Computation and Language (cs.CL)

Abstract: A series of datasets and models have been proposed for summaries generated for well-formatted documents such as news articles. Dialogue summaries, however, have been under explored. In this paper, we present the first dataset with fine-grained factual error annotations named DIASUMFACT. We define fine-grained factual error detection as a sentence-level multi-label classification problem, and we evaluate two state-of-the-art (SOTA) models on our dataset. Both models yield sub-optimal results, with a macro-averaged F1 score of around 0.25 over 6 error classes. We further propose an unsupervised model ENDERANKER via candidate ranking using pretrained encoder-decoder models. Our model performs on par with the SOTA models while requiring fewer resources. These observations confirm the challenges in detecting factual errors from dialogue summaries, which call for further studies, for which our dataset and results offer a solid foundation.

Abstract: Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be constantly updated to incorporate new classes, and the drift in decision boundary may lead to severe forgetting. This fundamental challenge, however, has not yet been studied extensively, especially in the setting where no samples from old classes are stored for rehearsal. In this paper, we take a closer look at how the drift in the classifier leads to forgetting, and accordingly, design four simple yet (super-) effective solutions to alleviate the classifier drift: an Individual Classifiers with Frozen Feature Extractor (ICE) framework where we individually train a classifier for each learning session, and its three variants ICE-PL, ICE-O, and ICE-PL&O which further take the logits of previously learned classes from old sessions or a constant logit of an Other class as a constraint to the learning of new classifiers. Extensive experiments and analysis on 6 class-incremental information extraction tasks demonstrate that our solutions, especially ICE-O, consistently show significant improvement over the previous state-of-the-art approaches with up to 44.7% absolute F-score gain, providing a strong baseline and insights for future research on class-incremental learning.

Abstract: Current pre-trained language models have enabled remarkable improvements in downstream tasks, but it remains difficult to distinguish effects of statistical correlation from more systematic logical reasoning grounded on the understanding of real world. We tease these factors apart by leveraging counterfactual conditionals, which force language models to predict unusual consequences based on hypothetical propositions. We introduce a set of tests from psycholinguistic experiments, as well as larger-scale controlled datasets, to probe counterfactual predictions from five pre-trained language models. We find that models are consistently able to override real-world knowledge in counterfactual scenarios, and that this effect is more robust in case of stronger baseline world knowledge -- however, we also find that for most models this effect appears largely to be driven by simple lexical cues. When we mitigate effects of both world knowledge and lexical cues to test knowledge of linguistic nuances of counterfactuals, we find that only GPT-3 shows sensitivity to these nuances, though this sensitivity is also non-trivially impacted by lexical associative factors.

Abstract: Through the use of first name substitution experiments, prior research has demonstrated the tendency of social commonsense reasoning models to systematically exhibit social biases along the dimensions of race, ethnicity, and gender (An et al., 2023). Demographic attributes of first names, however, are strongly correlated with corpus frequency and tokenization length, which may influence model behavior independent of or in addition to demographic factors. In this paper, we conduct a new series of first name substitution experiments that measures the influence of these factors while controlling for the others. We find that demographic attributes of a name (race, ethnicity, and gender) and name tokenization length are both factors that systematically affect the behavior of social commonsense reasoning models.

Abstract: As natural language processing (NLP) has recently seen an unprecedented level of excitement, and more people are eager to enter the field, it is unclear whether current research reproducibility efforts are sufficient for this group of beginners to apply the latest developments. To understand their needs, we conducted a study with 93 students in an introductory NLP course, where students reproduced the results of recent NLP papers. Surprisingly, we find that their programming skill and comprehension of research papers have a limited impact on their effort spent completing the exercise. Instead, we find accessibility efforts by research authors to be the key to success, including complete documentation, better coding practice, and easier access to data files. Going forward, we recommend that NLP researchers pay close attention to these simple aspects of open-sourcing their work, and use insights from beginners' feedback to provide actionable ideas on how to better support them.

Abstract: With a growing focus on morphological inflection systems for languages where high-quality data is scarce, training data noise is a serious but so far largely ignored concern. We aim at closing this gap by investigating the types of noise encountered within a pipeline for truly unsupervised morphological paradigm completion and its impact on morphological inflection systems: First, we propose an error taxonomy and annotation pipeline for inflection training data. Then, we compare the effect of different types of noise on multiple state-of-the-art inflection models. Finally, we propose a novel character-level masked language modeling (CMLM) pretraining objective and explore its impact on the models' resistance to noise. Our experiments show that various architectures are impacted differently by separate types of noise, but encoder-decoders tend to be more robust to noise than models trained with a copy bias. CMLM pretraining helps transformers, but has lower impact on LSTMs.

Abstract: With the widespread use of large language models (LLMs) in NLP tasks, researchers have discovered the potential of Chain-of-thought (CoT) to assist LLMs in accomplishing complex reasoning tasks by generating intermediate steps. However, human thought processes are often non-linear, rather than simply sequential chains of thoughts. Therefore, we propose Graph-of-Thought (GoT) reasoning, which models human thought processes not only as a chain but also as a graph. By representing thought units as nodes and connections between them as edges, our approach captures the non-sequential nature of human thinking and allows for a more realistic modeling of thought processes. Similar to Multimodal-CoT, we modeled GoT reasoning as a two-stage framework, generating rationales first and then producing the final answer. Specifically, we employ an additional graph-of-thoughts encoder for GoT representation learning and fuse the GoT representation with the original input representation through a gated fusion mechanism. We implement a GoT reasoning model on the T5 pre-trained model and evaluate its performance on a text-only reasoning task (GSM8K) and a multimodal reasoning task (ScienceQA). Our model achieves significant improvement over the strong CoT baseline with 3.41% and 5.08% on the GSM8K test set with T5-base and T5-large architectures, respectively. Additionally, our model boosts accuracy from 84.91% to 91.54% using the T5-base model and from 91.68% to 92.77% using the T5-large model over the state-of-the-art Multimodal-CoT on the ScienceQA test set. Experiments have shown that GoT achieves comparable results to Multimodal-CoT(large) with over 700M parameters, despite having fewer than 250M backbone model parameters, demonstrating the effectiveness of GoT.

