Korea, Republic of

Recently, Mixture-of-Experts (short as MoE) architecture has achieved remarkable success in increasing the model capacity of large-scale language models. However, MoE requires incorporating significantly more parameters than the base model being extended. In this paper, we propose building a parameter-efficient MoE architecture by sharing information across experts. We adopt the matrix product operator (MPO, a tensor decomposition from quantum many-body physics) to reconstruct the parameter matrix in the expert layer and increase model capacity for pre-trained language models by sharing parameters of the central tensor (containing the core information) among different experts while enabling the specificity through the auxiliary tensors (complementing the central tensor) of different experts. To address the unbalanced optimization issue, we further design the gradient mask strategy for the MPO-based MoE architecture. Extensive experiments based on T5 and GPT-2 show improved performance and efficiency of the pre-trained language model (27.2x reduction in total parameters for the superior model performance, compared with the Switch Transformers).

COLING 2022

Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models

mixture-of-expert

tensor decomposition

pre-trained language model

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference! 
 
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, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
 
Posters (including Findings of NAACL 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 and will have an oral session and a poster session.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

NAACL 2022

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

technical paper

[![](https://assets.underline.io/uploads/markdown_image/1/image/81a3c0317d24f663b49b996875024d45.png)](https://aclanthology.org/volumes/2022.coling-1/)



### THE CONFERENCE WE KNOW AND WE WANT.
**COLING**, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes but also in industrial research departments including tech-startups. COLING provides opportunities for all these communities to showcase their exciting discovery.

In fall of 2022, COLING will be held in Gyeongju in a hybrid format. All participants can either present at the venue site or join virtually. As more people get vaccinated, we are happy to provide safer environments for our colleagues. We believe that COLING 2022 will be one of the conferences, free from the pandemic. The hybrid format gives presenters and sponsors a valuable opportunity to promote their companies in both an online and in-person venue. For the first time in a long time, customers can interact with their sponsor's products first-hand. The online venue, too, gives sponsors the chance to network with those unable to attend the in-person session.

The hybrid format ultimately lends itself to greater exposure for our sponsors: COLING2022 will let you reach more potential partners and customers than ever before!

To gain access to this event page you are required to register. Find more information and pay the registration fee on event the organizer’s website **[https://coling2022.org/reg](https://coling2022.org/reg)**

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

Extracting spatial relations from texts is a fundamental task for natural language understanding and previous studies only regard it as a classification task, ignoring those spatial relations with null roles due to their poor information. To address the above issue, we first view spatial relation extraction as a generation task and propose a novel hybrid model HMCGR for this task. HMCGR contains a generation and a classification model, while the former can generate those null-role relations and the latter can extract those non-null-role relations to complement each other. Moreover, a reflexivity evaluation mechanism is applied to further improve the accuracy based on the reflexivity principle of spatial relation. Experimental results on SpaceEval show that HMCGR outperforms the SOTA baselines significantly.

A Hybrid Model of Classification and Generation for Spatial Relation Extraction

Text-to-SQL has attracted attention from both the natural language processing and database communities because of its ability to convert the semantics in natural language into SQL queries and its practical application in building natural language interfaces to database systems. The major challenges in text-to-SQL lie in encoding the meaning of natural utterances, decoding to SQL queries, and translating the semantics between these two forms. These challenges have been addressed to different extents by the recent advances. How- ever, there is still a lack of comprehensive surveys for this task. To this end, we review recent progress on text-to-SQL for datasets, methods, and evaluation and provide this systematic survey, addressing the aforementioned challenges and discussing potential future directions. We hope that this survey can serve as quick access to existing work and motivate future research.

Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect

Pre-trained models have brought remarkable success on the text summarization task. For dialogue summarization, the subdomain of text summarization, utterances are concatenated to flat text before being processed. As a result, existing summarization systems based on pre-trained models are unable to recognize the unique format of the speaker-utterance pair well in the dialogue. To investigate this issue, we conduct probing tests and manual analysis, and find that the powerful pre-trained model can not identify different speakers well in the conversation, which leads to various factual errors. Moreover, we propose three speaker-aware supervised contrastive learning (SCL) tasks: Token-level SCL, Turn-level SCL, and Global-level SCL. Comprehensive experiments demonstrate that our methods achieve significant performance improvement on two mainstream dialogue summarization datasets. According to detailed human evaluations, pre-trained models equipped with SCL tasks effectively generate summaries with better factual consistency.

Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning

Abstractive dialogue summarization aims to convert a long dialogue content into its short form where the salient information is preserved, while the redundant pieces are ignored. Different from the well-structured text, such as news and scientific articles, dialogues often consist of utterances coming from two or more interlocutors, where the conversations are often informal, verbose, and repetitive, sprinkled with false-starts, backchanneling, reconfirmations, hesitations, speaker interruptions and the salient information is often scattered across the whole chat. The above properties of conversations make it difficult to directly concentrate on scattered outstanding utterances and thus present new challenges of summarizing dialogues. In this work, we propose to explicitly have the model perceive the redundant parts of an input dialogue history, so that the model is able to pay more attention to the salient pieces. To be specific, we design two strategies to construct examples without salient pieces as negative cues. Then, the sequence-to-sequence likelihood loss is cooperated with the unlikelihood objective to drive the model focus less on the unimportant information as well as pay more attention to the salient pieces. Extensive experiments on the benchmark dataset demonstrate that our simple method outperforms baselines with regard to both semantic matching and factual consistent based metrics. The human evaluation also proves the performance gains led by our approach.

