EMNLP 2022 Papers

Incorporating large-scale pre-trained models with the prototypical neural networks is a de-facto paradigm in few-shot named entity recognition. Existing methods, unfortunately, are not aware of the fact that embeddings from pre-trained models contain a prominently large amount of information regarding word frequencies, biasing prototypical neural networks against learning word entities. This discrepancy constrains the two models’ synergy. Thus, we propose a one-line-code normalization method to reconcile such a mismatch with empirical and theoretical grounds. Our experiments based on nine benchmark datasets show the superiority of our method over the counterpart models and are comparable to the state-of-the-art methods. In addition to the model enhancement, our work also provides an analytical viewpoint for addressing the general problems in few-shot name entity recognition or other tasks that rely on pre-trained models or prototypical neural networks.

Reasoning over natural language is a long-standing goal for the research community. However, studies have shown that existing language models are inadequate in reasoning. To address the issue, we present POET, a novel reasoning pre-training paradigm. Through pre-training language models with programs and their execution results, POET empowers language models to harvest the reasoning knowledge possessed by program executors via a data-driven approach. POET is conceptually simple and can be instantiated by different kinds of program executors. In this paper, we showcase two simple instances POET-Math and POET-Logic, in addition to a complex instance, POET-SQL. Experimental results on six benchmarks demonstrate that POET can significantly boost model performance in natural language reasoning, such as numerical reasoning, logical reasoning, and multi-hop reasoning. POET opens a new gate on reasoning-enhancement pre-training, and we hope our analysis would shed light on the future research of reasoning like program executors.

Large language models can produce fluent dialogue but often hallucinate factual inaccuracies. While retrieval-augmented models help alleviate this issue, they still face a difficult challenge of both reasoning to provide correct knowledge and generating conversation simultaneously. In this work, we propose a modular model, Knowledge to Response (K2R), for incorporating knowledge into conversational agents, which breaks down this problem into two easier steps. K2R first generates a knowledge sequence, given a dialogue context, as an intermediate step. After this “reasoning step”, the model then attends to its own generated knowledge sequence, as well as the dialogue context, to produce a final response. In detailed experiments, we find that such a model hallucinates less in knowledge-grounded dialogue tasks, and has advantages in terms of interpretability and modularity. In particular, it can be used to fuse QA and dialogue systems together to enable dialogue agents to give knowledgeable answers, or QA models to give conversational responses in a zero-shot setting.

Reasoning over tabular data requires both table structure understanding and a broad set of table reasoning skills. Current models with table-specific architectures and pre-training methods perform well on understanding table structures, but they still struggle with tasks that require various table reasoning skills. In this work, we develop ReasTAP to show that high-level table reasoning skills can be injected into models during pre-training without a complex table-specific architecture design. We define 7 table reasoning skills, such as numerical operation, temporal comparison, and conjunction. Each reasoning skill is associated with one example generator, which synthesizes questions over semi-structured tables according to the sampled templates. We model the table pre-training task as a sequence generation task and pre-train ReasTAP to generate precise answers of the synthetic examples. ReasTAP is evaluated on four benchmarks covering three downstream tasks including 1) WikiSQL-Weak and WikiTQ for Table Question Answering, 2) TabFact for Table Fact Verification, and 3) LogicNLG for Faithful Table-to-Text Generation. Experimental results demonstrate that ReasTAP achieves new state-of-the-art results on all of them and delivers a significant improvement under low-resource setting. Our code is publicly available at https://github.com/Yale-LILY/ReasTAP.

Existing approaches to constructing training data for Natural Language Inference (NLI) tasks, such as for semi-structured table reasoning, are either via crowdsourcing or fully automatic methods. However, the former is expensive and time consuming and thus limits scale, and the latter often produces naive examples that may lack complex reasoning. This paper develops a realistic semi-automated framework for data augmentation for tabular inference. Instead of manually generating a hypothesis for each table, our methodology generates hypothesis templates transferable to similar tables. In addition, our framework entails the creation of rational counterfactual tables based on human written logical constraints and premise paraphrasing. For our case study, we use the INFOTABS (Gupta et al., 2020), which is an entity centric tabular inference dataset. We observed that our framework could generate human-like tabular inference examples, which could benefit training data augmentation, especially in the scenario with limited supervision.