Abstract: Paraphrase generation is a long-standing task in natural language processing (NLP). Supervised paraphrase generation models, which rely on human-annotated paraphrase pairs, are cost-inefficient and hard to scale up. On the other hand, automatically annotated paraphrase pairs (e.g., by machine back-translation), usually suffer from the lack of syntactic diversity -- the generated paraphrase sentences are very similar to the source sentences in terms of syntax. In this work, we present ParaAMR, a large-scale syntactically diverse paraphrase dataset created by abstract meaning representation back-translation. Our quantitative analysis, qualitative examples, and human evaluation demonstrate that the paraphrases of ParaAMR are syntactically more diverse compared to existing large-scale paraphrase datasets while preserving good semantic similarity. In addition, we show that ParaAMR can be used to improve on three NLP tasks: learning sentence embeddings, syntactically controlled paraphrase generation, and data augmentation for few-shot learning. Our results thus showcase the potential of ParaAMR for improving various NLP applications.

Abstract: The emergent capabilities of Large Language Models (LLMs) have made it crucial to align their values with those of humans. Current methodologies typically attempt alignment with a homogeneous human value and requires human verification, yet lack consensus on the desired aspect and depth of alignment and resulting human biases. In this paper, we propose A2EHV, an Automated Alignment Evaluation with a Heterogeneous Value system that (1) is automated to minimize individual human biases, and (2) allows assessments against various target values to foster heterogeneous agents. Our approach pivots on the concept of value rationality, which represents the ability for agents to execute behaviors that satisfy a target value the most. The quantification of value rationality is facilitated by the Social Value Orientation framework from social psychology, which partitions the value space into four categories to assess social preferences from agents' behaviors. We evaluate the value rationality of eight mainstream LLMs and observe that large models are more inclined to align neutral values compared to those with strong personal values. By examining the behavior of these LLMs, we contribute to a deeper understanding of value alignment within a heterogeneous value system.

Abstract: Parameter-efficient tuning (PET) methods fit pre-trained language models (PLMs) to downstream tasks by either computing a small compressed update for a subset of model parameters, or appending and fine-tuning a small number of new model parameters to the pre-trained network. Hand-designed PET architectures from the literature perform well in practice, but have the potential to be improved via automated neural architecture search (NAS). We propose an efficient NAS method for learning PET architectures via structured and unstructured pruning. We present experiments on GLUE demonstrating the effectiveness of our algorithm and discuss how PET architectural design choices affect performance in practice.

Abstract: Norms, which are culturally accepted guidelines for behaviours, can be integrated into conversational models to generate utterances that are appropriate for the socio-cultural context. Existing methods for norm recognition tend to focus only on surface-level features of dialogues and do not take into account the interactions within a conversation. To address this issue, we propose NormMark, a probabilistic generative Markov model to carry the latent features throughout a dialogue. These features are captured by discrete and continuous latent variables conditioned on the conversation history, and improve the model's ability in norm recognition. The model is trainable on weakly annotated data using the variational technique. On a dataset with limited norm annotations, we show that our approach achieves higher F1 score, outperforming current state-of-the-art methods, including GPT3.

Abstract: $k$-Nearest neighbor machine translation ($k$NN-MT) has attracted increasing attention due to its ability to non-parametrically adapt to new translation domains. By using an upstream NMT model to traverse the downstream training corpus, it is equipped with a datastore containing vectorized key-value pairs, which are retrieved during inference to benefit translation. However, there often exists a significant gap between upstream and downstream domains, which hurts the retrieval accuracy and the final translation quality. To deal with this issue, we propose a novel approach to boost the datastore retrieval of $k$NN-MT by reconstructing the original datastore. Concretely, we design a reviser to revise the key representations, making them better fit for the downstream domain. The reviser is trained using the collected semantically-related key-queries pairs, and optimized by two proposed losses: one is the key-queries semantic distance ensuring each revised key representation is semantically related to its corresponding queries, and the other is an L2-norm loss encouraging revised key representations to effectively retain the knowledge learned by the upstream NMT model. Extensive experiments on domain adaptation tasks demonstrate that our method can effectively boost the datastore retrieval and translation quality of $k$NN-MT.\footnote{Our code is available at \url{https://github.com/DeepLearnXMU/RevisedKey-knn-mt}.}

Abstract: Question generation (QG) is the task of generating a valid and fluent question based on a given context and the target answer. According to various purposes, even given the same context, instructors can ask questions about different concepts, and even the same concept can be written in different ways. However, the evaluation for QG usually depends on single reference-based similarity metrics, such as n-gram-based metric or learned metric, which is not sufficient to fully evaluate the potential of QG methods. To this end, we propose to paraphrase the reference question for a more robust QG evaluation. Using large language models such as GPT-3, we created semantically and syntactically diverse questions, then adopt the simple aggregation of the popular evaluation metrics as the final scores. Through our experiments, we found that using multiple (pseudo) references is more effective for QG evaluation while showing a higher correlation with human evaluations than evaluation with a single reference.