ACL 2023 论文列表

Semi-supervised learning has been an important approach to address challenges in extracting entities and relations from limited data. However, current semi-supervised works handle the two tasks (i.e., Named Entity Recognition and Relation Extraction) separately and ignore the cross-correlation of entity and relation instances as well as the existence of similar instances across unlabeled data. To alleviate the issues, we propose Jointprop, a Heterogeneous Graph-based Propagation framework for joint semi-supervised entity and relation extraction, which captures the global structure information between individual tasks and exploits interactions within unlabeled data. Specifically, we construct a unified span-based heterogeneous graph from entity and relation candidates and propagate class labels based on confidence scores. We then employ a propagation learning scheme to leverage the affinities between labelled and unlabeled samples. Experiments on benchmark datasets show that our framework outperforms the state-of-the-art semi-supervised approaches on NER and RE tasks. We show that the joint semi-supervised learning of the two tasks benefits from their codependency and validates the importance of utilizing the shared information between unlabeled data.

Efficient finetuning of pretrained language transformers is becoming increasingly prevalent for solving natural language processing tasks. While effective, it can still require a large number of tunable parameters. This can be a drawback for low-resource applications and training with differential-privacy constraints, where excessive noise may be introduced during finetuning. To this end, we propose a novel language transformer finetuning strategy that introduces task-specific parameters in multiple transformer layers. These parameters are derived from fixed random projections of a single trainable vector, enabling finetuning with significantly fewer parameters while maintaining performance. We achieve within 5% of full finetuning performance on GLUE tasks with as few as 4,100 parameters per task, outperforming other parameter-efficient finetuning approaches that use a similar number of per-task parameters. Besides, the random projections can be precomputed at inference, avoiding additional computational latency. All these make our method particularly appealing for low-resource applications. Finally, our method achieves the best or comparable utility compared to several recent finetuning methods when training with the same privacy constraints, underscoring its effectiveness and potential real-world impact.

Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool. In this work, we investigate and use pseudo-labeling for a recently proposed novel setup: joint transcription and translation of speech, which suffers from an absence of sufficient parallel data resources. We show that under such data-deficient circumstances, the unlabeled data can significantly vary in domain from the supervised data, which results in pseudo-label quality degradation. We investigate two categories of remedies that require no additional supervision and target the domain mismatch: pseudo-label filtering and data augmentation. We show that pseudo-label analysis and processing in this way results in additional gains on top of the vanilla pseudo-labeling setup providing a total improvement of up to 0.4% absolute WER and 2.1 BLEU points for En–De and 0.6% absolute WER and 2.2 BLEU points for En–Zh.

Generate-then-rank is a widely used mechanism for text generation, where a generator produces multiple text candidates and a ranker chooses the best one among the text candidates. However, existing methods usually train the generator and the ranker individually, neglecting the mutual feedback that could further enhance the generation quality. To tackle this limitation, we propose JGR, a novel joint training algorithm that integrates the generator and the ranker in a single framework. JGR optimizes the generator with a hybrid objective that combines data likelihood and ranker reward, and trains the ranker with a contrastive loss that compares the generator outputs. By iteratively updating the generator and the ranker, JGR can effectively harmonize their learning and enhance their quality jointly. We evaluate JGR on various text generation tasks and demonstrate that it surpasses existing methods on four public datasets across three common generation scenarios. Our code and models are publicly available at https://github.com/microsoft/ProphetNet/tree/master/JGR.

Semantic proto-role labeling (SPRL) assigns properties to arguments based on a series of binary labels. While multiple studies have evaluated various approaches to SPRL, it has only been studied in-depth as a standalone task using gold predicate/argument pairs. How do SPRL systems perform as part of an information extraction pipeline? We model SPRL jointly with predicate-argument extraction using a deep transformer model. We find that proto-role labeling is surprisingly robust in this setting, with only a small decrease when using predicted arguments. We include a detailed analysis of each component of the joint system, and an error analysis to understand correlations in errors between system stages. Finally, we study the effects of annotation errors on SPRL.

We solve the challenging document-level event extraction problem by proposing a joint exaction methodology that can avoid inefficiency and error propagation issues in classic pipeline methods. Essentially, we address the three crucial limitations in existing studies. First, the autoregressive strategy of path expansion heavily relies on the orders of argument role. Second, the number of events in documents must be specified in advance. Last, unexpected errors usually exist when decoding events based on the entity-entity adjacency matrix. To address these issues, this paper designs a Token-Token Bidirectional Event Completed Graph (TT-BECG) in which the relation eType-Role1-Role2 serves as the edge type, precisely revealing which tokens play argument roles in an event of a specific event type. Exploiting the token-token adjacency matrix of the TT-BECG, we develop an edge-enhanced joint document-level event extraction model. Guided by the target token-token adjacency matrix, the predicted token-token adjacency matrix can be obtained during the model training. Then, extracted events and event records in a document are decoded based on the predicted matrix, including the graph structure and edge type decoding. Extensive experiments are conducted on two public datasets, and the results confirm the effectiveness of our method and its superiority over the state-of-the-art baselines.

