Ireland

We show some interesting findings of applying Structured Pruning on Multilingual Pre-trained Models, and also present a simple method for more efficient pruning.

ACL 2022

Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency

multilingual pre-trained models

structured pruning

empirical study

# 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). 

poster

Word sense disambiguation (WSD) is a crucial problem in the natural language processing (NLP) community. Current methods achieve decent performance by utilizing supervised learning and large pre-trained language models. However, the imbalanced training dataset leads to poor performance on rare senses and zero-shot senses. There are more training instances and senses for words with top frequency ranks than those with low frequency ranks in the training dataset. We investigate the statistical relation between word frequency rank and word sense number distribution. Based on the relation, we propose a Z-reweighting method on the word level to adjust the training on the imbalanced dataset. The experiments show that the Z-reweighting strategy achieves performance gain on the standard English all words WSD benchmark. Moreover, the strategy can help models generalize better on rare and zero-shot senses.

Rare and Zero-shot Word Sense Disambiguation using Z-Reweighting

Simultaneous machine translation (SiMT) starts translating while receiving the streaming source inputs, and hence the source sentence is always incomplete during translating. Different from the full-sentence MT using the conventional seq-to-seq architecture, SiMT often applies prefix-to-prefix architecture, which forces each target word to only align with a partial source prefix to adapt to the incomplete source in streaming inputs. However, the source words in the front positions are always illusoryly considered more important since they appear in more prefixes, resulting in position bias, which makes the model pay more attention on the front source positions in testing. In this paper, we first analyze the phenomenon of position bias in SiMT, and develop a Length-Aware Framework to reduce the position bias by bridging the structural gap between SiMT and fullsentence MT. Specifically, given the streaming inputs, we first predict the full-sentence length and then fill the future source position with positional encoding, thereby turning the streaming inputs into a pseudo full-sentence. The proposed framework can be integrated into most existing SiMT methods to further improve performance. Experiments on two representative SiMT methods, including the state-of-the-art adaptive policy, show that our method successfully reduces the position bias and thereby achieves better SiMT performance.

Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework

Natural language processing models learn word representations based on the distributional hypothesis, which asserts that word context (e.g., co-occurrence) correlates with meaning. We propose that n-grams composed of random character sequences, or garble, provide a novel context for studying word meaning both within and beyond extant language. In particular, randomly generated character n-grams lack meaning but contain primitive information based on the distribution of characters they contain. By studying the embeddings of a large corpus of garble, extant language, and pseudowords using CharacterBERT, we identify an axis in the model's high-dimensional embedding space that separates these classes of n-grams. Furthermore, we show that this axis relates to structure within extant language, including word part-of-speech, morphology, and concept concreteness. Thus, in contrast to studies that are mainly limited to extant language, our work reveals that meaning and primitive information are intrinsically linked.

Signal in Noise: Exploring Meaning Encoded in Random Character Sequences with Character-Aware Language Models

Knowledge graph completion (KGC) aims to reason over known facts and infer the missing links. Text-based methods such as KG-BERT (Yao et al., 2019) learn entity representations from natural language descriptions, and have the potential for inductive KGC. However, the performance of text-based methods still largely lag behind graph embedding-based methods like TransE (Bordes et al., 2013) and RotatE (Sun et al., 2019b). In this paper, we identify that the key issue is efficient contrastive learning. To improve the learning efficiency, we introduce three types of negatives: in-batch negatives, pre-batch negatives, and self-negatives which act as a simple form of hard negatives. Combined with InfoNCE loss, our proposed model SimKGC can substantially outperform embedding-based methods on several benchmark datasets. In terms of mean reciprocal rank (MRR), we advance the state-of-the-art by +19% on WN18RR, +6.8% on the Wikidata5M transductive setting, and +22% on the Wikidata5M inductive setting. Thorough analyses are conducted to gain insights into each component. Our code is available at https://github.com/intfloat/SimKGC

SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models

Tangled multi-party dialogue contexts lead to challenges for dialogue reading comprehension, where multiple dialogue threads flow simultaneously within a common dialogue record, increasing difficulties in understanding the dialogue history for both human and machine. Previous studies mainly focus on utterance encoding methods with carefully designed features but pay inadequate attention to characteristic features of the structure of dialogues. We specially take structure factors into account and design a novel model for dialogue disentangling. Based on the fact that dialogues are constructed on successive participation and interactions between speakers, we model structural information of dialogues in two aspects: 1)speaker property that indicates whom a message is from, and 2) reference dependency that shows whom a message may refer to. The proposed method achieves new state-of-the-art on the Ubuntu IRC benchmark dataset and contributes to dialogue-related comprehension.

