Large Language Model (LLM) trained on the mixture of text and code has demonstrated impressive capability in translating natural language (NL) into structured code. In this work, we propose Code4Struct to leverage such text-to-structure translation capability to tackle structured prediction tasks in NLP. For example, Event Argument Extraction (EAE) aims to convert text into event-argument structures that can be represented as a class object using code. This alignment between structures and code enables us to take advantage of Programming Language (PL) features such as inheritance and type annotation to introduce external knowledge or add constraints with ease. We exploit the analogy between PL and NLP problems, and, as a case study, we use Code4Struct to tackle the EAE task using code generation. We ask a LLM to generate code to instantiate an event class with predicted arguments given a NL sentence. Despite only using 50 training instances for each event type, Code4Struct is comparable to fully-supervised models trained on 4,202 event instances and, when given the same 50-shot data, outperforms current state-of-the-art (SOTA) by 20.8% absolute F1. When prompted with hierarchical event types implemented using inheritance, Code4Struct can predict arguments for low-resource event types using 10-shot training instances from its sibling event type and outperforms zero-shot baseline by 12% absolute F1.
Norm discovery is important for understanding and reasoning about the acceptable behaviors and potential violations in human communication and interactions. We introduce NormSage, a framework for addressing the novel task of conversation-grounded multi-lingual, multi-cultural norm discovery, based on language model prompting and self-verification. NormSAGE leverages the expressiveness and implicit knowledge of the pretrained GPT-3 language model backbone, to elicit knowledge about norms through directed questions representing the norm discovery task and conversation context. It further addresses the risk of language model hallucination with a self-verification mechanism ensuring that the norms discovered are correct and are substantially grounded to their source conversations. Evaluation results show that our approach discovers significantly more relevant and insightful norms for conversations on-the-fly compared to baselines (>10+% in Likert scale rating). The norms discovered from Chinese conversation are also comparable to the norms discovered from English conversation in terms of insightfulness and correctness (<3% difference). In addition, the culture-specific norms are promising quality, allowing for 80% accuracy in culture pair human identification. Finally, our grounding process in norm discovery self-verification can be extended for instantiating the adherence and violation of any norm for a given conversation on-the-fly, with explainability and transparency. NormSAGE achieves an AUC of 95.4% in grounding, with natural language explanation matching human-written quality.
Multi-dimensional evaluation is the dominant paradigm for human evaluation in Natural Language Generation (NLG), i.e., evaluating the generated text from multiple explainable dimensions, such as coherence and fluency. However, automatic evaluation in NLG is still dominated by similarity-based metrics, and we lack a reliable framework for a more comprehensive evaluation of advanced models. In this paper, we propose a unified multi-dimensional evaluator UniEval for NLG. We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions. Furthermore, thanks to the unified Boolean QA format, we are able to introduce an intermediate learning phase that enables UniEval to incorporate external knowledge from multiple related tasks and gain further improvement. Experiments on three typical NLG tasks show that UniEval correlates substantially better with human judgments than existing metrics. Specifically, compared to the top-performing unified evaluators, UniEval achieves a 23% higher correlation on text summarization, and over 43% on dialogue response generation. Also, UniEval demonstrates a strong zero-shot learning ability for unseen evaluation dimensions and tasks. Source code, data and all pre-trained evaluators are available on our GitHub repository (https://github.com/maszhongming/UniEval).
Recent advances in pre-training vision-language models like CLIP have shown great potential in learning transferable visual representations. Nonetheless, for downstream inference, CLIP-like models suffer from either 1) degraded accuracy and robustness in the case of inaccurate text descriptions during retrieval-based inference (the challenge for zero-shot protocol); or 2) breaking the well-established vision-language alignment (the challenge for linear probing). To address them, we propose Decomposed Feature Prompting (DeFo). DeFo leverages a flexible number of learnable embeddings as textual input while maintaining the vision-language dual-model architecture, which enables the model to learn decomposed visual features with the help of feature-level textual prompts. We further use an additional linear layer to perform classification, allowing a scalable size of language inputs. Our empirical study shows DeFo's significance in improving the vision-language models. For example, DeFo obtains 73.2% test accuracy on ImageNet with a ResNet-50 backbone without tuning any pretrained weights of both the vision and language encoder, outperforming zero-shot CLIP by a large margin of 15.0%, and outperforming state-of-the-art vision-language prompt tuning method by 7.6%.
