Representation learning on graph has been demonstrated to be a powerful tool for solving real-world problems. Text-attributed graph carries both semantic and structural information among different types of graphs. Existing works have paved the way for knowledge extraction of this type of data by leveraging language models or graph neural networks or combination of them. However, these works suffer from issues like underutilization of relationships between nodes or words or unaffordable memory cost. In this paper, we propose a Node Representation Update Pre-training Architecture based on Co-modeling Text and Graph (NRUP). In NRUP, we construct a hierarchical text-attributed graph that incorporates both original nodes and word nodes. Meanwhile, we apply four self-supervised tasks for different level of constructed graph. We further design the pre-training framework to update the features of nodes during training epochs. We conduct the experiment on the benchmark dataset ogbn-arxiv. Our method achieves outperformance compared to baselines, fully demonstrating its validity and generalization.
论文检索
输入标题、作者或关键词，从 7,591 篇学术成果中精准定位
We present an accurate and interpretable method for answer extraction in machine reading comprehension that is reminiscent of case-based reasoning (CBR) from classical AI. Our method (CBR-MRC) builds upon the hypothesis that contextualized answers to similar questions share semantic similarities with each other. Given a test question, CBR-MRC first retrieves a set of similar cases from a nonparametric memory and then predicts an answer by selecting the span in the test context that is most similar to the contextualized representations of answers in the retrieved cases. The semi-parametric nature of our approach allows it to attribute a prediction to the specific set of evidence cases, making it a desirable choice for building reliable and debuggable QA systems. We show that CBR-MRC provides high accuracy comparable with large reader models and outperforms baselines by 11.5 and 8.4 EM on NaturalQuestions and NewsQA, respectively. Further, we demonstrate the ability of CBR-MRC in identifying not just the correct answer tokens but also the span with the most relevant supporting evidence. Lastly, we observe that contexts for certain question types show higher lexical diversity than others and find that CBR-MRC is robust to these variations while performance using fully-parametric methods drops.
Injecting structural hints: Using language models to study inductive biases in language learning
PDF ↗Both humans and transformer language models are able to learn language without explicit structural supervision. What cognitive inductive biases make this learning possible? Here, we examine the effect of different inductive learning biases by actively controlling the inductive biases of artificial learners: we structurally bias models by pretraining on synthetic formally-structured data, and evaluate these structural biases by fine-tuning on three typologically-distant human languages: English, Japanese, and Basque. We investigate the effect on downstream language perplexity of three types of inductive bias: 1) recursive, hierarchical processing 2) unrestricted token-token dependencies that can’t be modeled by context-free grammars, and 3) a Zipfian power-law vocabulary distribution. We show that complex, non-context-free interactions between tokens form the best inductive biases. Our study leverages the capabilities of transformer models to run controlled language learning experiments that are not possible to run on humans, and surfaces hypotheses about the structures that facilitate language learning in both humans and machines.
Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs
PDF ↗In comparative linguistics, colexification refers to the phenomenon of a lexical form conveying two or more distinct meanings. Existing work on colexification patterns relies on annotated word lists, limiting scalability and usefulness in NLP. In contrast, we identify colexification patterns of more than 2,000 concepts across 1,335 languages directly from an unannotated parallel corpus. We then propose simple and effective methods to build multilingual graphs from the colexification patterns: ColexNet and ColexNet+. ColexNet’s nodes are concepts and its edges are colexifications. In ColexNet+, concept nodes are additionally linked through intermediate nodes, each representing an ngram in one of 1,334 languages. We use ColexNet+ to train ColexNet+, high-quality multilingual embeddings that are well-suited for transfer learning. In our experiments, we first show that ColexNet achieves high recall on CLICS, a dataset of crosslingual colexifications. We then evaluate ColexNet+ on roundtrip translation, sentence retrieval and sentence classification and show that our embeddings surpass several transfer learning baselines. This demonstrates the benefits of using colexification as a source of information in multilingual NLP.
Recently, much research in psychology has benefited from the advances in machine learning techniques. Some recent studies showed that it is possible to build automated scoring models for children’s mindreading. These models were trained on a set of manually-labeled question-response pairs, which were collected by asking children to answer one or two questions after a short story is told or a video clip is played. However, existing models did not take the features of the stories and video clips into account when scoring, which obviously will reduce the accuracy of the scoring models. Furthermore, considering that different psychological tests may contain the same questions, this approach cannot be extended to other related psychological test datasets. In this study, we proposed a multi-modal learning framework to leverage the features extracted from the stories and videos related to the questions being asked during the children’s mindreading evaluation. Experimental results show that the scores produced by the proposed models agree well with those graded by human experts, highlighting the potential of the proposed network architecture for practical automated children’s mindreading scoring systems.
Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design
PDF ↗Discovering novel catalysts requires complex reasoning involving multiple chemical properties and resultant trade-offs, leading to a combinatorial growth in the search space. While large language models (LLM) have demonstrated novel capabilities for chemistry through complex instruction following capabilities and high quality reasoning, a goal-driven combinatorial search using LLMs has not been explored in detail. In this work, we present a Monte Carlo Tree Search-based approach that improves beyond state-of-the-art chain-of-thought prompting variants to augment scientific reasoning. We introduce two new reasoning datasets: 1) a curation of computational chemistry simulations, and 2) diverse questions written by catalysis researchers for reasoning about novel chemical conversion processes. We improve over the best baseline by 25.8% and find that our approach can augment scientist’s reasoning and discovery process with novel insights.
News recommendation aims to predict click behaviors based on user behaviors. How to effectively model the user representations is the key to recommending preferred news. Existing works are mostly focused on improvements in the supervised fine-tuning stage. However, there is still a lack of PLM-based unsupervised pre-training methods optimized for user representations. In this work, we propose an unsupervised pre-training paradigm with two tasks, i.e. user behavior masking and user behavior generation, both towards effective user behavior modeling. Firstly, we introduce the user behavior masking pre-training task to recover the masked user behaviors based on their contextual behaviors. In this way, the model could capture a much stronger and more comprehensive user news reading pattern. Besides, we incorporate a novel auxiliary user behavior generation pre-training task to enhance the user representation vector derived from the user encoder. We use the above pre-trained user modeling encoder to obtain news and user representations in downstream fine-tuning. Evaluations on the real-world news benchmark show significant performance improvements over existing baselines.
Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained applications. To counter this, our approach is to divide the whole sequence into segments and apply attention to the individual segments. We propose a segmented recurrent transformer (SRformer) that combines segmented (local) attention with recurrent attention. The loss caused by reducing the attention window length is compensated by aggregating information across segments with recurrent attention. SRformer leverages Recurrent Accumulate-and-Fire (RAF) neurons’ inherent memory to update the cumulative product of keys and values. The segmented attention and lightweight RAF neurons ensure the efficiency of the proposed transformer. Such an approach leads to models with sequential processing capability at a lower computation/memory cost. We apply the proposed method to T5 and BART transformers. The modified models are tested on summarization datasets including CNN-dailymail, XSUM, ArXiv, and MediaSUM. Notably, using segmented inputs of varied sizes, the proposed model achieves 6-22% higher ROUGE1 scores than a segmented transformer and outperforms other recurrent transformer approaches. Furthermore, compared to full attention, the proposed model reduces the computational complexity of cross attention by around 40%.
Pronunciation assessment and its application in computer-aided pronunciation training (CAPT) have seen impressive progress in recent years. With the rapid growth in language processing and deep learning over the past few years, there is a need for an updated review. In this paper, we review methods employed in pronunciation assessment for both phonemic and prosodic. We categorize the main challenges observed in prominent research trends, and highlight existing limitations, and available resources. This is followed by a discussion of the remaining challenges and possible directions for future work.
The scaling laws of language models have played a significant role in advancing large language models. In order to promote the development of document translation, we systematically examine the scaling laws in this field. In this paper, we carry out an in-depth analysis of the influence of three factors on translation quality: model scale, data scale, and sequence length. Our findings reveal that increasing sequence length effectively enhances model performance when model size is limited. However, sequence length cannot be infinitely extended; it must be suitably aligned with the model scale and corpus volume. Further research shows that providing adequate context can effectively enhance the translation quality of a document’s initial portion. Nonetheless, exposure bias remains the primary factor hindering further improvement in translation quality for the latter half of the document.
Non-autoregressive models have been widely used for various text generation tasks to accelerate the inference process but at the cost of generation quality to some extent. To achieve a good balance between inference speedup and generation quality, iterative NAR models like CMLM and Disco are proposed. Researchers have made much follow-up progress based on them, and some recent iterative models can achieve very promising performance while maintaining significant speedup. In this paper, we give more insights into iterative NAR models by exploring the anisotropic problem, i.e., the representations of distinct predicted target tokens are similar and indiscriminative. Upon the confirmation of the anisotropic problem in iterative NAR models, we first analyze the effectiveness of the contrastive learning method and further propose the Look Neighbors strategy to enhance the learning of token representations during training. Experiments on 4 WMT datasets show that our methods consistently improve the performance as well as alleviate the anisotropic problem of the conditional masked language model, even outperforming the current SoTA result on WMT14 EN \rightarrow DE.