Summarizing Dialogues with Negative Cues

Building query graphs from natural language
questions is an important step in complex question answering over knowledge graph (Complex KGQA). In general, a question can be correctly answered if its query graph is built correctly and the right answer is then retrieved by
issuing the query graph against the KG. Therefore, this paper focuses on query graph generation from natural language questions. Existing approaches for query graph generation
ignore the semantic structure of a question, resulting in a large number of noisy query graph
candidates that undermine prediction accuracies. In this paper, we define six semantic
structures from common questions in KGQA
and develop a novel Structure-BERT to predict the semantic structure of a question. By
doing so, we can first filter out noisy candidate query graphs, and then rank the remaining
candidates with a BERT-based ranking model.
Extensive experiments on two popular benchmarks MetaQA and WebQuestionsSP (WSP)
demonstrate the effectiveness of our method as
compared to state-of-the-arts.

Semantic Structure based Query Graph Prediction for Question Answering over Knowledge Graph

The International Classification of Diseases (ICD) is the foundation of global health statistics and epidemiology. The ICD is designed to translate health conditions into alphanumeric codes. A number of approaches have been proposed for automatic ICD coding, since manual coding is labor-intensive and there is a global shortage of healthcare workers. However, existing studies did not exploit the discourse structure of clinical notes, which provides rich contextual information for code assignment. In this paper, we exploit the discourse structure by leveraging section type classification and section type embeddings. We also focus on the class-imbalanced problem and the heterogeneous writing style between clinical notes and ICD code definitions. The proposed reconciled embedding approach is able to tackle them simultaneously. Experimental results on the MIMIC dataset show that our model outperforms all previous state-of-the-art models by a large margin.
The source code is available at https://github.com/discnet2022/discnet


Automatic ICD coding exploiting discourse structure and reconciled code embeddings

Unsupervised contrastive sentence embedding models, e.g., unsupervised SimCSE, use the InfoNCE loss function in training. Theoretically, we expect to use larger batches to get more adequate comparisons among samples and avoid overfitting. However, increasing batch size leads to performance degradation when it exceeds a threshold, which is probably due to the introduction of false-negative pairs through statistical observation. To alleviate this problem, we introduce a simple smoothing strategy upon the InfoNCE loss function, termed Gaussian Smoothed InfoNCE (GS-InfoNCE). In other words, we add random Gaussian noise as an extension to the negative pairs without increasing the batch size. Through experiments on the semantic text similarity tasks, though simple, the proposed smoothing strategy brings improvements to unsupervised SimCSE.

Smoothed Contrastive Learning for Unsupervised Sentence Embedding

We examine the inducement of rare but severe errors in English-Chinese and Chinese-English in-domain neural machine translation by minimal deletion of the source text with character-based models. By deleting a single character, we can induce severe translation errors. We categorize these errors and compare the results of deleting single characters and single words. We also examine the effect of training data size on the number and types of pathological cases induced by these minimal perturbations, finding significant variation. We find that deleting a word hurts overall translation score more than deleting a character, but certain errors are more likely to occur when deleting characters, with language direction also influencing the effect.

Rare but Severe Neural Machine Translation Errors Induced by Minimal Deletion: An Empirical Study on Chinese and English

In-the-Wild Video Question Answering

Entity linking, which aims at aligning ambiguous entity mentions to their referent entities in a knowledge base, plays a key role in multiple natural language processing tasks. Recently, zero-shot entity linking task has become a research hotspot, which links mentions to unseen entities to challenge the generalization ability. For this task, the training set and test set are from different domains, and thus entity linking models tend to be overfitting due to the tendency of memorizing the properties of entities that appear frequently in the training set. We argue that general ultra-fine-grained type information can help the linking models to learn contextual commonality and improve their generalization ability to tackle the overfitting problem. However, in the zero-shot entity linking setting, any type information is not available and entities are only identified by textual descriptions. Thus, we first extract the ultra-fine type information from the entity textual descriptions. Then, we propose a hierarchical multi-task model to improve the high-level zero-shot entity linking candidate generation task by utilizing the entity typing task as an auxiliary low-level task, which introduces extracted ultra-fine type information into the candidate generation task. Experimental results demonstrate the effectiveness of utilizing the ultra-fine entity type information and our proposed method achieves state-of-the-art performance.

Premium content

Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models

Downloads

Next from COLING 2022

A Hybrid Model of Classification and Generation for Spatial Relation Extraction

Similar lecture

Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations