Ireland

In this paper, we try to answer “How Pre-trained Language Models Capture Factual Knowledge” by quantitatively measuring and evaluating the word-level patterns that PLMs depend on to capture the factual words. We check the words that have three typical associations with the missing words: knowledge-dependent, positionally close, and highly co-occurred. Our analysis shows: (1) PLMs generate the missing factual words more by the positionally close and highly co-occurred words than the knowledge-dependent words; (2) the dependence on the knowledge-dependent words is more effective than the positionally close and highly co-occurred words. Accordingly, we conclude that the PLMs capture the factual knowledge ineffectively because depending on the inadequate associations.

ACL 2022

How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis

interpretation for nlp models

factual knowledge probing

pre-trained language models

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks. Posters (including Findings of ACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. 

 
We wish you a wonderful conference! 
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
 
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing) 
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing) 
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing (NLP). 

findings / work in progress

Relation linking (RL) is a vital module in knowledge-based question answering (KBQA) systems. It aims to link the relations expressed in natural language (NL) to the corresponding ones in knowledge graph (KG). Existing methods mainly rely on the textual similarities between NL and KG to build relation links. Due to the ambiguity of NL and the incompleteness of KG, many relations in NL are implicitly expressed, and may not link to a single relation in KG, which challenges the current methods. In this paper, we propose an implicit RL method called ImRL, which links relation phrases in NL to relation paths in KG. To find proper relation paths, we propose a novel path ranking model that aligns not only textual information in the word embedding space but also structural information in the KG embedding space between relation phrases in NL and relation paths in KG. Besides, we leverage a gated mechanism with attention to inject prior knowledge from external paraphrase dictionaries to address the relation phrases with vague meaning. Our experiments on two benchmark and a newly-created datasets show that ImRL significantly outperforms several state-of-the-art methods, especially for implicit RL.

Implicit Relation Linking for Question Answering over Knowledge Graph

Relation extraction (RE) is an important natural language processing task that predicts the relation between two given entities, where a good understanding of the contextual information is essential to achieve an outstanding model performance. Among different types of contextual information, the auto-generated syntactic information (namely, word dependencies) has shown its effectiveness for the task. However, most existing studies require modifications to the existing baseline architectures (e.g., adding new components, such as GCN, on the top of an encoder) to leverage the syntactic information. To offer an alternative solution, we propose to leverage syntactic information to improve RE by training a syntax-induced encoder on auto-parsed data through dependency masking. Specifically, the syntax-induced encoder is trained by recovering the masked dependency connections and types in first, second, and third orders, which significantly differs from existing studies that train language models or word embeddings by predicting the context words along the dependency paths. Experimental results on two English benchmark datasets, namely, ACE2005EN and SemEval 2010 Task 8 datasets, demonstrate the effectiveness of our approach for RE, where our approach outperforms strong baselines and achieve state-of-the-art results on both datasets.

Improving Relation Extraction through Syntax-induced Pre-training with Dependency Masking

Current practices in metric evaluation mainly focus on one single dataset from a targeted domain, e.g., News domain in each year's WMT Metrics Shared Task. In this paper, we qualitatively and quantitatively show that the performances of metrics are sensitive to data even when the data is from the same domain, i.e., the ranking of metrics varies when the evaluation is conducted on different datasets from the same domain. Then this paper further investigates 
two potential hypotheses, i.e., insignificant data points and the deviation of Independent and Identically Distributed (i.i.d) assumption, which may take responsibility for the issue of data variance. In conclusion, our findings suggest that when evaluating automatic translation metrics, researchers should take data variance into account and be cautious to claim the result on a single dataset even from the same domain, because it may lead to inconsistent results with most other datasets.

Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics

Keyphrase extraction (KPE) automatically extracts phrases in a document that provide a concise summary of the core content, which benefits downstream information retrieval and NLP tasks. Previous state-of-the-art methods select candidate keyphrases based on the similarity between learned representations of the candidates and the document. They suffer performance degradation on long documents due to discrepancy between sequence lengths which causes mismatch between representations of keyphrase candidates and the document. In this work, we propose a novel unsupervised embedding-based KPE approach, Masked Document Embedding Rank (MDERank), to address this problem by leveraging a mask strategy and ranking candidates by the similarity between embeddings of the source document and the masked document. We further develop a KPE-oriented BERT (KPEBERT) model by proposing a novel self-supervised contrastive learning method, which is more compatible to MDERank than vanilla BERT. Comprehensive evaluations on six KPE benchmarks demonstrate that the proposed MDERank outperforms state-of-the-art unsupervised KPE approach by average 1.80 F1@15 improvement. MDERank further benefits from KPEBERT and overall achieves average 3.53 F1@15 improvement over SIFRank.

MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction

Task weighting, which assigns weights on the including tasks during training, significantly matters the performance of Multi-task Learning (MTL); thus, recently, there has been an explosive interest in it. However, existing task weighting methods assign weights only based on the training loss, while ignoring the gap between the training loss and generalization loss. It degenerates MTL's performance. To address this issue, the present paper proposes a novel task weighting algorithm, which automatically weights the tasks via a learning-to-learn paradigm, referred to as MetaWeighting. Extensive experiments are conducted to validate the superiority of our proposed method in multi-task text classification.

MetaWeighting: Learning to Weight Tasks in Multi-Task Learning

Recent research has made impressive progress in large-scale multimodal pretraining. In the context of the rapid growth of the model size, it is necessary to seek efficient and flexible methods other than finetuning. In this paper, we propose to use prompt vectors to align the modalities. Our method achieves comparable performance to several other multimodal fusion methods in low-resource settings. We further show that our method is modular and parameter-efficient for processing tasks involving two or more data modalities.

Modular and Parameter-Efficient Multimodal Fusion with Prompting

Existing knowledge-grounded dialogue systems typically use finetuned versions of a pretrained language model (LM) and large-scale knowledge bases. These models typically fail to generalize on topics outside of the knowledge base, and require maintaining separate potentially large checkpoints each time finetuning is needed. In this paper, we aim to address these limitations by leveraging the inherent knowledge stored in the pretrained LM as well as its powerful generation ability. We propose a multi-stage prompting approach to generate knowledgeable responses from a single pretrained LM. We first prompt the LM to generate knowledge based on the dialogue context. Then, we further prompt it to generate responses based on the dialogue context and the previously generated knowledge. Results show that our knowledge generator outperforms the state-of-the-art retrieval-based model by 5.8% when combining knowledge relevance and correctness. In addition, our multi-stage prompting outperforms the finetuning-based dialogue model in terms of response knowledgeability and engagement by up to 10% and 5%, respectively.
Furthermore, we scale our model up to 530 billion parameters and show that larger LMs improve the generation correctness score by up to 10%, and response relevance, knowledgeability and engagement by up to 10%.

Multi-Stage Prompting for Knowledgeable Dialogue Generation

Several studies have investigated the reasons behind the effectiveness of fine-tuning, usually through the lens of probing. However, these studies often neglect the role of the size of the dataset on which the model is fine-tuned. In this paper, we highlight the importance of this factor and its undeniable role in probing performance. We show that the extent of encoded linguistic knowledge depends on the number of fine-tuning samples. The analysis also reveals that larger training data mainly affects higher layers, and that the extent of this change is a factor of the number of iterations updating the model during fine-tuning rather than the diversity of the training samples. Finally, we show through a set of experiments that fine-tuning data size affects the recoverability of the changes made to the model's linguistic knowledge.

On the Importance of Data Size in Probing Fine-tuned Models

Aligning parallel sentences in multilingual corpora is essential to curating data for downstream applications such as Machine Translation. In this work, we present OneAligner, an alignment model specially designed for sentence retrieval tasks. This model is able to train on only one language pair and transfers, in a cross-lingual fashion, to low-resource language pairs with negligible degradation in performance. When trained with all language pairs of a large-scale parallel multilingual corpus (OPUS-100), this model achieves the state-of-the-art result on the Tateoba dataset, outperforming an equally-sized previous model by 8.0 points in accuracy while using less than 0.6% of their parallel data. When finetuned on a single rich-resource language pair, be it English-centered or not, our model is able to match the performance of the ones finetuned on all language pairs under the same data budget with less than 2.0 points decrease in accuracy. Furthermore, with the same setup, scaling up the number of rich-resource language pairs monotonically improves the performance, reaching a minimum of 0.4 points discrepancy in accuracy, making it less mandatory to collect any low-resource parallel data. Finally, we conclude through empirical results and analyses that the performance of the sentence alignment task depends mostly on the monolingual and parallel data size, up to a certain size threshold, rather than on what language pairs are used for training or evaluation.

OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence Retrieval

Modern NLP classifiers are known to return uncalibrated estimations of class posteriors. Existing methods for posterior calibration rescale the predicted probabilities but often have an adverse impact on final classification accuracy,
thus leading to poorer generalization. We propose an end-to-end trained calibrator, Platt-Binning, that directly optimizes the objective while minimizing the difference between the predicted and empirical posterior probabilities. Our method leverages the sample efficiency of Platt scaling and the verification guarantees of histogram binning, thus not only reducing the calibration error but also improving task performance. In contrast to existing calibrators, we perform this efficient calibration during training. Empirical evaluation of benchmark NLP classification tasks echoes the efficacy of our proposal.

How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis

Downloads

Next from ACL 2022

Implicit Relation Linking for Question Answering over Knowledge Graph

Similar lecture

TextPruner: A Model Pruning Toolkit for Pre-Trained Language Models