Although large language models have achieved impressive zero-shot ability, the huge model size generally incurs high cost. Recently, semi-parametric language models, which augment a smaller language model with an external retriever, have demonstrated promising language modeling capabilities. However, it remains unclear whether such semi-parametric language models can perform competitively well as their fully-parametric counterparts on zero-shot generalization to downstream tasks. In this work, we introduce $\text{Zemi}$, a zero-shot semi-parametric language model. To our best knowledge, this is the first semi-parametric language model that can demonstrate strong zero-shot performance on a wide range of held-out unseen tasks. We train $\text{Zemi}$ with a novel semi-parametric multitask prompted training paradigm, which shows significant improvement compared with the parametric multitask training as proposed by T0. Specifically, we augment the multitask training and zero-shot evaluation with retrieval from a large-scale task-agnostic unlabeled corpus. In order to incorporate multiple potentially noisy retrieved augmentations, we further propose a novel $\text{augmentation fusion}$ module leveraging perceiver resampler and gated cross-attention. Notably, our proposed $\text{Zemi}_\text{LARGE}$ outperforms T0-3B by 16% on all seven evaluation tasks while being 3.9x smaller in model size.
Extracting informative arguments of events from news articles is a challenging problem in information extraction, which requires a global contextual understanding of each document. While recent work on document-level extraction has gone beyond single-sentence and increased the cross-sentence inference capability of end-to-end models, they are still restricted by certain input sequence length constraints and usually ignore the global context between events. To tackle this issue, we introduce a new global neural generation-based framework for document-level event argument extraction by constructing a document memory store to record the contextual event information and leveraging it to implicitly and explicitly help with decoding of arguments for later events. Empirical results show that our framework outperforms prior methods substantially and it is more robust to adversarially annotated examples with our constrained decoding design. (Our code and resources are available at https://github.com/xinyadu/memory_docie for research purpose.)
Fact-checking has gained increasing attention due to the widespread of falsified information. Most fact-checking approaches focus on claims made in English only due to the data scarcity issue in other languages. The lack of fact-checking datasets in low-resource languages calls for an effective cross-lingual transfer technique for fact-checking. Additionally, trustworthy information in different languages can be complementary and helpful in verifying facts. To this end, we present the first fact-checking framework augmented with cross-lingual retrieval that aggregates evidence retrieved from multiple languages through a cross-lingual retriever. Given the absence of cross-lingual information retrieval datasets with claim-like queries, we train the retriever with our proposed Cross-lingual Inverse Cloze Task (X-ICT), a self-supervised algorithm that creates training instances by translating the title of a passage. The goal for X-ICT is to learn cross-lingual retrieval in which the model learns to identify the passage corresponding to a given translated title. On the X-Fact dataset, our approach achieves 2.23% absolute F1 improvement in the zero-shot cross-lingual setup over prior systems. The source code and data are publicly available at https://github.com/khuangaf/CONCRETE.
Goal-oriented generative script learning aims to generate subsequent steps based on a goal, which is an essential task to assist robots in performing stereotypical activities of daily life. We show that the performance of this task can be improved if historical states are not just captured by the linguistic instructions given to people, but are augmented with the additional information provided by accompanying images. Therefore, we propose a new task, Multimedia Generative Script Learning, to generate subsequent steps by tracking historical states in both text and vision modalities, as well as presenting the first benchmark containing 2,338 tasks and 31,496 steps with descriptive images. We aim to generate scripts that are visual-state trackable, inductive for unseen tasks, and diverse in their individual steps. We propose to encode visual state changes through a multimedia selective encoder, transferring knowledge from previously observed tasks using a retrieval-augmented decoder, and presenting the distinct information at each step by optimizing a diversity-oriented contrastive learning objective. We define metrics to evaluate both generation quality and inductive quality. Experiment results demonstrate that our approach significantly outperforms strong baselines.
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification problem where each sentence is handled individually, ignoring the internal semantic connection among sentences in the background document. In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs. Our document semantic graphs preserve sentence-level information through the use of sentence nodes and provide concept connections between sentences. We jointly apply multi-task learning for sentence-level and concept-level knowledge selection and show that it improves sentence-level selection. Our experiments show that our semantic graph-based knowledge selection improves over sentence selection baselines for both the knowledge selection task and the end-to-end response generation task on HollE and improves generalization on unseen topics in WoW.
We tackle a new task, event graph completion, which aims to predict missing event nodes for event graphs. Existing link prediction or graph completion methods have difficulty dealing with event graphs because they are usually designed for a single large graph such as a social network or a knowledge graph, rather than multiple small dynamic event graphs. Moreover, they can only predict missing edges rather than missing nodes. In this work, we propose to utilize event schema, a template that describes the stereotypical structure of event graphs, to address the above issues. Our schema-guided event graph completion approach first maps an instance event graph to a subgraph of the schema graph by a heuristic subgraph matching algorithm. Then it predicts whether a candidate event node in the schema graph should be added to the instantiated schema subgraph by characterizing two types of local topology of the schema graph: neighbors of the candidate node and the subgraph, and paths that connect the candidate node and the subgraph. These two modules are later combined together for the final prediction. We also propose a self-supervised strategy to construct training samples, as well as an inference algorithm that is specifically designed to complete event graphs. Extensive experimental results on four datasets demonstrate that our proposed method achieves state-of-the-art performance, with 4.3% to 19.4% absolute F1 gains over the best baseline method on the four datasets.