Different from general documents, it is recognised that the ease with which people can understand a biomedical text is eminently varied, owing to the highly technical nature of biomedical documents and the variance of readers’ domain knowledge. However, existing biomedical document summarization systems have paid little attention to readability control, leaving users with summaries that are incompatible with their levels of expertise.In recognition of this urgent demand, we introduce a new task of readability controllable summarization for biomedical documents, which aims to recognise users’ readability demands and generate summaries that better suit their needs: technical summaries for experts and plain language summaries (PLS) for laymen.To establish this task, we construct a corpus consisting of biomedical papers with technical summaries and PLSs written by the authors, and benchmark multiple advanced controllable abstractive and extractive summarization models based on pre-trained language models (PLMs) with prevalent controlling and generation techniques.Moreover, we propose a novel masked language model (MLM) based metric and its variant to effectively evaluate the readability discrepancy between lay and technical summaries.Experimental results from automated and human evaluations show that though current control techniques allow for a certain degree of readability adjustment during generation, the performance of existing controllable summarization methods is far from desirable in this task.

Knowledge Graph Question Answering (KGQA) involves retrieving entities as answers from a Knowledge Graph (KG) using natural language queries. The challenge is to learn to reason over question-relevant KG facts that traverse KG entities and lead to the question answers. To facilitate reasoning, the question is decoded into instructions, which are dense question representations used to guide the KG traversals. However, if the derived instructions do not exactly match the underlying KG information, they may lead to reasoning under irrelevant context.Our method, termed ReaRev, introduces a new way to KGQA reasoning with respectto both instruction decoding and execution. To improve instruction decoding, we perform reasoning in an adaptive manner, where KG-aware information is used to iteratively update the initial instructions. To improve instruction execution, we emulate breadth-first search (BFS) with graph neural networks (GNNs). The BFS strategy treats the instructions as a set and allows our method to decide on their execution order on the fly. Experimental results on three KGQA benchmarks demonstrate the ReaRev’s effectiveness compared with previous state-of-the-art, especially when the KG is incomplete or when we tackle complex questions. Our code is publicly available at https://github.com/cmavro/ReaRev_KGQA.

We study the problem of extracting N-ary relation tuples from scientific articles. This task is challenging because the target knowledge tuples can reside in multiple parts and modalities of the document. Our proposed method ReSel decomposes this task into a two-stage procedure that first retrieves the most relevant paragraph/table and then selects the target entity from the retrieved component. For the high-level retrieval stage, ReSel designs a simple and effective feature set, which captures multi-level lexical and semantic similarities between the query and components. For the low-level selection stage, ReSel designs a cross-modal entity correlation graph along with a multi-view architecture, which models both semantic and document-structural relations between entities. Our experiments on three scientific information extraction datasets show that ReSel outperforms state-of-the-art baselines significantly.

Causal chain reasoning (CCR) is an essential ability for many decision-making AI systems, which requires the model to build reliable causal chains by connecting causal pairs. However, CCR suffers from two main transitive problems: threshold effect and scene drift. In other words, the causal pairs to be spliced may have a conflicting threshold boundary or scenario.To address these issues, we propose a novel Reliable Causal chain reasoning framework (ReCo), which introduces exogenous variables to represent the threshold and scene factors of each causal pair within the causal chain, and estimates the threshold and scene contradictions across exogenous variables via structural causal recurrent neural networks (SRNN). Experiments show that ReCo outperforms a series of strong baselines on both Chinese and English CCR datasets. Moreover, by injecting reliable causal chain knowledge distilled by ReCo, BERT can achieve better performances on four downstream causal-related tasks than BERT models enhanced by other kinds of knowledge.

We consider the problem of automatically generating longer stories of over two thousand words. Compared to prior work on shorter stories, long-range plot coherence and relevance are more central challenges here. We propose the Recursive Reprompting and Revision framework (Re3) to address these challenges by (a) prompting a general-purpose language model to construct a structured overarching plan, and (b) generating story passages by repeatedly injecting contextual information from both the plan and current story state into a language model prompt. We then revise by (c) reranking different continuations for plot coherence and premise relevance, and finally (d) editing the best continuation for factual consistency. Compared to similar-length stories generated directly from the same base model, human evaluators judged substantially more of Re3’s stories as having a coherent overarching plot (by 14% absolute increase), and relevant to the given initial premise (by 20%).