Data Maps (Swayamdipta, et al. 2020) have emerged as a powerful tool for diagnosing large annotated datasets. Given a model fitted on a dataset, these maps show each data instance from the dataset in a 2-dimensional space defined by a) the model’s confidence in the true class and b) the variability of this confidence. In previous work, confidence and variability are usually computed using training dynamics, which requires the fitting of a strong model to the dataset. In this paper, we introduce a novel approach: Zero-Shot Data Maps based on fast bi-encoder networks. For each data point, confidence on the true label and variability are computed over the members of an ensemble of zero-shot models constructed with different — but semantically equivalent — label descriptions, i.e., textual representations of each class in a given label space. We conduct a comparative analysis of maps compiled using traditional training dynamics and our proposed zero-shot models across various datasets. Our findings reveal that Zero-Shot Data Maps generally match those produced by the traditional method while delivering up to a 14x speedup. The code is available [here](https://github.com/symanto-research/zeroshot-cartography).
“You Are An Expert Linguistic Annotator”: Limits of LLMs as Analyzers of Abstract Meaning Representation
PDF ↗Large language models (LLMs) demonstrate an amazing proficiency and fluency in the \textit{use} of language. Does that mean that they have also acquired insightful linguistic knowledge \textit{about} the language, to an extent that they can serve as an “expert linguistic annotator’? In this paper, we examine the successes and limitations of the GPT-3, ChatGPT, and GPT-4 models, focusing on the Abstract Meaning Representation (AMR) parsing formalism (Banarescu et al., 2013), which provides rich graphical representations of sentence meaning structure while abstracting away from surface forms. We compare models’ analysis of this semantic structure across two settings: 1) direct production of AMR parses based on zero- and few-shot examples, and 2) indirect partial reconstruction of AMR via metalinguistic natural language queries (e.g., “Identify the primary event of this sentence, and the predicate corresponding to that event.”). Across these settings, we find that models can reliably reproduce the basic format of AMR, as well as some core event, argument, and modifier structure-however, model outputs are prone to frequent and major errors, and holistic analysis of parse acceptability shows that even with few-shot demonstrations, models have virtually 0% success in producing fully accurate parses. Eliciting responses in natural language produces similar patterns of errors. Overall, our findings indicate that these models out-of-the-box can accurately identify some core aspects of semantic structure, but there remain key limitations in their ability to support fully accurate semantic analyses or parses.
While recent large language models (LLMs) improve on various question answering (QA) datasets, it remains difficult for a single model to generalize across question types that require distinct reasoning abilities. We provide empirical evidence that state-of-the-art LLMs suffer from poor generalizability on reasoning types beyond those seen in the prompt. To remedy this, we propose a Mixture-of-Reasoning-Experts (MORE) framework that ensembles diverse specialized language models. We specialize the backbone language model with prompts optimized for different reasoning categories, including factual, multihop, mathematical, and commonsense reasoning. Our key insight is to leverage agreement among the specialized experts to select the best answer for each question, or to abstain from answering. This gives MORE higher accuracy than any single specialized model on a collection of 12 QA datasets from four reasoning types. Beyond generalizability, the interpretable design of MORE improves selective question answering results compared to baselines without incorporating inter-expert agreement. This framework is also more interpretable and useful to human consumers of QA outputs. Our human study confirms that presenting expert predictions and the answer selection process helps annotators more accurately calibrate when to trust the system’s output. We release all code and data to facilitate future work.
When we communicate with other humans, we do not simply generate a sequence of words. Rather, we use our cognitive state (beliefs, desires, intentions) and our model of the audience’s cognitive state to create utterances that affect the audience’s cognitive state in the intended manner. An important part of cognitive state is the common ground, which is the content the speaker believes, and the speaker believes the audience believes, and so on. While much attention has been paid to common ground in cognitive science, there has not been much work in natural language processing. In this paper, we introduce a new annotation and corpus to capture common ground. We then describe some initial experiments extracting propositions from dialog and tracking their status in the common ground from the perspective of each speaker.
Question-answering (QA) tasks often investigate specific question types, knowledge domains, or reasoning skills, leading to specialized models catering to specific categories of QA tasks. While recent research has explored the idea of unified QA models, such models are usually explored for high-resource scenarios and require re-training to extend their capabilities. To overcome these drawbacks, the paper explores the potential of two paradigms of tuning, model, and prompts, for unified QA under a low-resource setting. The paper provides an exhaustive analysis of their applicability using 16 QA datasets, revealing that prompt tuning can perform as well as model tuning in a few-shot setting with a good initialization. The study also shows that parameter-sharing results in superior few-shot performance, simple knowledge transfer techniques for prompt initialization can be effective, and prompt tuning achieves a significant performance boost from pre-training in a low-resource regime. The research offers insights into the advantages and limitations of prompt tuning for unified QA in a few-shot setting, contributing to the development of effective and efficient systems in low-resource scenarios.
Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrieval
PDF ↗Multi-document summarization (MDS) assumes a set of topic-related documents are provided as input. In practice, this document set is not always available; it would need to be retrieved given an information need, i.e. a question or topic statement, a setting we dub “open-domain’ MDS. We study this more challenging setting by formalizing the task and bootstrapping it using existing datasets, retrievers and summarizers. Via extensive automatic and human evaluation, we determine: (1) state-of-the-art summarizers suffer large reductions in performance when applied to open-domain MDS, (2) additional training in the open-domain setting can reduce this sensitivity to imperfect retrieval, and (3) summarizers are insensitive to the retrieval of duplicate documents and the order of retrieved documents, but highly sensitive to other errors, like the retrieval of irrelevant documents. Based on our results, we provide practical guidelines to enable future work on open-domain MDS, e.g. how to choose the number of retrieved documents to summarize. Our results suggest that new retrieval and summarization methods and annotated resources for training and evaluation are necessary for further progress in the open-domain setting.
GSAP-NER: A Novel Task, Corpus, and Baseline for Scholarly Entity Extraction Focused on Machine Learning Models and Datasets
PDF ↗Named Entity Recognition (NER) models play a crucial role in various NLP tasks, including information extraction (IE) and text understanding. In academic writing, references to machine learning models and datasets are fundamental components of various computer science publications and necessitate accurate models for identification. Despite the advancements in NER, existing ground truth datasets do not treat fine-grained types like ML model and model architecture as separate entity types, and consequently, baseline models cannot recognize them as such. In this paper, we release a corpus of 100 manually annotated full-text scientific publications and a first baseline model for 10 entity types centered around ML models and datasets. In order to provide a nuanced understanding of how ML models and datasets are mentioned and utilized, our dataset also contains annotations for informal mentions like “our BERT-based model” or “an image CNN”. You can find the ground truth dataset and code to replicate model training at https://data.gesis.org/gsap/gsap-ner.
This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to provide additional supervision signals, a stronger model may be learned through knowledge distillation. However, the vanilla DistillCSE through the standard implementation of knowledge distillation only achieves marginal improvements. The quantitative analyses demonstrate its reason that the standard knowledge distillation exhibits a relatively large variance of the teacher model’s logits due to the essence of contrastive learning. To mitigate the issue induced by high variance, this paper accordingly proposed two simple yet effective solutions for knowledge distillation: a Group-P shuffling strategy as an implicit regularization and the averaging logits from multiple teacher components. Experiments on standard benchmarks demonstrate that the proposed DistillCSE outperforms many strong baseline methods and yields a new state-of-the-art performance.
Blackbird language matrices (BLM), a new task for rule-like generalization in neural networks: Can Large Language Models pass the test?
PDF ↗How do we evaluate Large Language Models (LLMs) and determine the aspects and limits of their intelligent behaviour? It is currently conjectured that shortcomings of LLMs in multi-linguality and reasoning are due to a lack of ability to generalize. It has been argued that, instead, humans are better at generalization because they have a tendency at extracting rules from complex data. We propose a method to evaluate LLMs ability to rule-based generalization. When exposed to tests of analytic intelligence, for example the visual RAVEN IQ test, human problem-solvers identify the relevant objects in the picture and their relevant attributes and reason based on rules applied to them. Based on the induced rules, they are able to provide a generalisation and a solution to the test. An analogous language task has recently been proposed (called BLM) for LLM. In this paper, we argue that we can use this task to investigate what linguistic reasoning LLM develop, by asking them to solve some simple variants of the BLM task. We find that current state-of-the-art generative models, such as ChatGPT, can handle the task in the sense that they easily understand the instructions and can provide step-by-step reasoning that shows that it can solve two of the main cognitive hurdles: correspondence finding (object and attribute identification) and item novelty. However, overall they cannot find the correct answer, even with considerable help. In particular, they never identify the structure of the problem, exhibiting, we hypothesize, a lack of goal and subgoal management abilities, an ability that has been argued to measure differential abilities in humans. We argue that this finding supports the usefulness of the task as a method to test the limits and specific properties of generalisation ability in Large Language Models, providing an intrinsic evaluation method inspired by tests of human intelligence.