Emotion-Cause Pair Extraction (ECPE) aims to identify the document’s emotion clauses and corresponding cause clauses. Like other relation extraction tasks, ECPE is closely associated with the relationship between sentences. Recent methods based on Graph Convolutional Networks focus on how to model the multiplex relations between clauses by constructing different edges. However, the data of emotions, causes, and pairs are extremely unbalanced, and current methods get their representation using the same graph structure. In this paper, we propose a **J**oint **C**onstrained Learning framework with **B**oundary-adjusting for Emotion-Cause Pair Extraction (**JCB**). Specifically, through constrained learning, we summarize the prior rules existing in the data and force the model to take them into consideration in optimization, which helps the model learn a better representation from unbalanced data. Furthermore, we adjust the decision boundary of classifiers according to the relations between subtasks, which have always been ignored. No longer working independently as in the previous framework, the classifiers corresponding to three subtasks cooperate under the relation constraints. Experimental results show that **JCB** obtains competitive results compared with state-of-the-art methods and prove its robustness on unbalanced data.

Commonsense reasoning simulates the human ability to make presumptions about our physical world, and it is an essential cornerstone in building general AI systems. We proposea new commonsense reasoning dataset based on human’s Interactive Fiction (IF) gameplaywalkthroughs as human players demonstrate plentiful and diverse commonsense reasoning. The new dataset provides a natural mixture of various reasoning types and requires multi-hopreasoning. Moreover, the IF game-based construction procedure requires much less humaninterventions than previous ones. Different from existing benchmarks, our dataset focuseson the assessment of functional commonsense knowledge rules rather than factual knowledge. Hence, in order to achieve higher performance on our tasks, models need to effectively uti-lize such functional knowledge to infer the outcomes of actions, rather than relying solely onmemorizing facts. Experiments show that the introduced dataset is challenging to previousmachine reading models as well as the new large language models with a significant 20%performance gap compared to human experts.

We introduce SexTok, a multi-modal dataset composed of TikTok videos labeled as sexually suggestive (from the annotator’s point of view), sex-educational content, or neither. Such a dataset is necessary to address the challenge of distinguishing between sexually suggestive content and virtual sex education videos on TikTok. Children’s exposure to sexually suggestive videos has been shown to have adversarial effects on their development (Collins et al. 2017). Meanwhile, virtual sex education, especially on subjects that are more relevant to the LGBTQIA+ community, is very valuable (Mitchell et al. 2014). The platform’s current system removes/punishes some of both types of videos, even though they serve different purposes. Our dataset contains video URLs, and it is also audio transcribed. To validate its importance, we explore two transformer-based models for classifying the videos. Our preliminary results suggest that the task of distinguishing between these types of videos is learnable but challenging. These experiments suggest that this dataset is meaningful and invites further study on the subject.

Unsupervised domain adaptation of machine translation, which adapts a pre-trained translation model to a specific domain without in-domain parallel data, has drawn extensive attention in recent years. However, most existing methods focus on the fine-tuning based techniques, which is non-extensible. In this paper, we propose a new method to perform unsupervised domain adaptation in a non-parametric manner. Our method only resorts to in-domain monolingual data, and we jointly perform nearest neighbour inference on both forward and backward translation directions. The forward translation model creates nearest neighbour datastore for the backward direction, and vice versa, strengthening each other in an iterative style. Experiments on multi-domain datasets demonstrate that our method significantly improves the in-domain translation performance and achieves state-of-the-art results among non-parametric methods.

The lexical knowledge of NLP systems shouldbe tested (i) for their internal consistency(avoiding groundedness issues) and (ii) bothfor content words and logical words. In thispaper we propose a new method to test the understandingof the hypernymy relationship bymeasuring its antisymmetry according to themodels. Previous studies often rely only on thedirect question (e.g., A robin is a ...), where weargue a correct answer could only rely on collocationalcues, rather than hierarchical cues. We show how to control for this, and how it isimportant. We develop a method to ask similarquestions about logical words that encode anentailment-like relation (e.g., because or therefore).Our results show important weaknessesof BERT-like models on these semantic tasks.

Progress in NLP is increasingly measured through benchmarks; hence, contextualizing progress requires understanding when and why practitioners may disagree about the validity of benchmarks. We develop a taxonomy of disagreement, drawing on tools from measurement modeling, and distinguish between two types of disagreement: 1) how tasks are conceptualized and 2) how measurements of model performance are operationalized. To provide evidence for our taxonomy, we conduct a meta-analysis of relevant literature to understand how NLP tasks are conceptualized, as well as a survey of practitioners about their impressions of different factors that affect benchmark validity. Our meta-analysis and survey across eight tasks, ranging from coreference resolution to question answering, uncover that tasks are generally not clearly and consistently conceptualized and benchmarks suffer from operationalization disagreements. These findings support our proposed taxonomy of disagreement. Finally, based on our taxonomy, we present a framework for constructing benchmarks and documenting their limitations.