For users to trust model predictions, they need to understand model outputs, particularly their confidence — calibration aims to adjust (calibrate) models’ confidence to match expected accuracy. We argue that the traditional calibration evaluation does not promote effective calibrations: for example, it can encourage always assigning a mediocre confidence score to all predictions, which does not help users distinguish correct predictions from wrong ones. Building on those observations, we propose a new calibration metric, MacroCE, that better captures whether the model assigns low confidence to wrong predictions and high confidence to correct predictions. Focusing on the practical application of open-domain question answering, we examine conventional calibration methods applied on the widely-used retriever-reader pipeline, all of which do not bring significant gains under our new MacroCE metric. Toward better calibration, we propose a new calibration method (ConsCal) that uses not just final model predictions but whether multiple model checkpoints make consistent predictions. Altogether, we provide an alternative view of calibration along with a new metric, re-evaluation of existing calibration methods on our metric, and proposal of a more effective calibration method.

Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also contains such artifacts. To address these issues we present RankGen, a 1.2B parameter encoder model for English that scores model generations given a prefix. RankGen can be flexibly incorporated as a scoring function in beam search and used to decode from any pretrained language model. We train RankGen using large-scale contrastive learning to map a prefix close to the ground-truth sequence that follows it and far away from two types of negatives: (1) random sequences from the same document as the prefix, and (2) sequences generated from a large language model conditioned on the prefix. Experiments across four different language models (345M-11B parameters) and two domains show that RankGen significantly outperforms decoding algorithms like nucleus, top-k, and typical sampling on both automatic metrics (85.0 vs 77.3 MAUVE) as well as human evaluations with English writers (74.5% human preference over nucleus sampling). Analysis reveals that RankGen outputs are more relevant to the prefix and improve continuity and coherence compared to baselines. We release our model checkpoints, code, and human preference data with explanations to facilitate future research.

Knowledge underpins reasoning. Recent research demonstrates that when relevant knowledge is provided as additional context to commonsense question answering (QA), it can substantially enhance the performance even on top of state-of-the-art. The fundamental challenge is where and how to find such knowledge that is high quality and on point with respect to the question; knowledge retrieved from knowledge bases are incomplete and knowledge generated from language models are inconsistent.We present Rainier, or Reinforced Knowledge Introspector, that learns to generate contextually relevant knowledge in response to given questions. Our approach starts by imitating knowledge generated by GPT-3, then learns to generate its own knowledge via reinforcement learning where rewards are shaped based on the increased performance on the resulting question answering. Rainier demonstrates substantial and consistent performance gains when tested over 9 different commonsense benchmarks: including 5 datasets that are seen during model training, as well as 4 datasets that are kept unseen. Our work is the first to report that knowledge generated by models that are orders of magnitude smaller than GPT-3, even without direct supervision on the knowledge itself, can exceed the quality of commonsense knowledge elicited from GPT-3.

Video language pre-training methods have mainly adopted sparse sampling techniques to alleviate the temporal redundancy of videos. Though effective, sparse sampling still suffers inter-modal redundancy: visual redundancy and textual redundancy. Compared with highly generalized text, sparsely sampled frames usually contain text-independent portions, called visual redundancy. Sparse sampling is also likely to miss important frames corresponding to some text portions, resulting in textual redundancy. Inter-modal redundancy leads to a mismatch of video and text information, hindering the model from better learning the shared semantics across modalities. To alleviate it, we propose Redundancy-aware Video-language Pre-training. We design a redundancy measurement of video patches and text tokens by calculating the cross-modal minimum dis-similarity. Then, we penalize the high-redundant video patches and text tokens through a proposed redundancy-aware contrastive learning. We evaluate our method on four benchmark datasets, MSRVTT, MSVD, DiDeMo, and LSMDC, achieving a significant improvement over the previous state-of-the-art results.

Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks.A large body of defense methods has been proposed. However, they are still limited due to redundant attack search spaces and the inability to defend against various types of attacks.In this work, we present a novel fine-tuning approach called RObust SEletive fine-tuning (ROSE) to address this issue.ROSE conducts selective updates when adapting pre-trained models to downstream tasks, filtering out invaluable and unrobust updates of parameters.Specifically, we propose two strategies: the first-order and second-order ROSE for selecting target robust parameters.The experimental results show that ROSE achieves significant improvements in adversarial robustness on various downstream NLP tasks, and the ensemble method even surpasses both variants above.Furthermore, ROSE can be easily incorporated into existing fine-tuning methods to improve their adversarial robustness further.The empirical analysis confirms that ROSE eliminates unrobust spurious updates during fine-tuning, leading to solutions corresponding to flatter and wider optima than the conventional method.Code is available at https://github.com/jiangllan/ROSE.

