoning skills by 17.7% improvement of F1 score and significantly outperform previous state-of-the-art models.

Prior studies addressing target-oriented conversational tasks lack a crucial notion that has been intensively studied in the context of goal-oriented artificial intelligence agents, namely, planning. In this study, we propose the task of Target-Guided Open-Domain Conversation Planning (TGCP) task to evaluate whether neural conversational agents have goal-oriented conversation planning abilities. Using the TGCP task, we investigate the conversation planning abilities of existing retrieval models and recent strong generative models. The experimental results reveal the challenges facing current technology.

Stance detection aims to identify the attitude from an opinion towards a certain target. Despite the significant progress on this task, it is extremely time-consuming and budget-unfriendly to collect sufficient high-quality labeled data for every new target under fully-supervised learning, whereas unlabeled data can be collected easier. Therefore, this paper is devoted to few-shot stance detection and investigating how to achieve satisfactory results in semi-supervised settings. As a target-oriented task, the core idea of semi-supervised few-shot stance detection is to make better use of target-relevant information from labeled and unlabeled data. Therefore, we develop a novel target-aware semi-supervised framework. Specifically, we propose a target-aware contrastive learning objective to learn more distinguishable representations for different targets. Such an objective can be easily applied with or without unlabeled data. Furthermore, to thoroughly exploit the unlabeled data and facilitate the model to learn target-relevant stance features in the opinion content, we explore a simple but effective target-aware consistency regularization combined with a self-training strategy. The experimental results demonstrate that our approach can achieve state-of-the-art performance on multiple benchmark datasets in the few-shot setting.