Data annotation is the process of labeling data that could be used to train machine learning models. Having high quality annotation is crucial, as it allows the model to learn the relationship between the input data and the desired output. GPT-3, a large-scale language model developed by OpenAI, has demonstrated im- impressive zero- and few-shot performance on a wide range of NLP tasks. It is therefore natural to wonder whether it can be used to effectively annotate data for NLP tasks. In this paper, we evaluate the performance of GPT-3 as a data annotator by comparing it with traditional data annotation methods and analyzing its output on a range of tasks. Through this analysis, we aim to provide insight into the potential of GPT-3 as a general-purpose data annotator in NLP.

Out-of-distribution (OOD) detection is a critical task for reliable predictions over text. Fine-tuning with pre-trained language models has been a de facto procedure to derive OOD detectors with respect to in-distribution (ID) data. Despite its common use, the understanding of the role of fine-tuning and its necessity for OOD detection is largely unexplored. In this paper, we raise the question: is fine-tuning necessary for OOD detection? We present a study investigating the efficacy of directly leveraging pre-trained language models for OOD detection, without any model fine-tuning on the ID data. We compare the approach with several competitive fine-tuning objectives, and offer new insights under various types of distributional shifts. Extensive experiments demonstrate near-perfect OOD detection performance (with 0% FPR95 in many cases), strongly outperforming the fine-tuned counterpart.

The broad adoption of continuous prompts has brought state-of-the-art results on a diverse array of downstream natural language processing (NLP) tasks. Nonetheless, little attention has been paid to the interpretability and transferability of continuous prompts. Faced with the challenges, we investigate the feasibility of interpreting continuous prompts as the weighting of discrete prompts by jointly optimizing prompt fidelity and downstream fidelity. Our experiments show that: (1) one can always find a combination of discrete prompts as the replacement of continuous prompts that performs well on downstream tasks; (2) our interpretable framework faithfully reflects the reasoning process of source prompts; (3) our interpretations provide effective readability and plausibility, which is helpful to understand the decision-making of continuous prompts and discover potential shortcuts. Moreover, through the bridge constructed between continuous prompts and discrete prompts using our interpretations, it is promising to implement the cross-model transfer of continuous prompts without extra training signals. We hope this work will lead to a novel perspective on the interpretations of continuous prompts.

In the last few years, several studies have been devoted to dissecting dense text representations in order to understand their effectiveness and further improve their quality. Particularly, the anisotropy of such representations has been observed, which means that the directions of the word vectors are not evenly distributed across the space but rather concentrated in a narrow cone. This has led to several attempts to counteract this phenomenon both on static and contextualized text representations. However, despite this effort, there is no established relationship between anisotropy and performance. In this paper, we aim to bridge this gap by investigating the impact of different transformations on both the isotropy and the performance in order to assess the true impact of anisotropy. To this end, we rely on the clustering task as a means of evaluating the ability of text representations to produce meaningful groups. Thereby, we empirically show a limited impact of anisotropy on the expressiveness of sentence representations both in terms of directions and L2 closeness.

We examine the behaviour of an aspect-based sentiment classifier built by fine-tuning the BERT BASE model on the SemEval 2016 English dataset. In a set of masking experiments, we examine the extent to which the tokens identified as salient by LIME and a gradient-based method are being used by the classifier. We find that both methods are able to produce faithful rationales, with LIME outperforming the gradient-based method. We also identify a set of manually annotated sentiment expressions for this dataset, and carry out more masking experiments with these as human rationales. The enhanced performance of a classifier that only sees the relevant sentiment expressions suggests that they are not being used to their full potential. A comparison of the LIME and gradient rationales with the sentiment expressions reveals only a moderate level of agreement. Some disagreements are related to the fixed length of the rationales and the tendency of the rationales to contain content words related to the aspect itself.

Natural logic reasoning has received increasing attention lately, with several datasets and neural models proposed, though with limited success. More recently, a new class of works have emerged adopting a Neuro-Symbolic approach, called transformer guided chaining, whereby the idea is to iteratively perform 1-step neural inferences and chain together the results to generate a multi-step reasoning trace. Several works have adapted variants of this central idea and reported significantly high accuracies compared to vanilla LLM’s. In this paper, we perform a critical empirical investigation of the chaining approach on a multi-hop First-Order Logic (FOL) reasoning benchmark. In particular, we develop a reference implementation, called Chainformer, and conduct several experiments to analyze the accuracy, generalization, interpretability, and performance over FOLs. Our findings highlight key strengths and possible current limitations and suggest potential areas for future research in logic reasoning.

While pre-trained Chinese language models have demonstrated impressive performance on a wide range of NLP tasks, the Chinese Spell Checking (CSC) task remains a challenge. Previous research has explored using information such as glyphs and phonetics to improve the ability of CSC models to distinguish misspelled characters, with good results at the accuracy level on public datasets. However, the generalization ability of these CSC models has not been well understood: it is unclear whether they incorporate glyph-phonetic information and, if so, whether this information is fully utilized. In this paper, we aim to better understand the role of glyph-phonetic information in the CSC task and suggest directions for improvement. Additionally, we propose a new, more challenging, and practical setting for testing the generalizability of CSC models. All code is made publicly available.