Prompting has shown impressive success in enabling large pre-trained language models (LMs) to perform diverse NLP tasks, especially with only few downstream data. Automatically finding the optimal prompt for each task, however, is challenging. Most existing work resorts to tuning *soft* prompts (e.g., embeddings) which fall short of interpretability, reusability across LMs, and applicability when gradients are not accessible. *Discrete* prompts, on the other hand, are difficult to optimize, and are often created by “enumeration (e.g., paraphrasing)-then-selection” heuristics that do not explore the prompt space systematically. This paper proposes RLPrompt, an efficient discrete prompt optimization approach with reinforcement learning (RL). RLPrompt formulates a parameter-efficient policy network that generates the optimized discrete prompt after training with reward. To harness the complex and stochastic reward signals from the large LM environment, we incorporate effective reward stabilization that substantially enhances training efficiency. RLPrompt is flexibly applicable to different types of LMs, such as masked (e.g., BERT) and left-to-right models (e.g., GPTs), for both classification and generation tasks. Experiments on few-shot classification and unsupervised text style transfer show superior performance over a wide range of existing fine-tuning or prompting methods. Interestingly, the resulting optimized prompts are often ungrammatical gibberish text; and surprisingly, those gibberish prompts are transferrable between different LMs to retain significant performance, indicating that LM prompting may not follow human language patterns.

Interpreting the reasoning process from questions to answers poses a challenge in approaching explainable QA. A recently proposed structured reasoning format, entailment tree, manages to offer explicit logical deductions with entailment steps in a tree structure. To generate entailment trees, prior single pass sequence-to-sequence models lack visible internal decision probability, while stepwise approaches are supervised with extracted single step data and cannot model the tree as a whole. In this work, we propose RLET, a Reinforcement Learning based Entailment Tree generation framework, which is trained utilising the cumulative signals across the whole tree. RLET iteratively performs single step reasoning with sentence selection and deduction generation modules, from which the training signal is accumulated across the tree with elaborately designed aligned reward function that is consistent with the evaluation. To the best of our knowledge, we are the first to introduce RL into the entailment tree generation task. Experiments on three settings of the EntailmentBank dataset demonstrate the strength of using RL framework.

Reinforcement learning (RL) is frequently employed in fine-tuning large language models (LMs), such as GPT-3, to penalize them for undesirable features of generated sequences, such as offensiveness, social bias, harmfulness or falsehood. The RL formulation involves treating the LM as a policy and updating it to maximise the expected value of a reward function which captures human preferences, such as non-offensiveness. In this paper, we analyze challenges associated with treating a language model as an RL policy and show how avoiding those challenges requires moving beyond the RL paradigm. We start by observing that the standard RL approach is flawed as an objective for fine-tuning LMs because it leads to distribution collapse: turning the LM into a degenerate distribution. Then, we analyze KL-regularised RL, a widely used recipe for fine-tuning LMs, which additionally constrains the fine-tuned LM to stay close to its original distribution in terms of Kullback-Leibler (KL) divergence. We show that KL-regularised RL is equivalent to variational inference: approximating a Bayesian posterior which specifies how to update a prior LM to conform with evidence provided by the reward function. We argue that this Bayesian inference view of KL-regularised RL is more insightful than the typically employed RL perspective. The Bayesian inference view explains how KL-regularised RL avoids the distribution collapse problem and offers a first-principles derivation for its objective. While this objective happens to be equivalent to RL (with a particular choice of parametric reward), there exist other objectives for fine-tuning LMs which are no longer equivalent to RL. That observation leads to a more general point: RL is not an adequate formal framework for problems such as fine-tuning language models. These problems are best viewed as Bayesian inference: approximating a pre-defined target distribution.

ASR Error Detection (AED) models aim to post-process the output of Automatic Speech Recognition (ASR) systems, in order to detect transcription errors. Modern approaches usually use text-based input, comprised solely of the ASR transcription hypothesis, disregarding additional signals from the ASR model. Instead, we utilize the ASR system’s word-level confidence scores for improving AED performance. Specifically, we add an ASR Confidence Embedding (ACE) layer to the AED model’s encoder, allowing us to jointly encode the confidence scores and the transcribed text into a contextualized representation. Our experiments show the benefits of ASR confidence scores for AED, their complementary effect over the textual signal, as well as the effectiveness and robustness of ACE for combining these signals. To foster further research, we publish a novel AED dataset consisting of ASR outputs on the LibriSpeech corpus with annotated transcription errors.