Structural Characterization for Dialogue Disentanglement

Recent works on knowledge base question answering (KBQA) retrieve subgraphs for easier reasoning. The desired subgraph is crucial as a small one may exclude the answer but a large one might introduce more noises. However, the existing retrieval is either heuristic or interwoven with the reasoning, causing reasoning on the partial subgraphs, which increases the reasoning bias when the intermediate supervision
is missing. This paper proposes a trainable subgraph retriever (SR) decoupled from
the subsequent reasoning process, which enables a plug-and-play framework to enhance any subgraph-oriented KBQA model. Extensive experiments demonstrate SR achieves significantly better retrieval and QA performance than existing retrieval methods. Via weakly supervised pre-training as well as the end-to-end fine-tuning, SR achieves new state-of-the-art performance when combined with NSM (He
et al., 2021), a subgraph-oriented reasoner, for embedding-based KBQA methods. Codes and datasets are available online.

Subgraph Retrieval Enhanced Model  for Multi-hop Knowledge Base Question Answering

Summarizing biomedical discovery from genomics data using natural languages is an essential step in biomedical research but is mostly done manually. Here, we introduce Textomics, a novel dataset of genomics data description, which contains 22,273 pairs of genomics data matrices and their summaries. Each summary is written by the researchers who generated the data and associated with a scientific paper. Based on this dataset, we study two novel tasks: generating textual summary from a genomics data matrix and vice versa. Inspired by the successful applications of k nearest neighbors in modeling genomics data, we propose a kNN-Vec2Text model to address these tasks and observe substantial improvement on our dataset. We further illustrate how Textomics can be used to advance other applications, including evaluating scientific paper embeddings and generating masked templates for scientific paper understanding. Textomics serves as the first benchmark for generating textual summaries for genomics data and we envision it will be broadly applied to other biomedical and natural language processing applications.

Textomics: A Dataset for Genomics Data Summary Generation

The evolution of language follows the rule of gradual change. Grammar, vocabulary, and lexical semantic shifts take place over time, resulting in a diachronic linguistic gap. As such, a considerable amount of texts are written in languages of different eras, which creates obstacles for natural language processing tasks, such as word segmentation and machine translation. Although the Chinese language has a long history, previous Chinese natural language processing research has primarily focused on tasks within a specific era. Therefore, we propose a cross-era learning framework for Chinese word segmentation (CWS), CROSSWISE, which uses the Switch-memory (SM) module to incorporate era-specific linguistic knowledge. Experiments on four corpora from different eras show that the performance of each corpus significantly improves. Further analyses also demonstrate that the SM can effectively integrate the knowledge of the eras into the neural network.

That Slepen Al the Nyght with Open Ye! Cross-era Sequence Segmentation with Switch-memory

Although contextualized embeddings generated from large-scale pre-trained models perform well in many tasks, traditional static embeddings (e.g., Skip-gram, Word2Vec) still play an important role in low-resource and lightweight settings due to their low computational cost, ease of deployment, and stability. In this paper, we aim to improve word embeddings by 1) incorporating more contextual information from existing pre-trained models into the Skip-gram framework, which we call Context-to-Vec; 2) proposing a post-processing retrofitting method for static embeddings independent of training by employing priori synonym knowledge and weighted vector distribution. Through extrinsic and intrinsic tasks, our methods are well proven to outperform the baselines by a large margin.

Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings

For a natural language understanding benchmark to be useful in research, it has to consist of examples that are diverse and difficult enough to discriminate among current and near-future state-of-the-art systems. However, we do not yet know how best to select text sources to collect a variety of challenging examples. In this study, we crowdsource multiple-choice reading comprehension questions for passages taken from seven qualitatively distinct sources, analyzing what attributes of passages contribute to the difficulty and question types of the collected examples. To our surprise, we find that passage source, length, and readability measures do not significantly affect question difficulty. Through our manual annotation of seven reasoning types, we observe several trends between passage sources and reasoning types, e.g., logical reasoning is more often required in questions written for technical passages. These results suggest that when creating a new benchmark dataset, selecting a diverse set of passages can help ensure a diverse range of question types, but that passage difficulty need not be a priority.

Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency

Downloads

Next from ACL 2022

Rare and Zero-shot Word Sense Disambiguation using Z-Reweighting

Similar lecture

Structured Pruning Learns Compact and Accurate Models